--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/librechat-vs-mistral-vibe/" data_url: "https://onaihq.com/compare/agents/librechat-vs-mistral-vibe/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" --- # LibreChat vs Mistral Vibe > 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. > Mistral Vibe lifecycle: sunset. The legacy hosted Chat tab and its Chat Agents are being removed progressively as accounts migrate to unified Vibe Work. Enterprise migration began October 1, 2026 with an approximately six-month administrator window; no fixed final end date was published in the inspected release. Scope: Legacy hosted Vibe Chat tab and Chat-created Agents only; not Vibe Work, Vibe Code, Mistral API or customer-deployed models. Continuation: Vibe Work continues with Skills; the rename preserves accounts, plans and conversations. Checked 2026-10-21; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-release-notes, mistral-vibe:mistral-vibe:m-legacy-agents, mistral-vibe:mistral-vibe:m-rename. This comparison has 40 criteria with sourced findings for both products, including 40 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. - LibreChat source checks: 2026-10-21 to 2026-10-26. - Mistral Vibe source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/librechat-vs-mistral-vibe/ - Machine-readable JSON: https://onaihq.com/compare/agents/librechat-vs-mistral-vibe/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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hosted Work exposes task-oriented Fast/Think behavior; a complete current per-plan named chat-model catalogue was not established. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Migrated Team and Enterprise hosted Work; no arbitrary named-model picker entitlement asserted; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - providers: Mistral powers core Vibe; images use Black Forest Labs and voice uses Voxtral. Named selectable core-chat models per plan were not established. - current_models: The API model list and pricing recommendations do not establish current models selectable in hosted Work/Chat for each plan. Search on 2026-10-26: https://mistral.ai/products/vibe/, https://docs.mistral.ai/vibe/work/image-generation.md, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - user_choice: The September 22 hosted release explicitly covers migrating Free, Pro, Teams and Enterprise accounts and documents Fast/Think choice in unified Work. These are reasoning modes, not arbitrary provider/model selection. - auto_routing: Work chooses tools automatically, but model-routing rules and display of the chosen model were not established. Search on 2026-10-26: https://mistral.ai/products/vibe/, https://docs.mistral.ai/vibe/work/image-generation.md, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - multimodal_input: Work accepts document/image and audio context; exact model-by-model capabilities were not established. - providers — Which model providers are available? [partial]: Mistral powers core Vibe; images use Black Forest Labs and voice uses Voxtral. Named selectable core-chat models per plan were not established. Sources: mistral-vibe:mistral-vibe:m-home-20261026, mistral-vibe:mistral-vibe:m-image-20261026. - current_models — Which current models are selectable on this plan? [unknown]: The API model list and pricing recommendations do not establish current models selectable in hosted Work/Chat for each plan. Search on 2026-10-26: https://mistral.ai/products/vibe/, https://docs.mistral.ai/vibe/work/image-generation.md, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - user_choice — Can users pick the model per chat? [partial]: The September 22 hosted release explicitly covers migrating Free, Pro, Teams and Enterprise accounts and documents Fast/Think choice in unified Work. These are reasoning modes, not arbitrary provider/model selection. Sources: mistral-vibe:mistral-vibe:m-release-notes-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [unknown]: Work chooses tools automatically, but model-routing rules and display of the chosen model were not established. Search on 2026-10-26: https://mistral.ai/products/vibe/, https://docs.mistral.ai/vibe/work/image-generation.md, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - multimodal_input — Which models accept images, audio or files? [partial]: Work accepts document/image and audio context; exact model-by-model capabilities were not established. Sources: mistral-vibe:mistral-vibe:m-files-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-home-20261026, mistral-vibe:mistral-vibe:m-image-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026, mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public product and model changelogs exist; Vibe model lag and version-pinning remain unverified. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: release_lag_days, deprecation_notice, version_pinning. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: Unknown. The API/model lifecycle pages cannot establish hosted Vibe chat release lag, notice guarantees or admin model pinning; no three-release app availability dataset was obtained. - changelog — Is there a dated public model changelog? [supported]: Mistral publishes dated model/API changes and separate shipped Vibe/Admin release notes. Sources: mistral-vibe:mistral-vibe:m-releases, mistral-vibe:mistral-vibe:m-release-notes. - deprecation_notice — How much notice is given before a model is removed? [unknown]: Unknown. The API/model lifecycle pages cannot establish hosted Vibe chat release lag, notice guarantees or admin model pinning; no three-release app availability dataset was obtained. - version_pinning — Can an admin keep an older model version? [unknown]: Unknown. The API/model lifecycle pages cannot establish hosted Vibe chat release lag, notice guarantees or admin model pinning; no three-release app availability dataset was obtained. