--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/claude-vs-librechat/" data_url: "https://onaihq.com/compare/agents/claude-vs-librechat/data.json" generated_at: 2026-10-27 last_checked_at: 2026-10-26 last_cross_checked_at: 2026-10-26 next_check_at: 2026-12-20 publisher: "onAI" --- # Claude Team / Enterprise vs LibreChat > Published by onAI. onAI also sells one of the products compared here. Findings about other products link to public sources so you can check them; statements about onAI are marked as stated by onAI. > Claude Team / Enterprise lifecycle: sunset. Standalone Claude Design at claude.ai/design is scheduled to close on December 14, 2026; design creation continues inside Claude Artifacts. Scope: Only standalone Claude Design at claude.ai/design. This is not a sunset of Claude Team or Enterprise chat, Cowork or in-Claude Design. Continuation: Claude Artifacts Design inside Claude; the admin guide describes existing Design projects appearing there. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-artifacts-admin. This comparison has 46 criteria with sourced findings for both products, including 46 that a second agent cross-checked for both. 51 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation: they are scoped, fresh and cite public resolved sources. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. "Stated by onAI" marks the publisher's own statements about its product (evidence type vendor-statement), which cite no third-party source. Humans approve the rubric, templates and generator; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent. - Claude Team / Enterprise source checks: 2026-10-21 to 2026-10-26. - LibreChat source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/claude-vs-librechat/ - Machine-readable JSON: https://onaihq.com/compare/agents/claude-vs-librechat/data.json - Methodology: https://onaihq.com/compare/agents/methodology/ ## Models ### MOD-01: Model catalogue and providers Judgment rule: List each available model by provider and plan, including reasoning, fast and multimodal variants. Record whether the user picks the model, the product routes automatically, or both. A provider counts only if at least one of its current models is selectable on the scoped plan. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team and Enterprise offer Anthropic model families with seat-specific Fable billing and visible safety fallback; organization controls can restrict the picker. Availability: unknown Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Hosted commercial Chat documentation checked 2026-10-26; plan=Team Standard/Premium; current usage-based Enterprise; legacy seat-based Enterprise only where explicitly identified; add_ons=Usage credits for Fable on Team Standard and legacy Enterprise Standard; consumption billed separately on current Enterprise; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - current_models: The current selector/context guides list Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1, plus older choices. Pricing includes the Opus/Sonnet/Haiku families on Team and Enterprise. Fable 5/5.1 use paid credits on Team Standard and legacy Enterprise Standard, a capped included share on Premium, and API-rate consumption on current Enterprise. Admin restrictions can remove access; no authenticated tenant picker was observed. - user_choice: Users select a chat model and effort from the menu; changes apply to the next response. Enterprise model controls may restrict choices. Office and Cowork defaults are scoped separately. - auto_routing: Fable 5/5.1 safety fallback is enabled by default and may rerun a flagged request on an Opus model in the same chat. A visible notice and responding-model label disclose the switch, and users can disable it. General task-complexity routing is not established. - multimodal_input: The chat attachment guide documents images/PDF/documents; exact per-model modality and paid-seat compatibility remains unverified. - providers — Which model providers are available? [supported]: The commercial plan table includes Anthropic Fable, Opus, Sonnet and Haiku families; this is a single-provider hosted chat catalogue. Sources: claude:cl-pricing-20261026. - current_models — Which current models are selectable on this plan? [partial]: The current selector/context guides list Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1, plus older choices. Pricing includes the Opus/Sonnet/Haiku families on Team and Enterprise. Fable 5/5.1 use paid credits on Team Standard and legacy Enterprise Standard, a capped included share on Premium, and API-rate consumption on current Enterprise. Admin restrictions can remove access; no authenticated tenant picker was observed. Sources: claude:cl-model-menu-r2-20261026, claude:cl-context-plans-r2-20261026, claude:cl-pricing-20261026, claude:claude:fable-plan-20261026. - user_choice — Can users pick the model per chat? [partial]: Users select a chat model and effort from the menu; changes apply to the next response. Enterprise model controls may restrict choices. Office and Cowork defaults are scoped separately. Sources: claude:cl-model-menu-r2-20261026, claude:cl-model-control-20261026. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [partial]: Fable 5/5.1 safety fallback is enabled by default and may rerun a flagged request on an Opus model in the same chat. A visible notice and responding-model label disclose the switch, and users can disable it. General task-complexity routing is not established. Sources: claude:claude:transparent-fallback-20261026, claude:claude:fable-plan-20261026. - multimodal_input — Which models accept images, audio or files? [partial]: The chat attachment guide documents images/PDF/documents; exact per-model modality and paid-seat compatibility remains unverified. Sources: claude:cl-upload-r2-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-model-menu-r2-20261026, claude:cl-context-plans-r2-20261026, claude:cl-upload-r2-20261026, claude:cl-pricing-20261026, claude:claude:fable-plan-20261026, claude:cl-model-control-20261026, claude:claude:transparent-fallback-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The model catalog is configured by the customer across first-party provider integrations and custom endpoints. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - providers: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. - current_models: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. - auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. - providers — Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - current_models — Which current models are selectable on this plan? [partial]: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. Sources: librechat:librechat:releases. - user_choice — Can users pick the model per chat? [supported]: Users choose an endpoint/model unless admins enforce model specs or a fixed Agent. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [unknown]: auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input — Which models accept images, audio or files? [partial]: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. Sources: librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr ### MOD-02: Model freshness Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Release notes and scoped retirement notices exist; comparative lag and pinning remain open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: release_lag_days, version_pinning. - Read each atomic answer for its plan, access and feature limits. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: What was the lag for each of the last three major releases, per provider? Unverified after checking release notes and Haiku notice; three provider/product release-date pairs and persistent enterprise model pinning not verified. - changelog — Is there a dated public model changelog? [supported]: Claude publishes dated model and product release notes. Sources: claude:cl-release. - deprecation_notice — How much notice is given before a model is removed? [partial]: Haiku 4.5 consumer removal has October 15-to-29 notice, explicitly excluding Team/Enterprise. A general commercial-model notice period was not established. Sources: claude:cl-haiku-notice. - version_pinning — Can an admin keep an older model version? [unknown]: Can an admin keep an older model version? Unverified after checking release notes and Haiku notice; three provider/product release-date pairs and persistent enterprise model pinning not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-release, claude:cl-haiku-notice #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - changelog — Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases. - deprecation_notice — How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning — Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom ### MOD-03: Bring-your-own keys and provider contracts Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Office add-ins advertise customer cloud credentials; that does not establish BYO inference in regular Claude chat. Availability: generally-available Delivery: native Scope: surfaces=Claude for Microsoft 365 official add-ins, Claude Team and Enterprise web workspaces; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Office add-ins; regular Team/Enterprise chat only as an explicit gap; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: own_api_keys, custom_endpoint, byo_pricing, byo_restrictions. - Read each atomic answer for its plan, access and feature limits. - own_api_keys — Can the customer use its own provider API keys? [unknown]: Can the customer use its own provider API keys? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [partial]: Claude for Microsoft 365 advertises Foundry, Bedrock and Gemini Enterprise Agent Platform credentials. Regular Claude chat BYO cloud-account support remains unverified. Sources: claude:cl-office. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [unknown]: Can an admin add any OpenAI-compatible endpoint? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. - byo_pricing — Does BYO change the licence price? [unknown]: Does BYO change the licence price? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. - byo_restrictions — Which features stop working with BYO? [unknown]: Which features stop working with BYO? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. - own_api_keys — Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom. - byo_pricing — Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat. - byo_restrictions — Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code ### MOD-04: Local and self-hosted models Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work. #### Claude Team / Enterprise Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg. - feature_parity — Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code. - vendor_hosted_open_models — Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code ### MOD-05: Model control and usage limits Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has model/effort ceilings and ordinary defaults; always-start enforcement is a separate beta with project exceptions. Availability: beta Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Enterprise organization/custom-role model access and defaults; Always start with the default model and effort level is beta; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Beta applies specifically to forced starting model/effort; ordinary model ceilings and defaults are documented separately. Team entitlement is not inferred. - Existing chat-project selection is an explicit exception. No two-group/model restriction fixture; Chrome/Security and client-version coverage limits still apply. - model_allowlist_by_group — Can admins limit models per group? [partial]: Enterprise organization model/effort ceilings constrain custom roles; Haiku cannot be disabled. Per-source data-binding rules remain unverified. Sources: claude:cl-model-control-r2. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: Can admins restrict which models receive connector or knowledge content? Unverified after checking Claude Team/Enterprise pricing, identity, connector, privacy and release documentation retrieved 2026-10-21; no paid organization or shared fixture. - default_model — Can admins set the default model? [partial]: Enterprise can choose an ordinary organization/role default. The Always start switch is beta, still permits in-chat switching, and does not override remembered choices in existing chat projects. New projects and new project Cowork tasks use the default; unavailable product models fall back to Anthropic's recommendation. Sources: claude:cl-default-r2. - user_limits — What per-user message or token limits apply, and are they published? [supported]: Current usage-based Enterprise has no included token allowance or seat usage cap; Team/legacy plans differ. Sources: claude:cl-enterprise. - limit_behaviour — What happens when a limit is reached? [partial]: Disabling an enabled Enterprise model can require fallback or explicit switching; default selection is not permission to access a disabled model. Spend-limit enforcement remains separate. Sources: claude:cl-model-control-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-model-control-r2, claude:cl-default-r2, claude:cl-enterprise #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. - data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. - model_allowlist_by_group — Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - default_model — Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec. - user_limits — What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod. - limit_behaviour — What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin ## Company knowledge ### KNOW-01: Files in chat Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Chat attachments, project knowledge files and code/file tools have separate published limits. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team/Enterprise Chat attachments and project Files; enabled Chat code/file path only where explicitly named; add_ons=Code execution/file creation must be enabled for XLSX and the computing/file-tool route; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Limits are assigned to the named UI/repository/tool path rather than treated as conflicting universal maxima. Exact large-attachment transfer into the computing environment remains untested. - Office/Cowork paths are excluded. No long PDF, scan, formula workbook or PowerPoint fixture. - formats — Which formats are accepted? [supported]: Chat attachments support PDF/DOCX/CSV/TXT/HTML/ODT/RTF/EPUB/JSON and XLSX with code execution; JPEG/PNG/GIF/WebP images. This is not an Office/Cowork format matrix. Sources: claude:cl-upload-r2. - limits — What size and count limits apply per file and chat? [partial]: Chat Add files/photo attachments:500 MB/file,20/chat, PDF 1000-page maximum. Project Files:30 MB/file. The separate code/file-creation guide specifies30 MB per upload/download in its computing/file-tool path, with a separate larger-PDF processing caveat. A500 MB attachment is not promised to work in that30 MB tool path. Sources: claude:cl-upload-r2, claude:cl-code-files-r2. - ocr — Are scanned PDFs read? [partial]: For Chat PDF processing, up to 100 pages receive visual/text analysis;101–1000 pages text only. Scanned-contract OCR accuracy was not tested. Sources: claude:cl-upload-r2. - spreadsheets — Are Excel tables read with structure intact? [partial]: Chat XLSX uploads require code/file creation; its file-tool guide has a30 MB upload/download limit. Formula/table preservation was not fixture-tested. Sources: claude:cl-upload-r2, claude:cl-code-files-r2. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [partial]: Paid projects switch to search-based RAG near context limits and show an indicator; this does not establish every chat-file reading path. Sources: claude:cl-rag. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-upload-r2, claude:cl-code-files-r2, claude:cl-rag #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Files can be indexed, injected as extracted text or sent directly to compatible model providers. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - File counts, sizes and provider acceptance depend on deployment settings. - Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested. - formats — Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg. - limits — What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr. - ocr — Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr. - spreadsheets — Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current ### KNOW-02: Knowledge bases and shared collections Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Projects persist curated knowledge and instructions and support organizational sharing. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - persistent_collections — Can users keep document collections across chats? [supported]: Projects retain a knowledge base and instructions for related chats. Sources: claude:cl-projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [supported]: Team/Enterprise share projects with organization members; Enterprise groups can receive shared resources. Sources: claude:cl-projects, claude:cl-groups. - size_limits — What are the collection limits? [partial]: Project files have a 30 MB limit; paid RAG expands effective knowledge capacity, with no fixed total capacity verified. Sources: claude:cl-upload, claude:cl-rag. - assistant_binding — Can collections be bound to an assistant? [partial]: Project instructions and knowledge provide persistent task context; binding tools/model into a separately versioned assistant was not fully verified. Sources: claude:cl-projects. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-groups, claude:cl-upload, claude:cl-rag #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. - size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - persistent_collections — Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - assistant_binding — Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr ### KNOW-03: Enterprise connectors Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02). #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial First-party Microsoft/Google connectors and custom MCP provide distinct enterprise-data routes. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - atlassian: Claude Enterprise documents Atlassian Rovo MCP for Jira, Confluence and Teamwork Graph, including organization-managed authorization through Okta. This does not establish a native indexed Confluence connector, universal Team entitlement or observed ACL fidelity. - other_systems: Enterprise docs list GitHub and Slack; Salesforce is a separately approved paid-plan beta in release notes. Box/ServiceNow details remain unverified. - on_prem_sources: Remote MCP must be reachable from Anthropic cloud; Desktop-local MCP is separate and unavailable in cloud chat/Cowork. Named file-share/database connectors were not verified. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: Anthropic-hosted Graph connector covers SharePoint, OneDrive, Outlook and Teams; Claude owner enablement and Entra consent are separate. Sources: claude:cl-m365-20261026. - google_workspace — Which Google sources are connected? [supported]: Gmail, Calendar and Drive are documented with owner enablement and user authorization; live Docs/Sheets/Slides are separate connectors. Sources: claude:cl-google-20261026. - atlassian — Confluence and Jira? [partial]: Claude Enterprise documents Atlassian Rovo MCP for Jira, Confluence and Teamwork Graph, including organization-managed authorization through Okta. This does not establish a native indexed Confluence connector, universal Team entitlement or observed ACL fidelity. Sources: claude:claude:atlassian-enterprise-20261026, claude:cl-mcp-20261026. - other_systems — Which other business systems? [partial]: Enterprise docs list GitHub and Slack; Salesforce is a separately approved paid-plan beta in release notes. Box/ServiceNow details remain unverified. Sources: claude:cl-enterprise-20261026, claude:cl-release-20261026. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Remote MCP must be reachable from Anthropic cloud; Desktop-local MCP is separate and unavailable in cloud chat/Cowork. Named file-share/database connectors were not verified. Sources: claude:cl-mcp-20261026. - connector_provider — Who builds and maintains each connector? [supported]: Microsoft connector is Anthropic-hosted; custom MCP may be built/hosted by the customer or a third party. Sources: claude:cl-m365-20261026, claude:cl-mcp-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-m365-20261026, claude:cl-google-20261026, claude:cl-enterprise-20261026, claude:cl-release-20261026, claude:cl-mcp-20261026, claude:claude:atlassian-enterprise-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. - google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint. - google_workspace — Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian — Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems — Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg. - connector_provider — Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp ### KNOW-04: Permission-aware retrieval Judgment rule: Using two test users, verify that a restricted document in the fixture tenant is never cited or summarised for the user without access, including after a permission change. Record whether permissions are enforced at query time by the source system, mirrored into an index, or not enforced. Record the propagation delay of a revocation. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Documented live-source permissions do not replace the required two-user test. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No observed permission assurance or revocation SLA is established. Shared conversation output can reveal retrieved content to recipients. - source_permissions_respected — Are source permissions enforced per user? [supported]: Microsoft and Google connectors use the connected user account permissions. Sources: claude:cl-m365, claude:cl-google. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [supported]: Microsoft Graph delegated calls check source access; the connector is a proxy without a copied file-content cache. Sources: claude:cl-m365. - revocation_delay — How quickly does a removed permission take effect? [unknown]: How quickly does a removed permission take effect? Unverified after checking connector security and user docs; no restricted-document or revocation-latency fixture. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Owners control connectors/tools; Microsoft Sites.Selected and a SharePoint site allowlist are explicitly unavailable in this connector. Sources: claude:cl-m365-user. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [partial]: The Microsoft security guide says delegated access respects M365 DLP; exact Purview label exclusion behavior was not tested. Sources: claude:cl-m365. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-m365, claude:cl-google, claude:cl-m365-user #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Product resource ACLs and delegated Microsoft file selection are documented. Continuing source permissions for copied content remain untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - enforcement_point: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. - revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - admin_scope_controls: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. - sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - source_permissions_respected — Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. Sources: librechat:librechat:access, librechat:librechat:sharepoint. - revocation_delay — How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. Sources: librechat:librechat:access, librechat:librechat:agents. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:sharepoint, librechat:librechat:agents ### KNOW-05: Freshness and sync model Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Microsoft content is fetched on demand; Google project references have a separate sync path. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: sync_interval, deletion_propagation, index_location. - Read each atomic answer for its plan, access and feature limits. - live_or_indexed — Is content searched live or copied into an index? [partial]: Microsoft uses on-demand Graph access without caching file content. Google Docs attached to private projects sync from Drive. Sources: claude:cl-m365, claude:cl-google. - sync_interval — How often does an index refresh? [unknown]: How often does an index refresh? Unverified after checking Microsoft proxy and Google Workspace docs; full sync interval, deletion propagation and copied-index storage map not measured. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: How quickly does a deleted document disappear? Unverified after checking Microsoft proxy and Google Workspace docs; full sync interval, deletion propagation and copied-index storage map not measured. - index_location — Where is indexed content stored? [unknown]: Where is indexed content stored? Unverified after checking Microsoft proxy and Google Workspace docs; full sync interval, deletion propagation and copied-index storage map not measured. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-m365, claude:cl-google #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - live_or_indexed — Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr. - sync_interval — How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - index_location — Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin ### KNOW-06: Grounding and retrieval quality Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Google-source citations are documented; grounding accuracy remains unmeasured. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No observed accuracy or cross-language retrieval ranking. - citations — Are answers linked to specific sources? [partial]: Google connector answers cite original email/calendar/document sources when available. Sources: claude:cl-google. - citation_accuracy — Do the cited passages support the answer? [unknown]: Do the cited passages support the answer? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. - cross_language — Does a question in one language find documents in another? [unknown]: Does a question in one language find documents in another? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: Does it say when the corpus has no answer? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. - observed_accuracy — How many of the question set were answered correctly? [unknown]: How many of the question set were answered correctly? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-google #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial File-search citations are documented; retrieval accuracy remains unmeasured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - citations — Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language — Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy — How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access ### KNOW-07: Memory and personal context Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Improved memory and legacy memory have different Team/Enterprise administration and Cowork behavior. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise improved Settings>Memory experience; legacy Settings>Capabilities memory is separately qualified; project instructions are independent; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Identify experience by Settings>Memory versus legacy Memory under Settings>Capabilities; neither control set is applied universally. - No organization memory fixture. Current page retains a legacy section for a small number of Team/Enterprise organizations. - custom_instructions — Can users set persistent instructions? [supported]: Projects have persistent instructions for context and style. Sources: claude:cl-projects. - cross_chat_memory — Does the product remember facts across chats? [partial]: Improved memory: owners enable availability and members opt in; cloud Cowork shares Chat memory, local Cowork does not. Legacy memory is chat-only and unavailable in Cowork. Sources: claude:cl-memory-r2. - user_memory_controls — Can users view, edit and delete memories? [partial]: Improved memory users inspect/delete topics, pause/reset and choose sensitive-topic opt-in. Incognito remains subject to organization export/retention. Legacy settings and summary-memory behavior differ. Sources: claude:cl-memory-r2. - admin_memory_controls — Can admins turn memory off? [partial]: Improved memory: Owners/Primary Owners control availability; disabling it deletes existing entries. Legacy Team explicitly lacks org-level memory controls. Improved memory is unavailable under the named HIPAA/public-sector/custom-retention agreements. Sources: claude:cl-memory-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-memory-r2 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents. - cross_chat_memory — Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access ## Assistants and agents ### AGT-01: Custom assistants Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Projects, skills, plugins and artifacts provide reusable task context; full assistant governance remains partly unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No HR-policy assistant was built or shared with a test group. - create_assistants — Can users create assistants with instructions, knowledge and tools? [partial]: Projects pair instructions/knowledge; skills and plugins provide reusable task behavior, while custom agent model/tool binding was not fully audited. Sources: claude:cl-projects, claude:cl-academy. - creator_permissions — Can admins limit who creates them? [partial]: Enterprise groups/custom roles control plugin access and shared resources; a complete assistant-creator matrix was not verified. Sources: claude:cl-groups. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Team/Enterprise projects share with organization members; Enterprise groups can receive projects/skills/plugins. Sources: claude:cl-projects, claude:cl-groups. - catalogue — Is there an internal assistant directory? [partial]: Organization resources and plugins can be shared; a complete internal assistant directory was not inspected. Sources: claude:cl-groups. - prompt_library — Are shared prompt templates available? [partial]: Skills capture reusable instructions/processes across Office apps; plain prompt-template catalogue behavior was not verified. Sources: claude:cl-office. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-academy, claude:cl-groups, claude:cl-office #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents. - creator_permissions — Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access. - catalogue — Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents. - prompt_library — Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access ### AGT-02: Tools, actions and MCP Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Claude supports remote and local MCP with different execution and identity boundaries. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No external-tool call or fixture permission test was performed. - builtin_tools — Which tools are built in? [supported]: Code execution, web search, Research and connector tools are listed for commercial plans. Sources: claude:cl-pricing. - custom_actions — Can admins add API actions? [partial]: Custom remote MCP can expose action tools; OpenAPI-specific action configuration was not separately verified. Sources: claude:cl-mcp. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Remote MCP works through Anthropic cloud. Desktop-local MCP is a separate local-network mechanism; Cowork/cloud chat cannot use that local configuration. Sources: claude:cl-mcp. - tool_auth — Do tools act as the user or as a shared account? [supported]: Remote connectors can use per-user OAuth or fixed shared request-header credentials; the latter exposes that credential's access to users. Sources: claude:cl-mcp. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Owners enable connectors and tools; Microsoft Teams sends require Ask, while other tools have configurable permission behavior. Sources: claude:cl-m365, claude:cl-mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-mcp, claude:cl-m365 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. - builtin_tools — Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images. - custom_actions — Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_auth — Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code ### AGT-03: Web search and deep research Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web search and Research are offered; detailed search-provider geography and group policy remain open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - search_provider: Which search provider handles queries, and where? Unverified after checking commercial plan comparison, connector and release docs; current search provider, query location, web-specific citation behavior and full admin toggle matrix not established. Search on 2026-10-26: https://claude.com/pricing, https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork, https://support.claude.com/en/articles/10684626-enable-and-use-web-search. No additional scoped evidence established this answer. - web_search — Is web search available? [supported]: Commercial plans include web search. Sources: claude:cl-pricing-20261026. - admin_toggle — Can admins disable it per organisation or group? [supported]: An Owner or Primary Owner enables web search for the Team/Enterprise workspace under Organization settings > Capabilities. Members then enable it in chat; the new unified experience can invoke search without a per-chat toggle. Sources: claude:claude:web-search-controls-20261026. - search_provider — Which search provider handles queries, and where? [unknown]: Which search provider handles queries, and where? Unverified after checking commercial plan comparison, connector and release docs; current search provider, query location, web-specific citation behavior and full admin toggle matrix not established. Search on 2026-10-26: https://claude.com/pricing, https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork, https://support.claude.com/en/articles/10684626-enable-and-use-web-search. No additional scoped evidence established this answer. - deep_research — Is multi-step research with a report available? [supported]: Commercial plans list Research; no shared-corpus report was run. Sources: claude:cl-pricing-20261026. - web_citations — Are web sources cited? [supported]: The web-search guide documents direct citations and links to the sources used in searched answers. Citation correctness was not fixture-tested. Sources: claude:claude:web-search-controls-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-pricing-20261026, claude:claude:web-search-controls-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. - web_search — Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents. - admin_toggle — Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web. - search_provider — Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web. - deep_research — Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web. - web_citations — Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access ### AGT-04: Workflows and automation Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cowork documents scheduled multi-step tasks; external-event triggers remain unverified. Availability: beta Delivery: native Scope: surfaces=Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team and Enterprise Cowork; cloud execution in beta; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: event_triggers. - Read each atomic answer for its plan, access and feature limits. - workflow_builder — Is there a workflow or chain builder? [partial]: Cowork turns outcome instructions into multi-step tasks and reusable scheduled work; a separate no-code graph builder was not verified. Sources: claude:cl-cowork. - scheduled_tasks — Can prompts or assistants run on a schedule? [partial]: Scheduled Cowork tasks run in the cloud with no device online, subject to commercial beta and admin access. Sources: claude:cl-cowork. - event_triggers — Can external events start a workflow? [unknown]: Can external events start a workflow? Unverified after checking Cowork task/schedule and connector docs; no external-event trigger contract or event fixture. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Cowork is aimed at knowledge work with no terminal required. Sources: claude:cl-cowork. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-cowork #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. - event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. - workflow_builder — Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule. - event_triggers — Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api ### AGT-05: Agentic task execution Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cowork documents multi-step execution; broad action and stop-control behavior remains untested. Availability: beta Delivery: native Scope: surfaces=Claude Cowork cloud and desktop task execution, Claude connectors and remote MCP integrations; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise Cowork; cloud beta where stated; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - visible_steps: The documented task flow includes planning and subtasks; complete tool-step visibility was not independently observed. - side_effect_confirmation: Microsoft connector has required confirmations for specified email/calendar/Teams actions; this does not establish mandatory confirmation for every Cowork side effect. - stop_control: The paid-plan Cowork safety guide documents user stopping/monitoring of tasks. It does not guarantee that stopping reverses a completed write or cancels every submitted external action. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Paid Cowork plans and executes multi-step tasks with code, files and browser access where permitted. Sources: claude:cl-cowork-20261026. - visible_steps — Are steps and tool calls shown? [partial]: The documented task flow includes planning and subtasks; complete tool-step visibility was not independently observed. Sources: claude:cl-cowork-20261026. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Microsoft connector has required confirmations for specified email/calendar/Teams actions; this does not establish mandatory confirmation for every Cowork side effect. Sources: claude:cl-m365-20261026. - stop_control — Can the user stop a running task? [partial]: The paid-plan Cowork safety guide documents user stopping/monitoring of tasks. It does not guarantee that stopping reverses a completed write or cancels every submitted external action. Sources: claude:claude:cowork-stop-20261026, claude:cl-cowork-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-cowork-20261026, claude:cl-m365-20261026, claude:claude:cowork-stop-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - No gather-documents, draft-summary and propose-email task was run. - Highly experimental attached workspaces are distinct from ordinary Agent tool use. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code. - visible_steps — Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code. - stop_control — Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases ### AGT-06: Programmable access Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial A public model API and separate compliance/analytics interfaces exist; workspace feature parity is unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: knowledge_api, mcp_server. - Read each atomic answer for its plan, access and feature limits. - chat_api — Is there an API for chat and assistants? [partial]: Claude Platform has a public separately priced model API; this does not establish API access to the same Claude Team/Enterprise assistant conversations. Sources: claude:cl-api-prices. - knowledge_api — Can documents be loaded through an API? [unknown]: Can documents be loaded through an API? Unverified after checking Claude Platform pricing and commercial Compliance API docs; workspace knowledge ingestion and product MCP-server exposure not verified. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Enterprise Compliance API covers eligible deployments; automatic parity of model, budget and audit policy with separately purchased API usage was not established. Sources: claude:cl-compliance. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: Does the product expose itself to other agents over MCP? Unverified after checking Claude Platform pricing and commercial Compliance API docs; workspace knowledge ingestion and product MCP-server exposure not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-api-prices, claude:cl-compliance #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. - api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. - mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. - chat_api — Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api. - knowledge_api — Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access ## Daily work ### WORK-01: Clients and access points Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web, native clients and Chrome access are documented, with distinct admin and beta eligibility. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - web — Is a full web client available? [supported]: Commercial Claude is available on the web. Sources: claude:cl-enterprise. - desktop_apps — Windows and macOS apps? [supported]: Cowork supports macOS and Windows desktop clients on paid plans. Sources: claude:cl-cowork. - mobile_apps — iOS and Android apps with SSO? [partial]: iOS/Android clients support commercial accounts; SSO mobile login was not tested. Sources: claude:cl-cowork, claude:cl-m365-user. - browser_extension — Is there a browser extension or sidebar? [partial]: Claude in Chrome is available with plan/Enterprise admin eligibility. Sources: claude:cl-cowork. - managed_deployment — Can IT deploy and configure clients through MDM? [partial]: Team and Enterprise plan comparisons list enterprise desktop deployment; exact MDM packages/policies were not reviewed. Sources: claude:cl-pricing. - client_feature_gaps — Which features are missing on mobile? [partial]: Exports require web/Desktop; cloud Cowork rollout and admin enablement differ from local desktop execution. Sources: claude:cl-export-user, claude:cl-cowork. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-enterprise, claude:cl-cowork, claude:cl-m365-user, claude:cl-pricing, claude:cl-export-user #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. - browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. - web — Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local. - desktop_apps — Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps — iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights. - browser_extension — Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps — Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights ### WORK-02: Office suite and Teams integration Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native Microsoft add-ins and a separate Google Workspace beta have different approval and data paths. Availability: generally-available Delivery: native Scope: surfaces=Claude for Microsoft 365 official add-ins, Claude connectors and remote MCP integrations, Claude native Google Workspace sidebar beta; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise Office; Outlook beta; Google Workspace native beta; add_ons=Microsoft/Google subscriptions and administrator deployment approval where required; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No deployment or native-edit fixture. Google extension retains its own local per-file history and does not inherit custom organization retention. - word_excel_powerpoint — Does it work inside Word, Excel and PowerPoint? [supported]: Claude advertises native Excel/PowerPoint/Word add-ins as generally available on paid plans. Sources: claude:cl-office. - outlook — Does it work inside Outlook? [supported]: Outlook add-in is beta and opens drafts in the native composer for user sending. Sources: claude:cl-office. - teams — Is there a Teams app or bot? [partial]: Teams read/write is through the separate Microsoft connector; a native Teams app was not established. Sources: claude:cl-m365. - google_workspace_apps — Does it work inside Docs, Sheets or Gmail? [supported]: Native Google Docs/Sheets/Slides sidebar is beta for Team/Enterprise, installed via Google Marketplace. It edits the open file under the user identity with ask-before-edits by default; connectors are a separate feature. Sources: claude:cl-google-addon. - licence_prerequisites — Which licences or consents are needed? [partial]: Paid Claude or supported cloud credentials are advertised for Office; Google add-in needs a paid supported plan and Marketplace approval. Microsoft source connector needs work-account/Entra consent. Sources: claude:cl-office, claude:cl-google-addon, claude:cl-m365-user. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office, claude:cl-m365, claude:cl-google-addon, claude:cl-m365-user #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### WORK-03: Translation and writing Judgment rule: Record document translation preserving layout, the translation engine (LLM or dedicated such as DeepL), glossaries, formality control, supported languages including Swiss German conventions (no ß), and rewriting/proofreading tools. Translate the shared German contract into French and Italian and record layout and glossary results. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Office rewriting/review is documented; translation fidelity and glossary controls remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: document_translation, translation_engine, glossaries, formality_and_variants. - Read each atomic answer for its plan, access and feature limits. - document_translation — Can whole documents be translated with formatting kept? [unknown]: Can whole documents be translated with formatting kept? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - translation_engine — Which engine translates? [unknown]: Which engine translates? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - glossaries — Are company glossaries supported? [unknown]: Are company glossaries supported? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: Can formality and regional variants (de-CH) be set? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - writing_tools — Are dedicated rewrite and proofreading tools available? [partial]: Word add-in advertises tracked revisions, comments and company styles; no proofreading/translation fixture was run. Sources: claude:cl-office. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### WORK-04: Image generation and editing Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Claude explicitly excludes native photo/illustration generation; HTML/SVG visuals and uploaded-image analysis are separate capabilities. Availability: unknown Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Public help checked 2026-10-26; plan=Team/Enterprise native Claude web and desktop; third-party image tools excluded; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; os=not specified. Limitations: - image_editing: Can users edit uploaded images? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - admin_control: Can admins restrict image generation? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - usage_terms: What usage rights apply to output? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - image_generation — Can users generate images, with which models? [unsupported]: The official image FAQ explicitly says Claude does not generate photos or illustrations like dedicated image-generation tools. Its beta HTML/SVG diagrams/charts are not a native raster image-generation model. Sources: claude:claude:image-generation-boundary-20261026. - image_editing — Can users edit uploaded images? [unknown]: Can users edit uploaded images? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - admin_control — Can admins restrict image generation? [unknown]: Can admins restrict image generation? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - usage_terms — What usage rights apply to output? [unknown]: What usage rights apply to output? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:claude:image-generation-boundary-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured Agent image tools generate and edit images; model service rights/costs remain separate. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. - usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. - image_generation — Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images. - image_editing — Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images. - admin_control — Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access ### WORK-05: Voice and meetings Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Voice and Office dictation are listed; meeting and dialect details need evidence. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: read_aloud, meeting_summaries, swiss_german_speech. - Read each atomic answer for its plan, access and feature limits. - dictation — Can users dictate prompts? [supported]: Claude for Microsoft 365 advertises dictation in its sidebar. Sources: claude:cl-office. - read_aloud — Can answers be read aloud? [unknown]: Can answers be read aloud? Unverified after checking commercial Voice listing, Office and connector docs; standalone read-aloud, live meeting transcription and Swiss German accuracy not verified. - voice_conversation — Is a live voice mode available? [partial]: Team/Enterprise feature comparison lists Voice mode; exact client/language/audio-processing scope was not fully verified. Sources: claude:cl-pricing. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: Are meetings transcribed and summarised? Unverified after checking commercial Voice listing, Office and connector docs; standalone read-aloud, live meeting transcription and Swiss German accuracy not verified. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Is Swiss German speech recognised? Unverified after checking commercial Voice listing, Office and connector docs; standalone read-aloud, live meeting transcription and Swiss German accuracy not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office, claude:cl-pricing #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified. Limitations: - Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified. - Audio location depends on the chosen engine. No meeting or Swiss German fixture was run. - dictation — Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech. - read_aloud — Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech. - voice_conversation — Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2 ### WORK-06: Data analysis and document output Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enabled Chat code/file tools provide sandboxed analysis and Office/PDF output; Team egress defaults are not established by this finding. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise Chat code execution, file creation and artifact editing where enabled; excludes native Office and Cowork execution defaults; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Narrowed to verified file creation/execution. The guide's conflicting Team default is retained as a named configuration gap, not a claim about an enabled tenant. - No formula/PPT/PDF output fixture. Separate enabled MCP routes are not controlled by the code-sandbox egress setting. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Enabled Chat code/file creation runs code in a sandboxed container and can create Python analysis scripts. This does not establish a particular Team egress default. Sources: claude:cl-code-files-r2. - charts — Can it produce charts? [supported]: The Chat computing path can create PNG data visualizations; native Office add-in charts are outside this narrowed scope. Sources: claude:cl-code-files-r2. - office_file_output — Can it create Word, Excel or PowerPoint files? [supported]: Enabled Chat file creation produces downloadable XLSX/PPTX/DOCX/PDF, subject to the file-tool guide's30 MB upload/download path. Sources: claude:cl-code-files-r2. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Docs/Design/Slides artifact templates support editing; template availability differs by type and plan. Sources: claude:cl-artifacts-admin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-code-files-r2, claude:cl-artifacts-admin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. - office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. - canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code. - charts — Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts ### WORK-07: Sharing and team spaces Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial projects and artifacts support shared work; recipient source boundaries need tests. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: group_chat. - Read each atomic answer for its plan, access and feature limits. - share_chats — Can chats be shared inside the organisation? [partial]: Shared project members can see project content and chat within it; a full chat-link audience matrix was not verified. Sources: claude:cl-projects. - team_spaces — Are shared projects or workspaces available? [supported]: Team/Enterprise have shared projects; Enterprise groups receive shared projects/skills/plugins. Sources: claude:cl-projects, claude:cl-groups. - group_chat — Can several people chat together with the AI? [unknown]: Can several people chat together with the AI? Unverified after checking project sharing, group controls and connector security; synchronous group AI chat and cross-group sharing fixture not verified. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Microsoft connector guide says shared-chat recipients see the response incorporating tool data; original source authorization does not prove recipient-safe output sharing. Sources: claude:cl-m365. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-groups, claude:cl-m365 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. - share_chats — Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share. - team_spaces — Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects. - group_chat — Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects ### WORK-08: Interface languages and accessibility Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web and desktop interface languages include German, French and Italian; UI quality, complete admin localization and WCAG conformance remain unverified. Availability: unknown Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team and Enterprise using the documented web/desktop language setting; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - accessibility_statement: Is there a WCAG conformance statement? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - admin_ui_languages: Is the admin interface available in German? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - ui_languages — Which UI languages are offered? [supported]: The public display-language guide lists German, French and Italian, alongside English, Hindi, Indonesian, Japanese, Korean, Brazilian Portuguese and two Spanish variants, for web and desktop. Sources: claude:claude:display-languages-20261026. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: Are German, French and Italian UIs complete and natural? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: Is there a WCAG conformance statement? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - admin_ui_languages — Is the admin interface available in German? [unknown]: Is the admin interface available in German? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:claude:display-languages-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial English, German, French and Italian UI resources are registered in the pinned client; quality and accessibility conformance were not evaluated. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - ui_languages — Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages — Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin ## Administration and governance ### ADM-01: Single sign-on and authentication Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial SSO and domain controls are documented; exact client MFA/Conditional Access coverage remains open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Connector token/device policy caveats must not be generalized to Claude SSO itself. No trial login was performed. - sso_protocols — Which SSO protocols and identity providers work? [partial]: The SSO/provisioning guides document SAML IdPs including Entra, Okta, Google and others; full OIDC/direct-LDAP matrix was not established. Sources: claude:cl-sso, claude:cl-provision. - sso_plan — Which plan includes SSO? [supported]: SSO is available on Team and Enterprise. Sources: claude:cl-sso. - mfa — Can MFA be enforced? [unknown]: Can MFA be enforced? Unverified after checking SSO/provisioning and Microsoft connector security docs; direct MFA policy enforcement and client Conditional Access compatibility not tested. - conditional_access — Do Entra conditional-access policies apply? [unknown]: Do Entra conditional-access policies apply? Unverified after checking SSO/provisioning and Microsoft connector security docs; direct MFA policy enforcement and client Conditional Access compatibility not tested. - domain_capture — Can the company claim its email domain? [partial]: SSO requires domain verification; Enterprise account claiming and Team migration differ. Sources: claude:cl-sso, claude:cl-pricing. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-sso, claude:cl-provision, claude:cl-pricing #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. - domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth. - sso_plan — Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth. - mfa — Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth. - conditional_access — Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra ### ADM-02: User provisioning and lifecycle Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team JIT and Enterprise SCIM have different synchronization and removal behavior. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No leaver fixture or asset transfer test was performed. - scim — Is SCIM provisioning supported? [supported]: SCIM is available on Enterprise and explicitly unavailable on Team. Sources: claude:cl-provision. - group_sync — Are identity-provider groups synced? [partial]: Enterprise SCIM can synchronize groups; JIT group mappings change role/seat at login and do not synchronize custom-role groups. Sources: claude:cl-provision. - jit_provisioning — Are users created at first login? [supported]: Team/Enterprise JIT can provision at first SSO login; unassigned JIT users can retain their seat until manual removal. Sources: claude:cl-provision. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: Enterprise SCIM automatically removes users when IdP access is revoked; underlying chat/project ownership and retention were not fixture-tested. Sources: claude:cl-provision. - seat_assignment — Can admins assign and reclaim seats? [supported]: Admins/owners manage standard/premium or current Enterprise access seats; group mappings can assign role/tier on supported plans. Sources: claude:cl-provision. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-provision #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. - seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. - scim — Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - group_sync — Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra. - jit_provisioning — Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth. - seat_assignment — Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license ### ADM-03: Roles, groups and feature permissions Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise custom roles/groups add granular controls beyond Team owner/admin roles. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: Team has Owner/Admin/User; Enterprise also has custom roles and Primary Owner responsibilities. Sources: claude:cl-provision, claude:cl-compliance. - groups — Can permissions be set per group? [supported]: Enterprise groups can be manual or SCIM-synchronized and receive roles/resources. Sources: claude:cl-groups. - feature_toggles — Which features can be switched on or off per group? [partial]: Enterprise roles control model/effort and plugin access; owners manage connectors, artifacts and egress. A full feature-by-group matrix was not tested. Sources: claude:cl-model-control, claude:cl-groups, claude:cl-artifacts-admin. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Parent/linked organization identity and compliance are documented, but full subsidiary data-isolation behavior was not verified. Sources: claude:cl-compliance. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-provision, claude:cl-compliance, claude:cl-groups, claude:cl-model-control, claude:cl-artifacts-admin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Separate admin management UI is preview; the core authorization model is documented as available. - No two-group disabled-feature fixture was run. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access. - groups — Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin. - feature_toggles — Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights ### ADM-04: Usage and adoption analytics Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial analytics expose adoption and spend with plan-specific roles and CSV exports. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: privacy_modes. - Read each atomic answer for its plan, access and feature limits. - adoption_dashboard — Is there an adoption dashboard? [supported]: Team owners and Enterprise owners/admins have usage analytics; Enterprise admins cannot see Spend. Sources: claude:cl-analytics. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Product, group, member, model, skill and connector read/write activity are documented; availability varies by billing mode. Sources: claude:cl-analytics. - export — Can usage data be exported? [supported]: CSV spend reports include user/model token and estimated-spend fields, updated daily, with up to 90-day selectable history. Sources: claude:cl-analytics. - privacy_modes — Can per-person reporting be limited or pseudonymised? [unknown]: Can per-person reporting be limited or pseudonymised? Unverified after checking analytics and role docs; organization-wide pseudonymization/works-council reporting settings not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-analytics #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. - export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. - adoption_dashboard — Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens. - export — Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens ### ADM-05: Spend controls and cost allocation Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has user/group limits, with pooled group budgets in beta. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No small-budget enforced-stop fixture was run. - cost_visibility — Can admins see cost or consumption per user and group? [supported]: Enterprise analytics show model/member spend; legacy seat-based reports cover overage only. Sources: claude:cl-analytics. - budgets — Can budgets be set per user or group? [partial]: Enterprise supports organization/user limits and group per-user limits; shared monthly group budgets are beta. Sources: claude:cl-enterprise, claude:cl-groups. - budget_enforcement — Does reaching a budget alert, block or downgrade? [partial]: Docs expose blocked-by-limit behavior and individual/group resolution order; exact overshoot/timing was not tested. Sources: claude:cl-groups. - chargeback — Can costs be exported per cost centre? [partial]: Per-user/model CSVs can inform allocation; a native cost-centre chargeback export was not established. Sources: claude:cl-analytics. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-analytics, claude:cl-enterprise, claude:cl-groups #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. - budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. - chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights. - budgets — Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance. - budget_enforcement — Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin ### ADM-06: Audit logs and compliance export Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise audit metadata and content/compliance exports are distinct. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - CMEK disables the UI Export logs route; audit events remain accessible through Compliance API. No export or integrity fixture was run. - admin_events — Are admin and security events logged? [supported]: Enterprise audit events cover member, SSO, configuration, file and conversation metadata; exported fields include actor/device/IP. Sources: claude:cl-audit. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [supported]: Audit export excludes chat titles/content; organization data exports or Compliance API provide eligible content. Sources: claude:cl-audit, claude:cl-compliance. - siem_export — Can logs stream to a SIEM or be exported? [supported]: Enterprise Compliance API and partner integrations provide event/chat/file access for security tools. Sources: claude:cl-compliance, claude:cl-compliance-partners. - ediscovery — Are eDiscovery and legal hold supported? [partial]: Partner integrations include preservation/eDiscovery workflows; a native legal-hold setting was not verified. Sources: claude:cl-compliance-partners. - log_retention — How long are logs kept? [partial]: UI audit export aggregates the past 180 days; its download link lasts 24 hours. API retention/integrity guarantees were not fully inspected. Sources: claude:cl-audit. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-audit, claude:cl-compliance, claude:cl-compliance-partners #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. - content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. - siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. - ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. - admin_events — Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin. - siem_export — Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention — How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin ### ADM-07: Data loss prevention and personal data Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Eligible Enterprise organizations can use Compliance API partner monitoring; native inline PII handling remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude connectors and remote MCP integrations; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Enterprise with Primary-Owner-enabled Compliance API and separately configured partner integration; no Team entitlement; add_ons=Enterprise plan, Compliance API activation by Primary Owner, Applicable partner subscription and configuration; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - The positive integration statement is Enterprise-only. Team integration support remains unverified. - No Swiss AHV/IBAN fixture, custom-pattern behavior, pre-model blocking/redaction or filter geography verified. - pii_detection — Is personal data detected in prompts and files? [unknown]: Is personal data detected in prompts and files? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. - pii_action — Is it redacted, masked, blocked or only warned? [unknown]: Is it redacted, masked, blocked or only warned? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. - custom_patterns — Can admins add custom patterns or terms? [unknown]: Can admins add custom patterns or terms? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. - dlp_integration — Does it integrate with an existing DLP product? [partial]: Enterprise Compliance API partners offer monitoring/security/DLP integrations after Primary Owner activation. Claude Platform is a separate scope, and these integrations do not prove native inline pre-model redaction. Sources: claude:cl-compliance-partners-r2. - filter_location — Where does filtering run? [unknown]: Where does filtering run? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-compliance-partners-r2 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown. Availability: source-only Delivery: native Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Development-source finding; no running instance or AHV/IBAN fixture. - Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class. - Redaction applies only to eligible fresh Agent text; encrypted originals remain stored. - A dedicated external DLP integration remains unverified. - pii_detection — Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - custom_patterns — Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration. - filter_location — Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318 ### ADM-08: AI policy and guardrails Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has feature/model and plugin safeguards; broader policy enforcement remains partly unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: org_instructions, usage_notice. - Read each atomic answer for its plan, access and feature limits. - org_instructions — Can admins set organisation-wide instructions? [unknown]: Can admins set organisation-wide instructions? Unverified after checking commercial terms, Enterprise controls and security scanning releases; organization-wide enforced instructions and mandatory AUP acknowledgment not established. - usage_notice — Can users be required to accept a usage policy? [unknown]: Can users be required to accept a usage policy? Unverified after checking commercial terms, Enterprise controls and security scanning releases; organization-wide enforced instructions and mandatory AUP acknowledgment not established. - content_filters — Are content filters configurable? [partial]: Enterprise release notes announce skill/plugin security scanning beta; it does not establish a configurable prompt/topic content-filter system. Sources: claude:cl-release. - violation_reporting — Are policy hits visible to admins? [partial]: Security/compliance integrations can analyze events; a complete native policy-violation dashboard was not verified. Sources: claude:cl-compliance-partners. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-release, claude:cl-compliance-partners #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. - content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. - violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. - org_instructions — Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - usage_notice — Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface. - content_filters — Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod. - violation_reporting — Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod ## Data protection and sovereignty ### DATA-01: Hosting location and data residency Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial privacy documentation describes US storage and global inference; US-only Enterprise inference is a separate option. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Do not substitute cloud-provider model availability for residency of the hosted Claude workspace. Design and Google add-in retention have separate rules. - storage_region — Where are chats, files and indexes stored? [partial]: The commercial server-location article specifies US storage for Enterprise/API; exact Team and per-feature chat/file/index mapping was not established. Sources: claude:cl-servers. - inference_region — Where do model calls run, per provider? [supported]: Default commercial inference may run in the US, Europe, Asia or Australia; usage-based Enterprise can select US-only inference. Sources: claude:cl-servers, claude:cl-us-only. - backups_logs_region — Where are backups, logs and telemetry? [unknown]: Where are backups, logs and telemetry? Unverified after checking commercial location and US-only inference guides; no EU/Swiss-only hosting guarantee or backup/log/telemetry country matrix retrieved. - support_access_region — From where can vendor staff access data? [partial]: Internal support/safety processing can take place in countries with Anthropic affiliates; the full personnel/country/access map is not enumerated here. Sources: claude:cl-servers. - swiss_hosting — Is Swiss hosting available? [unknown]: Is Swiss hosting available? Unverified after checking commercial location and US-only inference guides; no EU/Swiss-only hosting guarantee or backup/log/telemetry country matrix retrieved. - residency_plan — Which plan or option provides residency? [supported]: US-only inference is limited to usage-based Enterprise, excludes Team and legacy seat-based Enterprise, and has model-specific 1.1x pricing. It does not control storage or third-party services. Sources: claude:cl-us-only. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-servers, claude:cl-us-only #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. - support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. - storage_region — Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote. - inference_region — Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex. - backups_logs_region — Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin. - support_access_region — From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting — Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license. - residency_plan — Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license ### DATA-02: Deployment options Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team/Enterprise are vendor-hosted workspaces; whole-platform private deployment is unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Local Cowork tasks, Desktop MCP and Office cloud credentials do not establish deployment of the whole hosted workspace. - multi_tenant_saas — Is a shared SaaS offered? [supported]: Team/Enterprise provide Anthropic-operated commercial SaaS; the DPA specifies logical separation of customer data. Sources: claude:cl-enterprise, claude:cl-dpa. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: Is a dedicated single-tenant instance offered, from what size? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - customer_cloud — Can it run in the customer's own cloud account, from what size? [unknown]: Can it run in the customer's own cloud account, from what size? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - on_premise — Can the whole platform run on customer infrastructure, from what size? [unknown]: Can the whole platform run on customer infrastructure, from what size? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - air_gapped — Can it run without internet access? [unknown]: Can it run without internet access? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - mode_feature_gaps — Which features are missing outside SaaS? [unknown]: Which features are missing outside SaaS? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-enterprise, claude:cl-dpa #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The project documents local and customer-cloud installs. A free public demo is separate from a production managed service. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. - dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. - mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. - multi_tenant_saas — Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin. - air_gapped — Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg. - mode_feature_gaps — Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code ### DATA-03: Training use and provider retention Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hosted commercial Chat/Cowork retention is separate from API/Code/provider ZDR arrangements and limited Fable exceptions. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Direct hosted Claude Team/Enterprise Chat and Cowork under Commercial Terms; API/ClaudeCode/third-party-provider ZDR routes discussed only as separate exceptions; add_ons=Standard hosted commercial retention; no assumed special ZDR agreement; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Reconciliation: the Covered Model minimum is a default rule; its temporary agreement-based exception is conditional. The current route guide expressly excludes notified exception customers from the general ZDR-transition instructions. - No-training, saved history, safety-monitoring copies and specialized ZDR agreements are distinct. No sales contact or agreement signing. - vendor_training — Does the vendor train on customer content? [supported]: Commercial Terms section B prohibits training on Customer Content; the privacy guide describes explicit feedback/bug submissions as an exception to default no-training. Sources: claude:cl-terms, claude:cl-training. - provider_training — Do model providers train on it under this product's contracts? [partial]: Direct hosted Claude uses Anthropic models under its commercial no-training terms. Separate API, Office BYO cloud or third-party integrations require their own contracts and are outside this hosted inference finding. Sources: claude:cl-terms. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [partial]: Hosted saved commercial chats persist until deletion; normal backend deletion is within 30 days with safety/legal exceptions. Covered Models have an additional default minimum 30-day safety-retention rule; ordinary saved-chat history is not thereby limited to30 days. Sources: claude:cl-retention-r2, claude:cl-covered-r2. - zero_retention — Is zero data retention available, and on which plan? [partial]: The route guide says hosted Enterprise Chat/Cowork already operate with standard retention. Separately, Console/API, Enterprise Code and provider ZDR configurations follow their own rules. The default Covered Model rule has a limited temporary Fable exception for eligible notified/agreement-based internal business applications; no general hosted Chat/Cowork ZDR entitlement is established. Sources: claude:cl-covered-r2, claude:cl-covered-routes-r2. - human_review — Can provider staff review content? [partial]: Commercial confidentiality/DPA measures permit authorized, least-privileged personnel processing. The detailed approved-reviewer path concerns the described Covered Model retained-monitoring configurations; it is not a complete hosted-chat human-access map. No no-human-access guarantee is made. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-covered-routes-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms, claude:cl-training, claude:cl-retention-r2, claude:cl-covered-r2, claude:cl-covered-routes-r2, claude:cl-dpa #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. - provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - vendor_training — Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat. - provider_training — Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat ### DATA-04: Retention and deletion Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Current Enterprise retention guidance schedules deletion on save and removes content through a daily process, with project precedence and feature exclusions. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise saved commercial Chat; Enterprise owner-configured Chat/project retention. Cowork is included only for documented project-activity effects, not blanket cloud-Code retention; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Reconciliation: current English text is authoritative for this snapshot; the earlier cached immediate-deletion wording is superseded and is not a current factual claim. Scheduling on save does not mean instant physical deletion. - No retention/deletion fixture. Google Workspace add-in and the named excluded cloud features have separate retention behavior. - default_retention — What is retained and for how long by default? [partial]: Saved commercial chats persist until deletion; Enterprise chats/projects default to indefinite retention without configured periods. Incognito normally deletes within 30 days. Other file/index/log schedules are not fully mapped. Sources: claude:cl-retention-r2, claude:cl-retention-admin-r2. - admin_retention — Can admins set retention periods? [supported]: Enterprise Owners/Primary Owners set a minimum 30-day Chat/project period. Project retention overrides contained chats, including indefinite projects. Shortening a period schedules over-age data on save; a daily process can take several days. Design/Tag/Managed Agents and other cloud-Code features are excluded. Sources: claude:cl-retention-admin-r2. - user_deletion — Can users delete their chats and files permanently? [partial]: User-deleted chats leave visible history immediately and normally delete from backend within 30 days, subject to legal/safety exceptions. This is different from the daily custom-retention job. Sources: claude:cl-retention-r2. - contract_end_deletion — What is deleted at contract end, and when? [partial]: DPA H requires return on request within 30 days and deletion within 30 days after expiry/termination, except legal requirements, disputes or combating harmful use. Confirmation/copy completeness were not tested. Sources: claude:cl-dpa. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-retention-r2, claude:cl-retention-admin-r2, claude:cl-dpa #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. - contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. - default_retention — What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention. - admin_retention — Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention. - user_deletion — Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings. - contract_end_deletion — What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings ### DATA-05: Sub-processors and foreign-law exposure Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The DPA provides subprocessor and transfer rules; the current country list remains inaccessible in this pass. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: subprocessor_countries. - Read each atomic answer for its plan, access and feature limits. - subprocessor_list — Is a dated sub-processor list published? [partial]: DPA Schedule 4 links to a published trust-portal list; its entries and revision were not extractable during retrieval. Sources: claude:cl-dpa, claude:cl-trust-route. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: Which countries do sub-processors operate in? Unverified after checking DPA Schedule 4, trust redirect and commercial terms; full current subprocessor countries, list date and ownership chain not retrieved. - change_notification — Are customers notified of sub-processor changes? [supported]: DPA C.3 provides notice before a new subprocessor gains data access and a 15-day objection window on reasonable privacy/security concerns. Sources: claude:cl-dpa. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: Commercial Terms contract with Anthropic Ireland Limited for EEA/Swiss/UK customers and Anthropic PBC elsewhere; the ultimate ownership/entity chain was not independently established. Sources: claude:cl-terms. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [supported]: DPA incorporates controller-to-processor/processor-to-processor SCCs and UK/Swiss schedules where applicable. Sources: claude:cl-dpa. - government_access_policy — Is there a published government-access or transparency policy? [supported]: Published policy requires valid process with emergency exceptions, reviews deficient requests, usually redirects enterprise requests to the customer and provides notice subject to exceptions. Sources: claude:cl-gov. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-dpa, claude:cl-trust-route, claude:cl-terms, claude:cl-gov #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. - transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_list — Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification — Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy — Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner ### DATA-06: Contracts and regulatory coverage Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public commercial contracts include a DPA and Swiss transfer terms; this is not a regulatory suitability verdict. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Generic confidentiality/DPA language does not establish a German section 203 or Swiss article 321 professional-secrecy undertaking. - dpa — Is a DPA available, and is it negotiable? [partial]: Commercial Terms incorporate the public DPA; standard acceptance is documented, while negotiability for this account was not verified. Sources: claude:cl-terms, claude:cl-dpa. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [supported]: DPA defines GDPR and includes a Swiss Addendum covering Swiss data protection laws and new/revised versions. Sources: claude:cl-dpa. - governing_law — Which law and court govern the contract? [supported]: For EEA/Swiss/UK customers, Terms M.7 specify Irish law and Irish courts for proceedings not subject to section J arbitration; specific orders may differ. Sources: claude:cl-terms. - ai_act_materials — Is EU AI Act documentation provided? [partial]: Provider materials describe transparency-code commitments, text watermarking and an eligible-organization detection API private preview. A complete deployer compliance pack was not inspected. Sources: claude:cl-ai-act. - sector_materials — Are FINMA or other sector materials provided? [partial]: Enterprise plan documentation lists HIPAA-ready configurations; scope/BAA conditions and FINMA/banking/public-sector materials were not fully retrieved. Sources: claude:cl-enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-ai-act, claude:cl-enterprise #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### DATA-07: Certifications and attestations Judgment rule: Record each certificate or report separately: ISO 27001, 27017, 27018, 27701, 42001; SOC 2 Type I/II with period; BSI C5; TISAX; national schemes. Record issuer, scope (which product and entity), validity and access route. A cloud provider's certificate does not certify the product. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The DPA documents report and penetration-test access; actual certification scope and validity remain open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - iso_27001: Anthropic publicly claims ISO 27001:2022 for its commercial products. The issuing body, full certificate scope and validity dates were not inspected; this is vendor-claimed evidence. - soc2: The commercial privacy page lists SOC 2 Type I and Type II. The auditor, report period and detailed service scope were not inspected. - c5: BSI C5 attestation? Unverified after checking public DPA and Trust Center; issuer, covered entity/product, period and validity of ISO/SOC/C5/other attestations were not verified. Search on 2026-10-26: https://www.anthropic.com/legal/data-processing-addendum, https://www.anthropic.com/legal/commercial-terms, https://trust.anthropic.com/. No additional scoped evidence established this answer. - other_certifications: The commercial privacy page claims ISO/IEC 42001:2023. No issuing-body certificate, validity dates or TISAX/ISO 27701 scope was inspected. - pentest: DPA Schedule 2 G.2 commits to annual external penetration tests and a customer-request summary; no summary or testing period was inspected. - iso_27001 — ISO 27001 with scope and validity? [partial]: Anthropic publicly claims ISO 27001:2022 for its commercial products. The issuing body, full certificate scope and validity dates were not inspected; this is vendor-claimed evidence. Sources: claude:claude:commercial-certifications-20261026. - soc2 — SOC 2 type, period and covered service? [partial]: The commercial privacy page lists SOC 2 Type I and Type II. The auditor, report period and detailed service scope were not inspected. Sources: claude:claude:commercial-certifications-20261026. - c5 — BSI C5 attestation? [unknown]: BSI C5 attestation? Unverified after checking public DPA and Trust Center; issuer, covered entity/product, period and validity of ISO/SOC/C5/other attestations were not verified. Search on 2026-10-26: https://www.anthropic.com/legal/data-processing-addendum, https://www.anthropic.com/legal/commercial-terms, https://trust.anthropic.com/. No additional scoped evidence established this answer. - other_certifications — Which other certificates (27701, 42001, TISAX)? [partial]: The commercial privacy page claims ISO/IEC 42001:2023. No issuing-body certificate, validity dates or TISAX/ISO 27701 scope was inspected. Sources: claude:claude:commercial-certifications-20261026. - report_access — How can customers obtain reports? [supported]: DPA F and Schedule 2 direct customers to the Trust Center and offer applicable reports/certificates on written request under confidentiality. No protected report was requested or downloaded. Sources: claude:cl-dpa-20261026. - pentest — Are independent penetration test summaries available? [partial]: DPA Schedule 2 G.2 commits to annual external penetration tests and a customer-request summary; no summary or testing period was inspected. Sources: claude:cl-dpa-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-dpa-20261026, claude:claude:commercial-certifications-20261026 #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### DATA-08: Encryption and key control Judgment rule: Record encryption at rest and in transit, customer-managed keys (BYOK/HYOK), key location, and private networking (private link, IP allow-lists, VPN). #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The DPA specifies encryption and logical isolation; Enterprise adds eligible customer keys and IP controls. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - encryption_at_rest — Is data encrypted at rest? [supported]: DPA Schedule 2 E specifies at least AES-256 at rest and TLS 1.2+ over public networks. Sources: claude:cl-dpa. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Eligible Enterprise organizations can connect AWS/GCP/Azure KMS keys for specified content; key locations and all feature exclusions need account-specific verification. Sources: claude:cl-cmek. - private_networking — Is private connectivity or IP restriction available? [partial]: Enterprise IP CIDR allowlisting is enabled through support; externally shared artifacts can remain outside it. Private Link/VPN-only service endpoints were not established. Sources: claude:cl-ip. - tenant_isolation — How are customers separated in shared SaaS? [supported]: DPA Schedule 2 H specifies logical separation of customer data and network segmentation; no independent isolation test was performed. Sources: claude:cl-dpa. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-dpa, claude:cl-cmek, claude:cl-ip #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Network and storage security depend on the customer’s deployment; application authentication does not certify encryption of all stored content. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - customer_managed_keys: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. - tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - encryption_at_rest — Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. Sources: librechat:librechat:auth, librechat:librechat:compose-pin. - private_networking — Is private connectivity or IP restriction available? [supported]: Operators deploy the stack on their own network and configure reverse proxies/HTTPS for remote access. Sources: librechat:librechat:remote, librechat:librechat:local. - tenant_isolation — How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:auth, librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:local ### DATA-09: Professional secrecy Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Personnel confidentiality and controlled safety review are documented; a qualified professional-secrecy contract or add-on remains unverified. Availability: unknown Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=German §203 StGB and Swiss Art.321 StGB use cases; existing hosting, support and provider-location exceptions still apply.; os=not specified. Limitations: - General confidentiality, a DPA and no-training commitments do not establish a professional-secrecy undertaking. No vendor/sales contact or agreement signing was performed. - No legal compliance verdict; unknown does not mean the offering is unavailable. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Does the undertaking extend to its sub-processors, and is that documented? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: Is it a dedicated offering or add-on, and on which plan? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Commercial Terms E and DPA B.7/Schedule2 constrain authorized personnel and subprocessor processing; Covered Model retained data can be accessed by approved safety reviewers through a logged controlled path. A complete subprocessor plain-text access matrix and §203/Art.321-specific restriction were not verified. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-covered-review. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-covered-review #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified. - Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom ## Commercials and vendor ### VEN-01: Pricing model and list prices Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team bundles usage while current Enterprise separates seat access from all token usage. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - pricing_unit — What is the pricing unit? [supported]: Team uses Standard/Premium seats with included limits; usage-based Enterprise uses access seats plus separate API-rate token consumption. Legacy Enterprise has different billing. Sources: claude:cl-pricing, claude:cl-enterprise. - list_prices — What are list prices per plan, with date and currency? [supported]: Retrieved 2026-10-21: Team Standard USD 20/month annual or USD 25 monthly; Premium USD 100 annual or USD 125 monthly. Enterprise USD 20/seat/month billed annually, before usage/tax. Sources: claude:cl-pricing, claude:cl-enterprise. - included_usage — What usage is included? [partial]: Team Premium advertises five times Standard usage; exact reproducible message/token quotas were not established. Current Enterprise includes no token usage. Sources: claude:cl-pricing, claude:cl-enterprise. - add_ons — Which features cost extra? [partial]: Enterprise model usage costs extra; applicable US-only inference adds 10%. Third-party services/credits and optional-service charges are not fully priced. Sources: claude:cl-enterprise, claude:cl-us-only. - overage — What do usage beyond limits and premium models cost? [partial]: Enterprise bills all usage at current API rates; Sonnet 5.5 list rate is USD 2/M input and USD 10/M output. Team/legacy overage and each tool surcharge were not exhaustively priced. Sources: claude:cl-enterprise, claude:cl-api-prices. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-enterprise, claude:cl-us-only, claude:cl-api-prices #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. - overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. - pricing_unit — What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat. - list_prices — What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat. - included_usage — What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat. - add_ons — Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images. - overage — What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens ### VEN-02: Scenario cost Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise list-cost scenarios separate the USD 240 annual access seat floor from modeled Sonnet usage and unpriced services. Availability: generally-available Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Current usage-based Enterprise; standard global inference; admin-configured Sonnet 5.5 low-effort chat scenario; add_ons=All token usage at API list rates, Third-party services and implementation unpriced; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - All figures exclude VAT and invented discounts. Team is capped at 150 seats and is not extrapolated to these sizes. Annual Enterprise access commitment is separate from consumption. - cost_200 — Year-one cost at 200 users? [partial]: From USD 57,504.00 / EUR 51,274.19 / CHF 47,361.97 + unknown services under the disclosed Sonnet 5.5 low-effort chat workload: USD 48,000.00 access seats + USD 9,504.00 modeled tokens. The seat-only floor is USD 48,000.00 / EUR 42,799.82 / CHF 39,534.20. This is modeled list cost, not observed usage or a quote. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020. - cost_1000 — Year-one cost at 1,000 users? [partial]: From USD 287,520.00 / EUR 256,370.93 / CHF 236,809.83 + unknown services under the disclosed Sonnet 5.5 low-effort chat workload: USD 240,000.00 access seats + USD 47,520.00 modeled tokens. The seat-only floor is USD 240,000.00 / EUR 213,999.11 / CHF 197,670.98. This is modeled list cost, not observed usage or a quote. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020. - cost_5000 — Year-one cost at 5,000 users? [partial]: From USD 1,437,600.00 / EUR 1,281,854.66 / CHF 1,184,049.15 + unknown services under the disclosed Sonnet 5.5 low-effort chat workload: USD 1,200,000.00 access seats + USD 237,600.00 modeled tokens. The seat-only floor is USD 1,200,000.00 / EUR 1,069,995.54 / CHF 988,354.88. This is modeled list cost, not observed usage or a quote. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020. - variable_share — Which part depends on usage? [supported]: ALM-14 shared cost assumptions v1.4, 2026-10-21: 12 months, 60% light 100/30% regular 400/10% power 1500 messages monthly = 330/user/month; 3000 input+600 billable output tokens/message incl retrieval/thinking. At Sonnet 5.5 USD 2/M input+USD 10/M output, 11.88M input+2.376M output/year costs USD 47.52/user; access USD 240 => modeled USD 287.52/user/year. Sonnet low effort is the scenario choice, with an admin-configurable default, based on the consumption guide; not a universal fixed default. Sources: claude:cl-consumption, claude:cl-api-prices, claude:cl-enterprise. - unknown_parts — Which costs could not be priced? [partial]: Unpriced: implementation, onboarding/support add-ons, third-party subscriptions and workflow-specific extra tool/context/repeated-step tokens. Scenario excludes US-only 1.1x premium, tax, discounts, cache/batch benefits and agent workloads beyond the fixed token allowance; these require separate pricing. EUR=USD/1.1215; CHF=EUR*0.9237, ECB 2026-10-20. Sources: claude:cl-enterprise, claude:cl-us-only, claude:cl-api-prices, claude:fx-20261020. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020, claude:cl-us-only #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified. Limitations: - ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise. - The budget is a floor because named infrastructure and service costs are unpriced. - cost_200 — Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_1000 — Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_5000 — Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - variable_share — Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort. - unknown_parts — Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort ### VEN-03: Evaluation access Judgment rule: Distinguish free tier, self-serve trial, sales-led pilot, paid proof of concept and open-source self-install. Record card requirement, duration, seat limit, and which features (SSO, connectors, admin) the trial includes. Map which shared scenarios can be run without sales approval. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial self-service purchase is documented; free consumer access is not a scoped Enterprise trial. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: self_serve_trial, trial_scope. - Read each atomic answer for its plan, access and feature limits. - free_tier — Is there a free tier for business use? [partial]: Claude Free is a separate consumer plan; no free Team/Enterprise organization entitlement was established. Sources: claude:cl-pricing. - self_serve_trial — Is a self-serve business trial available? [unknown]: Is a self-serve business trial available? Unverified after checking pricing and Enterprise acquisition guides; no self-serve business trial duration, card rule or trial identity/compliance/connector inclusion confirmed. - trial_scope — Do trials include SSO, connectors and admin features? [unknown]: Do trials include SSO, connectors and admin features? Unverified after checking pricing and Enterprise acquisition guides; no self-serve business trial duration, card rule or trial identity/compliance/connector inclusion confirmed. - sales_gate — Does meaningful evaluation require sales contact? [supported]: Team can be bought self-serve. Enterprise self-serve starts at 20 seats; sales-assisted Enterprise starts at 50. No purchase or sales contact was performed. Sources: claude:cl-enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-enterprise #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Customers can self-install without licence payment; the public demo is an evaluation-only alternative. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - free_tier — Is there a free tier for business use? [supported]: MIT self-installation permits organizational use without a software licence fee. Sources: librechat:librechat:license. - self_serve_trial — Is a self-serve business trial available? [supported]: Self-installation has no trial clock or software card requirement; the free hosted Demo can be tried separately under its terms. Sources: librechat:librechat:local, librechat:librechat:demo. - trial_scope — Do trials include SSO, connectors and admin features? [supported]: Self-installed instances can configure SSO, Agents, file retrieval and administration with their own service accounts. It is not evidence that every experimental add-on is enabled by default. Sources: librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag. - sales_gate — Does meaningful evaluation require sales contact? [supported]: The documented Docker install does not require sales approval; optional third-party services have separate account requirements. Sources: librechat:librechat:local, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:demo, librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag, librechat:librechat:firstchat ### VEN-04: Contract terms and pricing transparency Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Seat prices are public, with plan caps, annual Enterprise commitment and variable usage. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - minimum_commitment — What seat or spend minimum applies? [supported]: Team: 2-150 seats. Current Enterprise self-serve: 20-seat minimum; sales-assisted: 50. Sources: claude:cl-pricing, claude:cl-enterprise. - contract_length — What contract lengths are offered? [supported]: Team lists monthly and annual billing; Enterprise access seats are annual. Consumption is additional under the purchase route. Sources: claude:cl-pricing, claude:cl-enterprise. - cancellation — How can the contract be cancelled or reduced? [partial]: General Terms I.2 permit customer termination with notice and vendor convenience termination with30-day notice; annual seat refunds, reductions and renewal cancellation depend on plan/order and were not verified. Sources: claude:cl-terms. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [partial]: Enterprise self-serve bills USD by credit/ACH; sales-assisted supports multicurrency/invoicing. Irish contracting is stated for Swiss/EEA customers, but a CHF/EUR invoice tariff was not verified. Sources: claude:cl-enterprise, claude:cl-terms. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Partially specified: public seat/API rates and minimums, but actual consumption, third-party services, Enterprise optional charges and local invoice terms require more detail. Sources: claude:cl-enterprise, claude:cl-api-prices. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-enterprise, claude:cl-terms, claude:cl-api-prices #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. - minimum_commitment — What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license. - contract_length — What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license. - cancellation — How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat ### VEN-05: Source licence Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial service rights are public; a complete component-source licence inventory was not established. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: branding_restrictions, enterprise_features_closed. - Read each atomic answer for its plan, access and feature limits. - licence_type — Which licence applies to each component? [partial]: Commercial Terms grant service use and allocate customer input/output rights; this does not establish an OSI licence for the hosted platform, clients or connector code. Sources: claude:cl-terms. - branding_restrictions — Do licence terms restrict branding or user counts? [unknown]: Do licence terms restrict branding or user counts? Unverified after checking Commercial Terms and public Claude Code issue repository; component revisions, client/server/connector source licences, branding restrictions and separate enterprise-edition source status not verified. - enterprise_features_closed — Are enterprise features in a separate closed edition? [unknown]: Are enterprise features in a separate closed edition? Unverified after checking Commercial Terms and public Claude Code issue repository; component revisions, client/server/connector source licences, branding restrictions and separate enterprise-edition source status not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. - licence_type — Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code ### VEN-06: Data export and exit Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team/Enterprise exports provide conversations but do not prove portable assistants and knowledge. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - chat_export: Team/Enterprise Primary Owners export organization conversation/user data, excluding deleted items. Members can export their own chats if enabled; uploaded-file contents are excluded. - assistant_export: Can assistants and prompts be exported in a reusable format? Unverified after checking organization/member export and Compliance API docs; no export fixture, reusable assistant/prompts or complete knowledge-base/source-file package verified. Search on 2026-10-26: https://support.claude.com/en/articles/13346720-export-your-organization-s-data, https://support.claude.com/en/articles/9450526-export-your-claude-data, https://support.claude.com/en/articles/13015708-access-the-compliance-api. No additional scoped evidence established this answer. - knowledge_export: The organization export guide covers conversation/user data and excludes generated Office/PDF files; members’ personal exports exclude uploaded-file contents. A complete reusable project/knowledge-source archive was not established and no export fixture was run. - export_format: Documented exports and Compliance API support structured access; the complete archive schema/file manifest was not downloaded or inspected. - chat_export — Can admins export all chats? [partial]: Team/Enterprise Primary Owners export organization conversation/user data, excluding deleted items. Members can export their own chats if enabled; uploaded-file contents are excluded. Sources: claude:cl-export-org-20261026, claude:cl-export-user-20261026. - assistant_export — Can assistants and prompts be exported in a reusable format? [unknown]: Can assistants and prompts be exported in a reusable format? Unverified after checking organization/member export and Compliance API docs; no export fixture, reusable assistant/prompts or complete knowledge-base/source-file package verified. Search on 2026-10-26: https://support.claude.com/en/articles/13346720-export-your-organization-s-data, https://support.claude.com/en/articles/9450526-export-your-claude-data, https://support.claude.com/en/articles/13015708-access-the-compliance-api. No additional scoped evidence established this answer. - knowledge_export — Can knowledge bases and their sources be exported? [partial]: The organization export guide covers conversation/user data and excludes generated Office/PDF files; members’ personal exports exclude uploaded-file contents. A complete reusable project/knowledge-source archive was not established and no export fixture was run. Sources: claude:cl-export-org-20261026, claude:cl-export-user-20261026. - export_format — Are formats documented and machine-readable? [partial]: Documented exports and Compliance API support structured access; the complete archive schema/file manifest was not downloaded or inspected. Sources: claude:cl-export-org-20261026, claude:cl-compliance-20261026. - post_termination_window — How long can data be retrieved after termination? [supported]: DPA H requires a return request within 30 days after expiry/termination, with deletion obligations and legal/dispute/harmful-use exceptions. Sources: claude:cl-dpa-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-export-org-20261026, claude:cl-export-user-20261026, claude:cl-compliance-20261026, claude:cl-dpa-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. - assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. - knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - chat_export — Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - export_format — Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin. - post_termination_window — How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api ### VEN-07: Support and service levels Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public support/status channels exist; local-language commitments and contractual SLA remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - support_channels: Help Center support is available; Enterprise self-serve and sales-assisted support/CSM arrangements differ. Exact response times/hours were not established. - support_languages: Is support available in German, French or Italian? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - regional_presence: Anthropic’s November 2025 company announcement identifies an existing Zurich office and planned Munich expansion. Current staffing, Swiss contracting terms and local-language support guarantees were not established. - uptime_sla: Is there an uptime SLA with credits? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - support_channels — Which support channels are available on each plan? [partial]: Help Center support is available; Enterprise self-serve and sales-assisted support/CSM arrangements differ. Exact response times/hours were not established. Sources: claude:cl-enterprise-20261026. - support_languages — Is support available in German, French or Italian? [unknown]: Is support available in German, French or Italian? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - regional_presence — Is there a DACH or Swiss entity, team or partner? [partial]: Anthropic’s November 2025 company announcement identifies an existing Zurich office and planned Munich expansion. Current staffing, Swiss contracting terms and local-language support guarantees were not established. Sources: claude:claude:regional-presence-20261026. - uptime_sla — Is there an uptime SLA with credits? [unknown]: Is there an uptime SLA with credits? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - status_page — Is there a public status page with history? [supported]: status.claude.com publishes component health and incident history; it is not a contractual reliability score. Sources: claude:cl-status-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-enterprise-20261026, claude:cl-status-20261026, claude:claude:regional-presence-20261026 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public project/community channels are available; a binding business support SLA was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. - support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - support_channels — Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat. - support_languages — Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla — Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page — Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat ### VEN-08: Onboarding, training and adoption Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Academy tutorials and use-case material are public; commercial service entitlements need clarification. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: onboarding_service, adoption_programme, service_cost. - Read each atomic answer for its plan, access and feature limits. - onboarding_service — Is guided onboarding included? [unknown]: Is guided onboarding included? Unverified after checking Academy, pricing and Enterprise comparison; included guided onboarding, champion programme, paid professional-services scope and charges not established. - user_training — Is end-user training offered, in which languages? [partial]: Claude Academy provides written/video training for chat, Cowork, Office, connectors and skills; German/French/Italian delivery was not established. Sources: claude:cl-academy. - use_case_library — Are role-based use cases and templates provided? [partial]: Academy has workflow/tutorial examples and Office use cases; the library was not exhaustively mapped to organizational roles. Sources: claude:cl-academy. - adoption_programme — Is there a champion or adoption programme? [unknown]: Is there a champion or adoption programme? Unverified after checking Academy, pricing and Enterprise comparison; included guided onboarding, champion programme, paid professional-services scope and charges not established. - service_cost — Which services cost extra? [unknown]: Which services cost extra? Unverified after checking Academy, pricing and Enterprise comparison; included guided onboarding, champion programme, paid professional-services scope and charges not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-academy #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. - adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - onboarding_service — Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training — Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library — Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost — Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat ## Sources ### claude:claude:fable-plan-20261026 Claude Fable models on your plan. Fable 5/5.1 are available on paid plans. Team/legacy Enterprise Premium include a capped share of weekly usage; Standard uses paid usage credits. Current usage-based Enterprise bills at API rates. Organization model access can restrict availability. - URL: https://support.claude.com/en/articles/15424964-claude-fable-models-on-your-plan - Locator: How Fable models work on each plan and model-picker access; HTTP 200, body SHA256 c7e39ae19952ae2186de8c95a8034bd16a43b7da9e5b6750eca0b7c30614456a - Evidence kind: documented - Source date: 2026-09-02 - Retrieved: 2026-10-26 ### claude:claude:transparent-fallback-20261026 Claude Fable automatic model switching. Hosted Fable safety fallbacks rerun requests on an Opus model with a visible switch notice and response model label. Users can disable automatic switching. This is a safety fallback, not general task-based multi-provider routing. - URL: https://support.claude.com/en/articles/15363606-why-claude-switched-models-in-your-conversation-with-fable-5-or-fable-5-1 - Locator: What happens after a fallback, settings and where switching applies; HTTP 200, body SHA256 98a2769ab04b54a170b3034afde3b042c016f76ccd332e98c4065288a60ea846 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-model-menu-r2-20261026 Change the model, effort, and thinking settings. The chat-selector guide names model families and effort controls but does not provide a complete Team seat-tier or per-product entitlement matrix. - URL: https://support.claude.com/en/articles/8664678-change-the-model-effort-and-thinking-settings - Locator: Chat selector; supported effort models; Enterprise restrictions; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 74026587f919fac61d5fc3f4747ea1c889b2d3b2b6b2ee895dfbcc2dfae25cae on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-context-plans-r2-20261026 Context windows on paid Claude plans. The paid-plan guide distinguishes Chat and Cowork context/model tables; it does not guarantee every model on each Team seat tier or Office add-in. - URL: https://support.claude.com/en/articles/8606394-how-large-is-the-context-window-on-paid-claude-plans - Locator: Paid-plan scope; separate Chat and Cowork tables; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 6f8fa356708c3a887106e33876dea65b71a3a9dae2ec09600ef035e14cb448e4 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-upload-r2-20261026 Upload files to Claude. The attachment guide specifies500 MB chat uploads,30 MB project files, and separate PDF visual/text behavior; these are not universal tool-path limits. - URL: https://support.claude.com/en/articles/8241126-upload-files-to-claude - Locator: Chat attachments versus project Files; PDF handling; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 640974fd8725ee528375e7fca7fe66265f94a30fb0c82071022d3da529b437ed on 2026-10-26 - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-26 ### claude:cl-pricing-20261026 Claude pricing. Team is listed for 2-150 seats with Standard/Premium pricing; current Enterprise lists USD 20/seat/month annual access plus usage and a 20-seat self-serve minimum. - URL: https://claude.com/pricing - Locator: Team/Enterprise cards; commercial comparison; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 9dac8ef940d7d07738f28ea203879b59cd98dfefd0bef624a91b361049a23a9f on 2026-10-26 - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-model-control-20261026 Manage model access for your organization. Enterprise controls model/effort access by organization and custom role, while Haiku cannot be disabled and coverage has named exceptions. - URL: https://support.claude.com/en/articles/15694740-manage-model-access-for-your-organization - Locator: Organization and custom-role ceilings; Haiku exception; coverage; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 449e547e02b145fe3878d3591a80eca230ddff996580d601b38f007b78aba179 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:custom Custom endpoints. Operators configure compatible endpoints and customer-held keys, including local and hosted services. - URL: https://www.librechat.ai/docs/quick_start/custom_endpoints - Locator: Endpoint setup; API key; base URL; model list - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:azure Azure OpenAI configuration. Azure OpenAI uses customer deployment groups, instance names and credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/azure - Locator: Deployment groups; API credentials - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:bedrock AWS Bedrock object structure. Bedrock routes use customer AWS configuration and region selection. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/aws_bedrock - Locator: Region; credentials; model selection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:vertex Anthropic Vertex AI configuration. Claude can run through customer Google Vertex AI credentials and regions. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/anthropic_vertex - Locator: Project and region configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:modelspec Model specifications. Administrators can enforce configured model presets and defaults; available endpoints still depend on customer credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/model_specs - Locator: enforce; preset; modelSelect; addedEndpoints - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:agents Agents. Agents combine instructions, models, files, tools, skills and sharing permissions, with visible execution and configurable approval. - URL: https://www.librechat.ai/docs/features/agents - Locator: Builder; Capabilities; Version history; Sharing; Activity; tool approval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:ocr OCR for documents. OCR can augment text extraction, or files can be sent to compatible provider APIs; format and model limitations remain. - URL: https://www.librechat.ai/docs/features/ocr - Locator: File Context; Upload as Text; Optional OCR; Limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:releases LibreChat v0.8.8 release. The stable release documents agent controls, current model updates and explicitly experimental schedules/workspaces and beta Agents API. - URL: https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8 - Locator: Highlights, 2026-10-01 - Evidence kind: documented - Source date: 2026-10-01 - Retrieved: 2026-10-21 ### claude:cl-release Claude release notes. Dated notes distinguish current models, cloud/unified Cowork rollout, memory defaults and connector changes. - URL: https://support.claude.com/en/articles/12138966-release-notes - Locator: Model launches; memory; Office/connector changes; Cowork transition - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-haiku-notice Claude Haiku 4.5 is leaving the model selector. The dated consumer Haiku retirement excludes Team/Enterprise, so it does not prove removal from their model catalogue. - URL: https://support.claude.com/en/articles/17444146-claude-haiku-4-5-is-leaving-the-model-selector - Locator: October 15 notice; October 29 removal; Team/Enterprise exceptions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-office Claude for Microsoft 365. Claude advertises native Excel/PowerPoint/Word add-ins, Outlook beta and optional Foundry/Bedrock/Gemini Enterprise Agent Platform credentials. - URL: https://claude.com/claude-for-microsoft-365 - Locator: App capabilities; GA/beta; cloud credentials; review controls - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:firstchat Your first chat. LibreChat ships without a model key; the public demo is for evaluation rather than private or durable data. - URL: https://www.librechat.ai/docs/quick_start/first_chat - Locator: Software you host yourself; endpoint credentials; public demo - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:code Code Interpreter API. A separate code execution service supports multiple languages and downloadable generated files; stateful/attached modes are experimental. - URL: https://www.librechat.ai/docs/features/code_interpreter - Locator: Setup; self-hosted service; workspace permissions; generated files - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:license LibreChat v0.8.8 MIT licence. The pinned repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/LICENSE - Locator: LICENSE, permission grant and notice requirement - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:ragcfg RAG API configuration. OpenAI, Hugging Face and Ollama embedding configurations are documented; image choice affects local embedding support. - URL: https://www.librechat.ai/docs/configuration/rag_api - Locator: Embedding providers; lite image; full image - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-enterprise What is the Enterprise plan?. Current Enterprise has no included tokens, bills all usage at API rates and differs from legacy seat-based arrangements. - URL: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan - Locator: Pricing; self-serve versus sales-assisted; legacy sections - Evidence kind: documented - Source date: 2026-09-01 - Retrieved: 2026-10-21 ### claude:cl-model-control-r2 Manage model access for your organization. Enterprise model and effort access uses organization ceilings/custom roles; Haiku cannot be disabled and product/version limits apply. - URL: https://support.claude.com/en/articles/15694740-manage-model-access-for-your-organization - Locator: Enterprise eligibility; role ceilings; Haiku; fallback/coverage - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-default-r2 Set a default model for your organization. Enterprise defaults are distinct from the beta forced-start switch, which preserves existing chat-project choices and permits in-chat changes. - URL: https://support.claude.com/en/articles/15330088-set-a-default-model-for-your-organization - Locator: Ordinary defaults; Always start beta; projects and product fallback - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:access Granular access control. Roles, groups and resource ACLs govern features and sharing, with Entra groups synchronized at sign-in. - URL: https://www.librechat.ai/docs/features/access_control - Locator: Feature permissions; Resource ACLs; System grants; Groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:admin LibreChat Admin Panel. A separate browser management panel is available for testing and uses the underlying LibreChat admin APIs. - URL: https://www.librechat.ai/docs/features/admin_panel - Locator: Status Preview; separate service; admin APIs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:balance Balance configuration. Optional token-credit balances initialize and refill user credits; tracking is disabled by default. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/balance - Locator: enabled; startBalance; refill configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mod Automated moderation. Moderation scores abusive login/registration/message activity and may ban users; it is not a documented content DLP classifier. - URL: https://www.librechat.ai/docs/features/mod_system - Locator: Violation scoring and limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:balance-pin LibreChat balance admission implementation. The pinned middleware reserves user credits and throws a TOKEN_BALANCE error when the reservation cannot be admitted. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/packages/api/src/middleware/checkBalance.ts - Locator: packages/api/src/middleware/checkBalance.ts, checkBalance - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: packages/api/src/middleware/checkBalance.ts ### claude:cl-rag Retrieval augmented generation for projects. Paid projects automatically switch to retrieval when knowledge approaches context limits and show a RAG indicator. - URL: https://support.claude.com/en/articles/11473015-retrieval-augmented-generation-rag-for-projects - Locator: Activation; search tool; context indicator - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-upload-r2 Upload files to Claude. The attachment guide specifies500 MB chat uploads,30 MB project files, and separate PDF visual/text behavior; these are not universal tool-path limits. - URL: https://support.claude.com/en/articles/8241126-upload-files-to-claude - Locator: Chat attachments versus project Files; PDF handling - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-21 ### claude:cl-code-files-r2 Create and edit files with Claude. Chat code/file tools create Office/PDF output and document a30 MB upload/download path; the same page has inconsistent Team egress defaults. - URL: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude - Locator: Availability; computing/file-tool limits; file output; network sections - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:rag RAG API. A separate RAG API indexes uploaded content in PostgreSQL/PGVector for retrieval. - URL: https://www.librechat.ai/docs/features/rag_api - Locator: Architecture; document indexing; embeddings; semantic search - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:text Upload files as text. Text upload injects extracted file content rather than relying only on vector retrieval. - URL: https://www.librechat.ai/docs/features/upload_as_text - Locator: Full text extraction and context - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:filecfg File configuration. File limits and formats are configurable by endpoint and file processing route. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/file_config - Locator: File limits; MIME patterns; provider routes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:r4-spreadsheet-parser LibreChat spreadsheet text parser. The built-in parser accepts XLSX/XLS/ODS and serializes each sheet as its name followed by CSV values. It does not establish preserved workbook layout, recalculated formulas or fixture accuracy. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/files/documents/crud.ts - Locator: getParserForMimeType; excelSheetToText, lines 109-129 - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/files/documents/crud.ts ### librechat:librechat:r4-text-current LibreChat current Upload as Text guide. The development guide lists XLSX/XLS/ODS parsing up to 15 MB and token-bounded text injection, not a formatted spreadsheet editor. - URL: https://www.librechat.ai/docs/features/upload_as_text - Locator: Built-in parser; supported documents; truncation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-upload Upload files to Claude. The page distinguishes 500 MB chat uploads, 30 MB project files and PDF visual processing up to 100 pages. - URL: https://support.claude.com/en/articles/8241126-upload-files-to-claude - Locator: Formats; chat/project limits; visual PDF processing - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-21 ### claude:cl-projects What are projects?. Projects persist selected knowledge/instructions and provide organization sharing with view/edit permissions. - URL: https://support.claude.com/en/articles/9517075-what-are-projects - Locator: Knowledge; instructions; Team/Enterprise collaboration - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-21 ### claude:cl-groups Manage groups and group spend limits on Enterprise plans. Enterprise groups support roles and shared resources, per-user limits and optional shared monthly budgets in beta. - URL: https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans - Locator: Group sharing; SCIM; role controls; budgets - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:projects Projects. Projects persist files and instructions across a user’s chats but cannot be shared or transferred. - URL: https://www.librechat.ai/docs/features/projects - Locator: Availability; personal scope; files and instructions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:atlassian-enterprise-20261026 Enterprise-managed authorization for MCP connectors. Claude Enterprise documents generally available organization-managed authorization through Okta for named MCP providers including Atlassian. Its Atlassian section names Jira, Confluence and Teamwork Graph. - URL: https://claude.com/blog/enterprise-managed-auth - Locator: August 24 GA update and Atlassian Rovo MCP description; HTTP 200, body SHA256 5d973cd85982883fc28f409f6919e829a1e3791223634ca167e12524c411284e - Evidence kind: documented - Source date: 2026-08-24 - Retrieved: 2026-10-26 ### claude:cl-mcp-20261026 Get started with custom connectors using remote MCP. Remote MCP originates from Anthropic cloud, can use per-user OAuth or shared credentials, and differs from Desktop-local MCP. - URL: https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp - Locator: Network route; owner publication; OAuth/request headers; local distinction; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 e6307ff6f907b387075c5f8db3a45fae8cf8ea9eb15fd576b44f3368e1c5ed43 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-release-20261026 Claude release notes. Dated notes distinguish current models, cloud/unified Cowork rollout, memory defaults and connector changes. - URL: https://support.claude.com/en/articles/12138966-release-notes - Locator: Model launches; memory; Office/connector changes; Cowork transition; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 07f9dcfff3c0fc1f7a6060ad0b718558075286175f3b4e1b13c665d79cab3616 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-enterprise-20261026 What is the Enterprise plan?. Current Enterprise has no included tokens, bills all usage at API rates and differs from legacy seat-based arrangements. - URL: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan - Locator: Pricing; self-serve versus sales-assisted; legacy sections; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 de2b461205d4426c558e88750f5be23f7d495804c407827fc5695ecd5e1a20ee on 2026-10-26 - Evidence kind: documented - Source date: 2026-09-01 - Retrieved: 2026-10-26 ### claude:cl-m365-20261026 Microsoft 365 connector security guide. The Anthropic-hosted Microsoft Graph proxy retrieves on demand without file-content caching and has separately enabled write tools and delegated permissions. - URL: https://support.claude.com/en/articles/12684923-microsoft-365-connector-security-guide - Locator: On-demand proxy; delegated permissions; consent; write controls; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 8965fd2ee1dbdd7b494b834a1cbae1cd4194bf096abd2d916244178108738d3f on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-google-20261026 Use Google Workspace connectors. Google connectors retrieve user-authorized data, sync referenced Google Docs and support live editing with separate app controls. - URL: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors - Locator: Sources; private project sync; live Docs/Sheets/Slides; authorization; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 b61eb14f3e2efb4ab2a9cc441eb6beb363b5514d3c55e6f9dc8cd2565d48d135 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:sharepoint SharePoint and OneDrive integration. The Microsoft file picker uses Entra token reuse and delegated on-behalf-of downloads to attach files. - URL: https://www.librechat.ai/docs/configuration/sharepoint - Locator: Prerequisites; delegated permissions; admin consent - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mcp MCP. MCP servers can be configured through YAML or the permission-gated UI, including per-user OAuth. - URL: https://www.librechat.ai/docs/features/mcp - Locator: YAML/UI setup; authentication; ownership and selection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mcpcfg MCP server configuration. Configuration includes stdio, SSE and Streamable HTTP transports and server-specific credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/mcp_servers - Locator: Transport examples; headers; OAuth - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-m365 Microsoft 365 connector security guide. The Anthropic-hosted Microsoft Graph proxy retrieves on demand without file-content caching and has separately enabled write tools and delegated permissions. - URL: https://support.claude.com/en/articles/12684923-microsoft-365-connector-security-guide - Locator: On-demand proxy; delegated permissions; consent; write controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-m365-user Connect to Microsoft 365. Microsoft 365 connects SharePoint/OneDrive/Outlook/Teams, excludes Sites.Selected allowlisting and OneNote reads, and requires organizational consent. - URL: https://support.claude.com/en/articles/15183774-connect-to-microsoft-365 - Locator: Setup; supported content; site restrictions; permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-google Use Google Workspace connectors. Google connectors retrieve user-authorized data, sync referenced Google Docs and support live editing with separate app controls. - URL: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors - Locator: Sources; private project sync; live Docs/Sheets/Slides; authorization - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:compose-pin LibreChat Docker service configuration. The pinned example runs a MongoDB primary store and a separate PGVector/RAG service with customer-mounted data. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/docker-compose.yml - Locator: docker-compose.yml, api/mongodb/vectordb/rag_api services - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: docker-compose.yml ### claude:cl-memory-r2 Chat search and memory. Improved memory has Team/Enterprise owner controls and cloud-Cowork sharing; legacy Team lacks org controls and legacy memory is chat-only. - URL: https://support.claude.com/en/articles/11817273-use-claude-s-chat-search-and-memory-to-build-on-previous-context - Locator: Improved Settings>Memory versus legacy; owners; Cowork; exclusions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:memory User memory. Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats. - URL: https://www.librechat.ai/docs/features/memory - Locator: Key/value store; controls; disabled by default - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-academy Claude Academy tutorials. Academy publishes written/video guides for chat, connectors, agents, Office work and skills. - URL: https://academy.claude.com/tutorials - Locator: Chat; Cowork; Office; AI fluency guides - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-pricing Claude pricing. Team is listed for 2-150 seats with Standard/Premium pricing; current Enterprise lists USD 20/seat/month annual access plus usage and a 20-seat self-serve minimum. - URL: https://claude.com/pricing - Locator: Team/Enterprise cards; commercial comparison - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-mcp Get started with custom connectors using remote MCP. Remote MCP originates from Anthropic cloud, can use per-user OAuth or shared credentials, and differs from Desktop-local MCP. - URL: https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp - Locator: Network route; owner publication; OAuth/request headers; local distinction - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:images Image generation and editing. Agents can use configured image tools for generation/editing; provider credentials and model parameters are separate. - URL: https://www.librechat.ai/docs/features/image_gen - Locator: OpenAI Image Tools; provider setup; admin configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:web-search-controls-20261026 Enable and use Claude web search. Team/Enterprise Owners first enable web search for the workspace, after which members use it in chat. Search answers include citations and source links. The article does not identify a universal search backend or query-processing region. - URL: https://support.claude.com/en/articles/10684626-enable-and-use-web-search - Locator: Team/Enterprise workspace enablement and How web search works; HTTP 200, body SHA256 76f79d8a3eb4181b4e1028b23a4df9821c316008015fe0290feb4582d6b9a83d - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:web Web search. Search can use Serper, SearXNG, Tavily or Keenable, with independently configured scraping and optional reranking. - URL: https://www.librechat.ai/docs/features/web_search - Locator: Provider, scraper and reranker configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-cowork Get started with Claude Cowork. Paid Cowork runs multi-step tasks with local access where permitted and cloud task persistence, with Team/Enterprise cloud availability in beta. - URL: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork - Locator: Availability; cloud beta; task flow; tools; scheduling - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:schedule Scheduled Chats. Opt-in experimental schedules execute saved Agents with cron/time zones and recheck access and balance before running. - URL: https://www.librechat.ai/docs/features/scheduled_chats - Locator: Experimental and disabled by default; runtime and permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:api Agents API beta. The beta API exposes chat/Responses inference, Agent/Skill management and authenticated event delivery. - URL: https://www.librechat.ai/docs/features/agents_api - Locator: Inference; management; Agent Events; authentication - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:cowork-stop-20261026 Use Claude Cowork safely. The paid-plan Cowork safety guide instructs users to monitor and stop a task when needed. It does not promise rollback of completed external actions or a guaranteed cancellation boundary. - URL: https://support.claude.com/en/articles/13364135-use-claude-cowork-safely - Locator: Paid-plan availability, monitoring tasks and stopping suspicious behavior; HTTP 200, body SHA256 363aa11b90d168d68950bcf4820d677b076c63c1f27598be7d17ef04c727da24 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-cowork-20261026 Get started with Claude Cowork. Paid Cowork runs multi-step tasks with local access where permitted and cloud task persistence, with Team/Enterprise cloud availability in beta. - URL: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork - Locator: Availability; cloud beta; task flow; tools; scheduling; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 0c2c6bcedbe79e9bc84268a92da091133ea4c9737d6790eb74583def73350c02 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-compliance Access the Compliance API. Enterprise Compliance API exposes events, chats and file content with primary-owner activation and scoped organization keys. - URL: https://support.claude.com/en/articles/13015708-access-the-compliance-api - Locator: Eligibility; primary-owner activation; event/chat/file data - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-api-prices Claude Platform pricing. Current public API prices include Sonnet 5.5 at USD 2/M input and USD 10/M output, while model choice, tokens and features change usage cost. - URL: https://platform.claude.com/docs/en/about-claude/pricing - Locator: Model pricing table; regional rates; tool token charges - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-export-user Export your Claude data. Organization members can export their own chats when enabled, without uploaded-file contents; exports are web/Desktop only. - URL: https://support.claude.com/en/articles/9450526-export-your-claude-data - Locator: Team/Enterprise owner enablement; contents; 24-hour link - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:retention Temporary chat and data retention. Operators configure expiry for chats/messages/files/shared links; normal chats do not expire by default and memories are excluded. - URL: https://www.librechat.ai/docs/features/temporary_chat - Locator: Default 30-day temporary retention; all/ephemeral; deadlines; memories - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:insights Admin Insights. Insights reports persisted MongoDB activity and identifiable recent conversations; it is not monetary billing analytics. - URL: https://www.librechat.ai/docs/features/insights - Locator: Opt-in; capabilities; metrics; tenant scope - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:local Docker installation. Docker self-installation runs LibreChat with its configured service dependencies. - URL: https://www.librechat.ai/docs/local/docker - Locator: Installation; configuration; updating - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-google-addon Use Claude in Google Docs, Sheets, and Slides. A native Google Workspace sidebar beta supports Team/Enterprise, separate from connectors; edits require approval by default and extension data does not inherit organization retention. - URL: https://support.claude.com/en/articles/16951679-use-claude-in-google-docs-sheets-and-slides - Locator: Beta eligibility; native extension; approvals; data retention - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:image-generation-boundary-20261026 Can Claude produce images?. The vendor explicitly says Claude does not generate photos or illustrations like image-generation tools. HTML/SVG diagrams, charts and interactive visuals are a separate beta web/desktop capability; uploaded-image analysis is also separate. - URL: https://support.claude.com/en/articles/9002504-can-claude-produce-images - Locator: Native image generation versus HTML/SVG custom visuals; HTTP 200, body SHA256 4d918af1acc08fe9d2c1ea21ae840029c1c9109acad12cb2eaeeb8b8daab4da9 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:speech Speech configuration. Administrators configure audio provider engines and models separately from text generation. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/speech - Locator: Speech-to-text and text-to-speech engines - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:speech-conversation-r2 LibreChat conversation-mode speech settings. Conversation mode chains transcription, auto-send and TTS playback for hands-free turns after microphone activation; engines and audio routing are separately configured. - URL: https://www.librechat.ai/docs/configuration/stt_tts - Locator: Speech Tab: conversationMode, autoTranscribeAudio, autoSendText, automaticPlayback; engine and allowedAddresses settings - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-artifacts-admin Artifacts admin guide for Team and Enterprise plans. Admins control artifact templates, while standalone Claude Design closes 2026-12-14 and in-Claude design continues. - URL: https://support.claude.com/en/articles/16994751-artifacts-admin-guide-for-team-and-enterprise-plans - Locator: Templates; October defaults; standalone Design closure; data handling - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:artifacts Artifacts. Artifacts render generated React, HTML and Mermaid content in the chat interface. - URL: https://www.librechat.ai/docs/features/artifacts - Locator: React, HTML and Mermaid previews - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:share Shareable links. Shared links publish a transcript branch and optional file snapshots independently of the owner’s live file ACL. - URL: https://www.librechat.ai/docs/features/shareable_links - Locator: Authentication defaults; file snapshots; continuation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:display-languages-20261026 Claude display-language settings. Claude documents English, French, German, Italian, Hindi, Indonesian, Japanese, Korean, Brazilian Portuguese and Latin American/Spain Spanish interfaces on web and desktop. Voice language is a separate setting. - URL: https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language - Locator: Supported Languages and On Web and Desktop; HTTP 200, body SHA256 9a6fd87cbba7b558c9972e24b7bcd94249d6cb04003eea26541794f93dbae61b - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:i18n-pin LibreChat locale registration. The pinned client registers English, German, French and Italian translations among its supported locales. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/client/src/locales/i18n.ts - Locator: client/src/locales/i18n.ts, language resources - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: client/src/locales/i18n.ts ### claude:cl-sso Set up single sign-on. SSO and JIT are available to Team/Enterprise with owner configuration and verified domains. - URL: https://support.claude.com/en/articles/13132885-set-up-single-sign-on-sso - Locator: Team/Enterprise eligibility; IdP; owner roles; provisioning - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-provision Set up JIT or SCIM provisioning. Team supports JIT but not SCIM; Enterprise SCIM synchronizes membership and role/seat mappings with documented removal differences. - URL: https://support.claude.com/en/articles/13133195-set-up-jit-or-scim-provisioning - Locator: Plan eligibility; provisioning matrix; group mapping - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:auth Authentication system. Local/LDAP accounts can be required to use TOTP; federated MFA belongs to the identity provider and account creation/deletion scripts are documented. - URL: https://www.librechat.ai/docs/configuration/authentication - Locator: Required two-factor authentication; Registration; User scripts - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:openid OAuth2 and OIDC. LibreChat documents OAuth2/OIDC providers including Microsoft Entra, Google, Keycloak and Auth0. - URL: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC - Locator: Supported providers; setup - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:saml SAML authentication. SAML is a documented authentication option for the self-hosted application. - URL: https://www.librechat.ai/docs/configuration/authentication/SAML - Locator: Overview and requirements - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:entra Azure Entra authentication. Entra OIDC supports group-based admission and Graph integration using configured scopes and token reuse. - URL: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC/azure - Locator: Group claims; token reuse; Microsoft Graph integration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-model-control Manage model access for your organization. Enterprise controls model/effort access by organization and custom role, while Haiku cannot be disabled and coverage has named exceptions. - URL: https://support.claude.com/en/articles/15694740-manage-model-access-for-your-organization - Locator: Organization and custom-role ceilings; Haiku exception; coverage - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-analytics View usage analytics for Team and Enterprise plans. Admins have plan-scoped adoption and spend views, including per-user/model CSVs and separate seat-based overage reporting. - URL: https://support.claude.com/en/articles/12883420-view-usage-analytics-for-team-and-enterprise-plans - Locator: Roles; product/model/user data; CSV exports - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:tokens Token usage. Usage and estimated costs use recorded tokens and configured provider rates; transactions are distinct from balance enforcement. - URL: https://www.librechat.ai/docs/configuration/token_usage - Locator: Context cost; transactions; per-endpoint token rates - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-audit Access audit logs. Enterprise audit export covers 180 days of metadata, excludes prompt content and has a CMEK export limitation with a Compliance API alternative. - URL: https://support.claude.com/en/articles/9970975-access-audit-logs - Locator: Enterprise export; 180 days; fields; content exclusion; CMEK - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-compliance-partners Get started with Claude Compliance API integrations. The documentation lists partner compliance/eDiscovery/monitoring integrations; each integration needs separate scope and behavior verification. - URL: https://support.claude.com/en/articles/15167101-get-started-with-claude-compliance-api-integrations - Locator: Security, archive and eDiscovery partners - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:logging Logging. Backend operational logs are written to customer files and can feed external tools; the guide describes 14-day rotation rather than a compliance archive. - URL: https://www.librechat.ai/docs/configuration/logging - Locator: Error/debug logs; rotation; external tools - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-compliance-partners-r2 Get started with Claude Compliance API integrations. Enterprise Compliance integrations are Primary-Owner-enabled; Claude Platform has a separate scope and this is not a Team entitlement or proof of inline redaction. - URL: https://support.claude.com/en/articles/15167101-get-started-with-claude-compliance-api-integrations - Locator: Eligibility and Enterprise activation; monitoring/DLP partners - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:r4-content-filter LibreChat development content-filter configuration. Opt-in base-YAML policies inspect selected message/file content; block and audit differ from limited Agent text redaction. This is development documentation, not a hosted DLP assurance. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/message_filter - Locator: Source-Aware Filters; Pattern Configuration; Redaction; File Fields - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:r4-pii-runtime LibreChat content-inspection runtime. Source-aware configured inspection executes in the LibreChat API. Missing policy disables that scope; configured actions and fields bound inspection. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/runtime.ts - Locator: createConfiguredContentInspector; source rule configuration - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/runtime.ts ### librechat:librechat:r4-patterns LibreChat pattern detector. Default starter patterns detect credential-shaped tokens/headers. Operator custom patterns use bounded regular expressions; a generic comprehensive PII classifier is not established. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/detectors/pattern.ts - Locator: STARTER_PATTERNS; configured RE2JS rules - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/detectors/pattern.ts ### librechat:librechat:r4-private-submission LibreChat private text submission. The private text ingress permits configured redaction only on eligible fresh interactive Agent text. Original content is encrypted; edit/resume/file paths do not gain blanket redaction. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/private/submission.ts - Locator: createPrivateTextIngress; fresh Agent text and clientRequestId checks - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/private/submission.ts ### librechat:librechat:r4-filter-middleware LibreChat API content-filter middleware. The server middleware applies configured inspection and rejects blocked/uninspectable requests with HTTP 400. No deployment or detection fixture was run. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/middleware/messageFilterPii.ts - Locator: createMessageFilterPii; contentFilterBlockResponse; uninspectable response - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/middleware/messageFilterPii.ts ### librechat:librechat:r4-config-1318 LibreChat config v1.3.18 changelog. Dated development config changes add limited Agent text redaction and ephemeral retention mode. These are not a promise of universal redaction or a vendor zero-retention contract. - URL: https://www.librechat.ai/changelog/config_v1.3.18 - Locator: October 22, 2026; opt-in PII redaction; retention mode - Evidence kind: documented - Source date: 2026-10-22 - Retrieved: 2026-10-26 ### librechat:librechat:interface Interface configuration. Administrators configure UI feature permissions and usage terms in the self-hosted deployment. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/interface - Locator: Feature permissions; custom welcome and terms - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-servers Where are your servers located? Do you host your models on EU servers?. Commercial documentation says data is stored in the US, inference can route globally and internal support/safety processes can occur in affiliate countries. - URL: https://privacy.claude.com/en/articles/7996890-where-are-your-servers-located-do-you-host-your-models-on-eu-servers - Locator: Commercial global routing; US storage; internal processing - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-us-only Enable US-only inference for your organization. Usage-based Enterprise offers US-only inference at 1.1 times standard rates for applicable newer models, excluding storage and third-party processing. - URL: https://support.claude.com/en/articles/15422948-enable-us-only-inference-for-your-organization - Locator: Eligibility; billing; exclusions - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### librechat:librechat:remote Remote hosting. The application can be deployed on customer-selected remote servers with operator-managed security. - URL: https://www.librechat.ai/docs/remote - Locator: Hosting options; security considerations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-dpa Data Processing Addendum. The DPA covers confidential processing, subprocessors, audit access, security and post-termination return/deletion with transfer schedules. - URL: https://www.anthropic.com/legal/data-processing-addendum - Locator: B.7; C; E/F; H; SCC/Swiss schedules - Evidence kind: documented - Source date: 2025-02-24 - Retrieved: 2026-10-21 ### librechat:librechat:demo LibreChat Demo terms. The free hosted Demo is offered as-is with possible data cleanups and no durable business-service guarantee. - URL: https://www.librechat.ai/demo/terms - Locator: Evaluation scope; retention; disclaimer - Evidence kind: documented - Source date: 2026-03-12 - Retrieved: 2026-10-21 ### claude:cl-terms Commercial Terms of Service. Commercial terms prohibit model training on customer content, define EEA/Swiss/UK Irish contracting and provide confidentiality and commercial-use restrictions. - URL: https://www.anthropic.com/legal/commercial-terms - Locator: Customer content; confidentiality; contracting party; fees - Evidence kind: documented - Source date: 2025-06-17 - Retrieved: 2026-10-21 ### claude:cl-training Is my data used for model training?. Commercial content is not used for training by default; explicit feedback can be used and retained up to five years, with owner controls. - URL: https://privacy.claude.com/en/articles/7996868-is-my-data-used-for-model-training - Locator: Commercial default; feedback; disable feedback - Evidence kind: documented - Source date: 2026-08-18 - Retrieved: 2026-10-21 ### claude:cl-covered-r2 Covered Models. Covered Models have default minimum retention, with a separate limited agreement-based Fable ZDR exception for eligible internal-business applications. - URL: https://support.claude.com/en/articles/15425695-covered-models - Locator: Default retention; temporary eligible Fable exception; EFS - Evidence kind: documented - Source date: 2026-09-01 - Retrieved: 2026-10-21 ### claude:cl-covered-routes-r2 Data retention practices for Covered Models. The updated guide excludes notified exception customers from the standard ZDR-transition instructions and says hosted Enterprise Chat/Cowork already use standard retention. - URL: https://support.claude.com/en/articles/15425996-data-retention-practices-for-covered-models - Locator: ZDR configurations; eligible notices; cloud-provider storage; hosted Chat/Cowork - Evidence kind: documented - Source date: 2026-09-05 - Retrieved: 2026-10-21 ### claude:cl-retention-r2 How long do you store organization data?. Commercial saved-chat retention differs from API retention; backend deletion normally takes up to 30 days and safety/legal/feedback exceptions remain. - URL: https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data - Locator: Saved commercial chats; deletion; safety and feedback exceptions - Evidence kind: documented - Source date: 2026-07-01 - Retrieved: 2026-10-21 ### claude:cl-retention-admin-r2 Configure custom data retention controls for Enterprise plans. Current English guidance schedules over-age content on save and deletes through a daily background process, preserving project precedence and feature exclusions. - URL: https://support.claude.com/en/articles/10440198-configure-custom-data-retention-controls-for-enterprise-plans - Locator: Project precedence; daily deletion process; role and feature limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:settings Personal settings. Users configure interface language, audio and personal data controls. - URL: https://www.librechat.ai/docs/features/settings - Locator: Language; speech; data controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-gov Government requests for user information. Anthropic documents valid-process review, rejection of deficient requests, notice exceptions and generally directing enterprise requests to the customer. - URL: https://privacy.claude.com/en/articles/9519291-what-is-anthropic-s-policy-for-handling-governmental-requests-for-user-information - Locator: Valid process; challenge; customer notice; exceptions - Evidence kind: documented - Source date: 2026-03-16 - Retrieved: 2026-10-21 ### claude:cl-trust-route Anthropic subprocessor list access route. The public list URL redirects to a trust portal that returned no extractable entries in this research; countries and revision remain unverified. - URL: https://www.anthropic.com/subprocessors - Locator: DPA Schedule 4 link; redirect to trust.anthropic.com/subprocessors - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:owner ClickHouse acquisition of LibreChat. ClickHouse announced the acquisition of LibreChat and that Danny Avila and the team joined ClickHouse. - URL: https://clickhouse.com/blog/clickhouse-acquires-librechat - Locator: Announcement, November 4, 2025 - Evidence kind: documented - Source date: 2025-11-04 - Retrieved: 2026-10-21 ### claude:cl-ai-act Introducing Claude Fable 5.1 and Claude Mythos 5.1. The provider announcement describes transparency-code signing, watermarking for later models and a restricted-preview detection API; this is not a deployer compliance verdict. - URL: https://www.anthropic.com/claude-fable-and-mythos-5-1 - Locator: Compliance with the EU AI Act - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:commercial-certifications-20261026 Anthropic commercial compliance credentials. The commercial privacy page claims ISO 27001:2022, ISO/IEC 42001:2023 and SOC 2 Type I/II. Copies are request-gated; issuer, certificate/report scope, period and validity were not inspected. - URL: https://privacy.claude.com/en/articles/10015870-what-certifications-has-anthropic-obtained - Locator: Commercial-products applicability and credential list; HTTP 200, body SHA256 d44ecb66e9cf7636e39a9b9da3c61cc6513dfca890e68fcdaa1bc7051f310335 - Evidence kind: vendor-claimed - Source date: 2026-03-16 - Retrieved: 2026-10-26 ### claude:cl-dpa-20261026 Data Processing Addendum. The DPA covers confidential processing, subprocessors, audit access, security and post-termination return/deletion with transfer schedules. - URL: https://www.anthropic.com/legal/data-processing-addendum - Locator: B.7; C; E/F; H; SCC/Swiss schedules; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 c11e0d2d380f6155e900d4357d2a154e85cd0b38db427ca11e5048e02c375218 on 2026-10-26 - Evidence kind: documented - Source date: 2025-02-24 - Retrieved: 2026-10-26 ### claude:cl-cmek What are customer-managed encryption keys?. Eligible Enterprise organizations can use customer AWS/GCP/Azure master keys for certain chats, projects and files, with feature limitations. - URL: https://support.claude.com/en/articles/15505325-what-are-customer-managed-encryption-keys-cmek - Locator: Eligibility; customer KMS; scope - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-ip Restrict access to Claude with IP allowlisting. Enterprise supports source-IP CIDR restrictions configured through support; externally shared artifacts can remain outside that restriction. - URL: https://support.claude.com/en/articles/13200993-restrict-access-to-claude-with-ip-allowlisting - Locator: Enterprise eligibility; coverage; external sharing exception - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-covered-review Data retention practices for Covered Models. Controlled reviewers may inspect safety-flagged retained data, with logged access; normal chat/Cowork already use standard retention. - URL: https://support.claude.com/en/articles/15425996-data-retention-practices-for-covered-models - Locator: Human review; 30 days; affected ZDR configurations - Evidence kind: documented - Source date: 2026-09-05 - Retrieved: 2026-10-21 ### librechat:librechat:siteprivacy LibreChat website privacy policy. Website, demo and self-hosted software are distinct privacy scopes; website terms do not establish a customer deployment DPA. - URL: https://www.librechat.ai/privacy - Locator: Scope and exclusions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:secrecy-message-pin LibreChat v0.8.8 message storage schema. The pinned Mongoose schema declares message text as a String and content as mixed fields; this source does not establish operator exclusion from live content. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/packages/data-schemas/src/schema/message.ts - Locator: packages/data-schemas/src/schema/message.ts, text at lines 55-58 and content at lines 139-143 - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: packages/data-schemas/src/schema/message.ts ### librechat:librechat:secrecy-demo-policy LibreChat Demo privacy policy. The Demo policy describes model-provider transmission and contractual processor instruction/security duties for the Demo; it does not cover a customer self-hosted deployment. - URL: https://www.librechat.ai/demo/privacy - Locator: Scope; section 4 Third-Party AI Model Providers; section 6 Data Sharing and Sub-Processors - Evidence kind: documented - Source date: 2026-03-12 - Retrieved: 2026-10-21 ### claude:fx-20261020 ECB euro reference historical rates. Directly retrieved ECB XML gives EUR 1 = USD 1.1215 = CHF 0.9237. - URL: https://www.ecb.europa.eu/stats/eurofxref/eurofxref-hist.xml - Locator: Cube time=2026-10-20; USD and CHF - Evidence kind: documented - Source date: 2026-10-20 - Retrieved: 2026-10-21 ### claude:cl-consumption Claude Enterprise consumption guide. The guide recommends Sonnet for routine/high-volume work and lower effort, while administrators configure the actual default and usage controls. - URL: https://support.claude.com/en/articles/14782391-claude-enterprise-consumption-guide - Locator: Model/effort recommendations; defaults; limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-vm Azure Retail Prices, Switzerland North Linux VMs. EUR hourly PAYG rates retrieved 2026-10-21 are 0.2226, 0.4453 and 0.8905 for D4s, D8s and D16s v5 respectively. - URL: https://prices.azure.com/api/retail/prices?currencyCode=EUR&%24filter=armRegionName+eq+%27switzerlandnorth%27+and+serviceName+eq+%27Virtual+Machines%27+and+%28armSkuName+eq+%27Standard_D4s_v5%27+or+armSkuName+eq+%27Standard_D8s_v5%27+or+armSkuName+eq+%27Standard_D16s_v5%27%29+and+priceType+eq+%27Consumption%27 - Locator: Consumption; Virtual Machines Dsv5 Series; Standard_D4s_v5/D8s_v5/D16s_v5 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-pg Azure Retail Prices, PostgreSQL Flexible Server. EUR hourly PAYG GP compute is 0.2288, 0.4576 and 0.9152 for 2/4/8 vCore; storage is EUR 0.1325 per GB-month. - URL: https://prices.azure.com/api/retail/prices?currencyCode=EUR&%24filter=armRegionName+eq+%27switzerlandnorth%27+and+serviceName+eq+%27Azure+Database+for+PostgreSQL%27+and+priceType+eq+%27Consumption%27 - Locator: General Purpose Ddsv5 Series Compute, 2/4/8 vCore; Flex Server Storage - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-fx ECB euro reference rate history. The 2026-10-20 reference rates are EUR 1 = USD 1.1215 and CHF 0.9237. - URL: https://www.ecb.europa.eu/stats/eurofxref/eurofxref-hist.xml - Locator: Cube time=2026-10-20; USD and CHF - Evidence kind: documented - Source date: 2026-10-20 - Retrieved: 2026-10-21 ### librechat:librechat:cost-model OpenAI API pricing. Standard gpt-6-luna API price is USD 0.10 per million input tokens and USD 0.50 per million output tokens; caching, batch and regional premiums are separate. - URL: https://developers.openai.com/api/docs/pricing - Locator: Standard, short-context gpt-6-luna row - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-effort GPT-6 Luna model documentation. The model accepts reasoning effort none, the lowest documented effort, and lists the same standard text-token rates. - URL: https://developers.openai.com/api/docs/models/gpt-6-luna - Locator: Reasoning effort and text-token pricing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-export-org-20261026 Export your organization data. Team/Enterprise Primary Owners can export organization conversation/user data; deleted content is excluded and links expire in 24 hours. - URL: https://support.claude.com/en/articles/13346720-export-your-organization-s-data - Locator: Primary owner; scope; deleted items; link expiry; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 57af2f5ad8f732b35209851f2ba150423ac16e9d6a5c59718d6b0dd9ef672cae on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-export-user-20261026 Export your Claude data. Organization members can export their own chats when enabled, without uploaded-file contents; exports are web/Desktop only. - URL: https://support.claude.com/en/articles/9450526-export-your-claude-data - Locator: Team/Enterprise owner enablement; contents; 24-hour link; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 5fe1cfd761095719efd95b5bc63049b1ceed6ddc3ed081373247053022153bfc on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-compliance-20261026 Access the Compliance API. Enterprise Compliance API exposes events, chats and file content with primary-owner activation and scoped organization keys. - URL: https://support.claude.com/en/articles/13015708-access-the-compliance-api - Locator: Eligibility; primary-owner activation; event/chat/file data; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 f641744bc193c80154bdb21a45e3c0527566f256728552432047c12936b79225 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:export-pin LibreChat conversation export implementation. The pinned user conversation exporter supports JSON, CSV, Markdown and text, plus screenshot export. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/client/src/hooks/Conversations/useExportConversation.ts - Locator: client/src/hooks/Conversations/useExportConversation.ts, export dispatch - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: client/src/hooks/Conversations/useExportConversation.ts ### claude:claude:regional-presence-20261026 Anthropic European office announcement. The dated company announcement identifies an existing Zurich office and plans for Munich and Paris. It does not establish current staffing, a Swiss contracting entity or guaranteed local-language support. - URL: https://www.anthropic.com/news/new-offices-in-paris-and-munich-expand-european-presence - Locator: November 7, 2025 announcement, Zurich and planned Munich offices; HTTP 200, body SHA256 f73fca94192490d5216bd82ba233110af7093cfb2d08e3848eb79d3c055eea72 - Evidence kind: vendor-claimed - Source date: 2025-11-07 - Retrieved: 2026-10-26 ### claude:cl-status-20261026 Claude Status. Claude publishes separate hosted-product components and an incident history without providing a scoped contractual SLA in this page. - URL: https://status.claude.com/ - Locator: Component health; incident history; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 dabd165cf98d3b64e94051b42876be9d30ed1383af03d4c1a201674b97acb34e on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26