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-releases, mistral-vibe:mistral-vibe:m-release-notes ### 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. #### 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 #### Mistral Vibe 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. ### 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. #### 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 #### Mistral Vibe 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. ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Vibe publishes relative plan allowances and some fixed limits; per-group model policies remain open. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: model_allowlist_by_group, data_bound_models, default_model. - model_allowlist_by_group — Can admins limit models per group? [unknown]: Unknown. Admin Workspace/tool controls were checked, but an enforced group-to-model allowlist, data-to-model rule or admin default chat model was not established. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: Unknown. Admin Workspace/tool controls were checked, but an enforced group-to-model allowlist, data-to-model rule or admin default chat model was not established. - default_model — Can admins set the default model? [unknown]: Unknown. Admin Workspace/tool controls were checked, but an enforced group-to-model allowlist, data-to-model rule or admin default chat model was not established. - user_limits — What per-user message or token limits apply, and are they published? [partial]: The page gives relative multipliers and Team Flash Answers at 200/day versus Pro 150/day. An exhaustive exact Work limit table was not established. Sources: mistral-vibe:mistral-vibe:m-pricing. - limit_behaviour — What happens when a limit is reached? [partial]: Library processing exhaustion pauses new uploads while existing content stays usable; paid API/Code usage can stop or consume prepaid PAYG. Sources: mistral-vibe:mistral-vibe:m-libraries, mistral-vibe:mistral-vibe:m-subscription. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-libraries, mistral-vibe:mistral-vibe:m-subscription ## 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Work accepts documents, tables, images and recordings; documentation does not replace a file-fidelity test. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: limits, full_vs_chunked. - formats — Which formats are accepted? [supported]: PDF, Word, PowerPoint, Excel/CSV/ODS/Numbers, common images/text/code and email formats are listed. Sources: mistral-vibe:mistral-vibe:m-files. - limits — What size and count limits apply per file and chat? [unknown]: Unknown. The 100 MB/100-file limits are for Libraries; exact per-chat file byte/count limits were not established and were not copied across. - ocr — Are scanned PDFs read? [partial]: Work describes extracting text from scanned-page images; complete multi-page scanned-PDF fidelity was not tested. Sources: mistral-vibe:mistral-vibe:m-files. - spreadsheets — Are Excel tables read with structure intact? [partial]: Excel/CSV analysis and paid spreadsheet editing are documented; formulas/structure were not tested against the shared workbook. Sources: mistral-vibe:mistral-vibe:m-files, mistral-vibe:mistral-vibe:m-sheets. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [unknown]: Unknown. Files persist for the chat and Libraries are indexed, but exact full-file versus chunk selection and user-visible coverage were not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-files, mistral-vibe:mistral-vibe:m-sheets ### 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. #### 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 #### Mistral Vibe 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. ### 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). #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Named featured connectors and a third-party MCP directory connect external data and actions; current pricing labels connectors beta. Availability: beta Delivery: official-integration Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team and Enterprise hosted Vibe Work after account migration; feature-specific beta/preview and Enterprise-only controls retained below; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - microsoft_365: Featured sources list Outlook, Outlook Calendar and SharePoint Search API. Separate OneDrive/Teams connector entitlements were not verified. - google_workspace: The guide names Gmail, Google Calendar and Google Drive in Work context; exact Google Drive setup scope was not fully verified. - on_prem_sources: Custom MCP can point at reachable tools, but a supported on-prem file-share/database connector with verified network prerequisites was not established. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/connectors.md, https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/vibe/work/connectors/mcp-connectors.md. No additional scoped evidence established this answer. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: Featured sources list Outlook, Outlook Calendar and SharePoint Search API. Separate OneDrive/Teams connector entitlements were not verified. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026. - google_workspace — Which Google sources are connected? [partial]: The guide names Gmail, Google Calendar and Google Drive in Work context; exact Google Drive setup scope was not fully verified. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-files-20261026. - atlassian — Confluence and Jira? [supported]: The featured Atlassian connector supports Confluence and Jira. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026. - other_systems — Which other business systems? [supported]: Featured examples include Box, GitHub, Linear, Notion, Slack and Stripe; the remaining MCP directory is third-party. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026. - on_prem_sources — Can on-prem file shares or databases be connected? [unknown]: Custom MCP can point at reachable tools, but a supported on-prem file-share/database connector with verified network prerequisites was not established. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/connectors.md, https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/vibe/work/connectors/mcp-connectors.md. No additional scoped evidence established this answer. - connector_provider — Who builds and maintains each connector? [supported]: Featured integrations are Mistral-managed; custom/directory MCP servers are third-party/customer-operated and need admin setup. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe 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. ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Request-time featured connectors and indexed Knowledge Connectors are distinct; source deletions propagate after synchronization with no published interval. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team and Enterprise hosted Vibe Work after account migration; feature-specific beta/preview and Enterprise-only controls retained below; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - sync_interval: No universal source-sync interval was established; live connectors and manually indexed Libraries must be distinguished. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/connectors.md, https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. - deletion_propagation: The connected-tool help article says source file/folder/library deletion propagates to the Knowledge Connector index after synchronization. Disabling a Knowledge Connector removes access and schedules index deletion. No bounded propagation or purge time is stated. - index_location: Libraries state European cloud storage; exact country, backup and embedding-processing regions were not established. - live_or_indexed — Is content searched live or copied into an index? [supported]: Featured request-time connectors fetch live without a persistent connector index. Knowledge Connectors can separately index selected files, folders or libraries; uploaded Libraries persist their own content. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:connector-data-controls-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. - sync_interval — How often does an index refresh? [unknown]: No universal source-sync interval was established; live connectors and manually indexed Libraries must be distinguished. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/connectors.md, https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. - deletion_propagation — How quickly does a deleted document disappear? [partial]: The connected-tool help article says source file/folder/library deletion propagates to the Knowledge Connector index after synchronization. Disabling a Knowledge Connector removes access and schedules index deletion. No bounded propagation or purge time is stated. Sources: mistral-vibe:mistral-vibe:connector-data-controls-20261026. - index_location — Where is indexed content stored? [partial]: Libraries state European cloud storage; exact country, backup and embedding-processing regions were not established. Sources: mistral-vibe:mistral-vibe:m-libraries-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:connector-data-controls-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Library answers document numbered footnotes; measured multilingual grounding quality remains unknown. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team and Enterprise hosted Vibe Work after account migration; feature-specific beta/preview and Enterprise-only controls retained below; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - citation_accuracy: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - cross_language: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - no_answer_behaviour: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - observed_accuracy: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - citations — Are answers linked to specific sources? [supported]: Library responses use numbered footnotes to source passages and a Sources panel. Sources: mistral-vibe:mistral-vibe:m-libraries-20261026. - citation_accuracy — Do the cited passages support the answer? [unknown]: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - cross_language — Does a question in one language find documents in another? [unknown]: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. - observed_accuracy — How many of the question set were answered correctly? [unknown]: No shared DE/FR/EN corpus or question-set trial was run, so this quality outcome cannot be inferred from feature documentation. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/libraries.md, https://mistral.ai/pricing/, https://docs.mistral.ai/vibe/work/connectors.md. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: supported Migrated Work uses personal Knowledge Base and persistent instructions, with user and admin controls. Availability: beta Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Migrated Team/Enterprise hosted Work; personal Knowledge Base public preview, organization/workspace controls as documented; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Persistent account instructions specify role, tone and format; Projects can carry their own instructions. Sources: mistral-vibe:mistral-vibe:m-instructions-20261026, mistral-vibe:mistral-vibe:m-projects-20261026. - cross_chat_memory — Does the product remember facts across chats? [supported]: Work Knowledge Base retrieves saved knowledge across tasks; it replaces legacy Memories as accounts migrate. Sources: mistral-vibe:mistral-vibe:m-memory-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users can browse/edit/delete/export knowledge and disable its use; disabling does not erase saved entries. Sources: mistral-vibe:mistral-vibe:m-memory-20261026. - admin_memory_controls — Can admins turn memory off? [supported]: Admins can disable Knowledge and constrain sensitive-data saving at organization/Workspace scope. Sources: mistral-vibe:mistral-vibe:m-memory-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-instructions-20261026, mistral-vibe:mistral-vibe:m-projects-20261026, mistral-vibe:mistral-vibe:m-memory-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ## 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Skills are the current reusable Work configuration; legacy Chat Agents remain migration-scoped. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration, Legacy Vibe Chat during enterprise migration; version=not specified; plan=Team/Enterprise Work Skills; legacy Chat Agents only during migration; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - creator_permissions: Admins govern Skills/features and may force-enable Workspace Skills; a separate per-user creator-role restriction was not fully verified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: Work users create reusable Skills with instructions/resources. Legacy Chat Agents additionally bind instructions, tools and Libraries during migration. Sources: mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:m-legacy-agents-20261026. - creator_permissions — Can admins limit who creates them? [partial]: Admins govern Skills/features and may force-enable Workspace Skills; a separate per-user creator-role restriction was not fully verified. Sources: mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Skills can be personal or published to a Workspace; legacy Agents have individual/group/organization sharing. Sources: mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:m-legacy-agents-20261026. - catalogue — Is there an internal assistant directory? [supported]: The Skills interface distinguishes built-in, personal and Workspace Skills; Studio-published resources can appear in Work. Sources: mistral-vibe:mistral-vibe:m-skills-20261026. - prompt_library — Are shared prompt templates available? [supported]: Built-in Skills include research, extraction and onboarding, and custom Skills can encode reusable methods/templates. Sources: mistral-vibe:mistral-vibe:m-skills-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:m-legacy-agents-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: supported Work provides native tools, custom remote MCP and explicit action controls. Availability: beta Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise hosted Work; connectors/custom MCP beta; Studio workflow execution separately metered; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. - builtin_tools — Which tools are built in? [supported]: Tools include web/Open URL, Libraries, paid Code Interpreter, Canvas, image generation, Skills and connectors. Sources: mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:m-web-20261026, mistral-vibe:mistral-vibe:m-interpreter-20261026. - custom_actions — Can admins add API actions? [supported]: Admins can add customer MCP tools; Studio developers can publish deterministic Workflows as callable assistants. Sources: mistral-vibe:mistral-vibe:m-mcp-20261026, mistral-vibe:mistral-vibe:m-workflows-20261026. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Custom HTTPS MCP servers support auto-detected no-auth, Bearer/Basic or OAuth 2.1 authentication and require administrator setup. Sources: mistral-vibe:mistral-vibe:m-mcp-20261026. - tool_auth — Do tools act as the user or as a shared account? [supported]: Featured tools use personal OAuth, with separate organization-level GitHub/Slack bot routes and MCP credentials. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-admincon-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [supported]: Writes pause for Continue, Always allow or Decline; users can preauthorize a function, while admins can block/restrict tools. Sources: mistral-vibe:mistral-vibe:m-safety-20261026, mistral-vibe:mistral-vibe:m-admincon-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:m-web-20261026, mistral-vibe:mistral-vibe:m-interpreter-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026, mistral-vibe:mistral-vibe:m-workflows-20261026, mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-admincon-20261026, mistral-vibe:mistral-vibe:m-safety-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Live web search and a Deep Research Skill produce linked sources; exact search processing regions remain unspecified. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Migrated Team/Enterprise Work web search and Deep Research Skill; limits by plan; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - search_provider: AFP/AP supply news results. The general web-search backend and its query-processing region were not established. - deep_research: Deep Research is available as a Work Skill producing multi-source cited reports; exact plan limits need the pricing/account scope. - web_search — Is web search available? [supported]: Web search and Open URL retrieve current public information; login/paywalled pages have documented limitations. Sources: mistral-vibe:mistral-vibe:m-web-20261026. - admin_toggle — Can admins disable it per organisation or group? [supported]: Admins can disable Web Search and Deep Research per Workspace; group access can be assigned through Workspace membership. Sources: mistral-vibe:mistral-vibe:m-adminvibe-20261026, mistral-vibe:mistral-vibe:m-groups-20261026. - search_provider — Which search provider handles queries, and where? [partial]: AFP/AP supply news results. The general web-search backend and its query-processing region were not established. Sources: mistral-vibe:mistral-vibe:m-web-20261026. - deep_research — Is multi-step research with a report available? [partial]: Deep Research is available as a Work Skill producing multi-source cited reports; exact plan limits need the pricing/account scope. Sources: mistral-vibe:mistral-vibe:m-web-20261026, mistral-vibe:mistral-vibe:m-skills-20261026. - web_citations — Are web sources cited? [supported]: Web responses provide inline references and a Sources panel. Sources: mistral-vibe:mistral-vibe:m-web-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-web-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026, mistral-vibe:mistral-vibe:m-groups-20261026, mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Studio developers publish Workflows for Work use, with tier entitlement unspecified; time-based Work scheduling is public preview. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise Work scheduling and workflow selection; Studio construction/hosting needs its own paid API or Enterprise entitlement; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Time-based scheduling remains public preview. Studio workflow creation/hosting needs a separately eligible service plan; current scheduling is not event-triggered. - workflow_builder — Is there a workflow or chain builder? [supported]: Work does not build deterministic Workflows itself; Studio developers build and publish them for explicit selection in Work. Sources: mistral-vibe:mistral-vibe:m-workflows-20261026. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Public-preview schedules run once/daily/weekly/monthly/yearly; Free advertises up to five and paid plans fair-use conditions. Sources: mistral-vibe:mistral-vibe:m-schedule-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. - event_triggers — Can external events start a workflow? [unsupported]: The scheduling guide states triggers are time-based for now; event triggers are prospective, without a dated commitment. Sources: mistral-vibe:mistral-vibe:m-schedule-20261026. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Studio workflow construction targets developers; ordinary Work users select published workflows and schedule prompts. Sources: mistral-vibe:mistral-vibe:m-workflows-20261026, mistral-vibe:mistral-vibe:m-schedule-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-workflows-20261026, mistral-vibe:mistral-vibe:m-schedule-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Work is documented as a supervised multi-step agent with task progress and optional preauthorization. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise migrated Work agent execution and plan-included connectors; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - agent_mode: Work decomposes tasks and calls connectors/tools; no fixture execution or intervention count was observed. - agent_mode — Is there an agent mode for multi-step tasks? [partial]: Work decomposes tasks and calls connectors/tools; no fixture execution or intervention count was observed. Sources: mistral-vibe:mistral-vibe:m-safety-20261026. - visible_steps — Are steps and tool calls shown? [supported]: Longer tasks show todos, reasoning summaries and expandable tool inputs/outputs/status. Sources: mistral-vibe:mistral-vibe:m-safety-20261026. - side_effect_confirmation — Must the user confirm actions with side effects? [supported]: External create/update/send/delete actions request approval unless the user has Always allow enabled for that function. Sources: mistral-vibe:mistral-vibe:m-safety-20261026. - stop_control — Can the user stop a running task? [supported]: A stop button can interrupt work, but the guide warns that already-submitted external effects cannot be guaranteed stopped or undone. Sources: mistral-vibe:mistral-vibe:m-safety-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-safety-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Studio/administration APIs are separate from the end-user Work chat; legacy Chat Agents explicitly lack API invocation. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: knowledge_api, mcp_server. - chat_api — Is there an API for chat and assistants? [partial]: Legacy Chat-created Agents cannot be called programmatically; developers create separate Studio/API agents. A full hosted Work conversation API was not established. Sources: mistral-vibe:mistral-vibe:m-legacy-agents. - knowledge_api — Can documents be loaded through an API? [unknown]: Unknown. Studio/library APIs were not comprehensively retrieved to establish full Work knowledge ingestion/ACL parity. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Enterprise Admin APIs expose usage, groups and limits; parity with every Work tool/retention/permission policy was not tested. Sources: mistral-vibe:mistral-vibe:m-usage-api, mistral-vibe:mistral-vibe:m-provision. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: Unknown. Work is documented as an MCP client; a supported Work-as-MCP-server interface was not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-legacy-agents, mistral-vibe:mistral-vibe:m-usage-api, mistral-vibe:mistral-vibe:m-provision ## 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hosted Vibe is available on web and mobile; developer IDE/CLI routes have a different audience. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration, Vibe iOS/Android apps; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: desktop_apps, browser_extension, managed_deployment, client_feature_gaps. - web — Is a full web client available? [supported]: The product and pricing pages list the hosted web app. Sources: mistral-vibe:mistral-vibe:m-home, mistral-vibe:mistral-vibe:m-pricing. - desktop_apps — Windows and macOS apps? [unknown]: Unknown. No standalone general-work Windows/macOS app was verified; CLI/IDE coding clients are recorded separately. - mobile_apps — iOS and Android apps with SSO? [partial]: iOS and Android apps are linked in the voice guide; company-SSO mobile behavior was not verified. Sources: mistral-vibe:mistral-vibe:m-voice. - browser_extension — Is there a browser extension or sidebar? [unknown]: Unknown. Vibe Code IDE extensions are documented, but a general browser extension/sidebar was not established. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: Unknown. No MDM/Intune package and managed configuration contract was retrieved. - client_feature_gaps — Which features are missing on mobile? [unknown]: Unknown. No complete mobile/web parity matrix or mobile Enterprise SSO fixture was obtained. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-home, mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-voice ### 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. #### 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. #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Work accesses Outlook and Google services through connectors; embedded Office, Outlook or Teams add-ins remain unverified. Availability: unknown Delivery: unknown Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise hosted Work with beta connectors; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Source-account and connector route dependent; os=not specified. Limitations: - word_excel_powerpoint: The Work connector guide describes source retrieval/actions. It does not establish this editor/mail/Teams add-in or its separate licence/admin-consent requirements. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/vibe/work/voice-mode.md, https://mistral.ai/products/vibe/. No additional scoped evidence established this answer. - outlook: The featured Outlook connector reads/sends email and the Outlook Calendar connector manages events from Work. This does not establish an embedded Outlook add-in. - teams: The Work connector guide describes source retrieval/actions. It does not establish this editor/mail/Teams add-in or its separate licence/admin-consent requirements. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/vibe/work/voice-mode.md, https://mistral.ai/products/vibe/. No additional scoped evidence established this answer. - google_workspace_apps: Featured Gmail and Google Calendar tools act from Work. A Google Drive task example is documented; embedded Gmail/Docs/Sheets add-ons were not established. - licence_prerequisites: Featured connectors require an authorized source account and OAuth consent; custom remote MCP configuration requires an administrator. The complete source licence and tenant-admin consent matrix was not established. - word_excel_powerpoint — Does it work inside Word, Excel and PowerPoint? [unknown]: The Work connector guide describes source retrieval/actions. It does not establish this editor/mail/Teams add-in or its separate licence/admin-consent requirements. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/vibe/work/voice-mode.md, https://mistral.ai/products/vibe/. No additional scoped evidence established this answer. - outlook — Does it work inside Outlook? [partial]: The featured Outlook connector reads/sends email and the Outlook Calendar connector manages events from Work. This does not establish an embedded Outlook add-in. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. - teams — Is there a Teams app or bot? [unknown]: The Work connector guide describes source retrieval/actions. It does not establish this editor/mail/Teams add-in or its separate licence/admin-consent requirements. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/vibe/work/voice-mode.md, https://mistral.ai/products/vibe/. No additional scoped evidence established this answer. - google_workspace_apps — Does it work inside Docs, Sheets or Gmail? [partial]: Featured Gmail and Google Calendar tools act from Work. A Google Drive task example is documented; embedded Gmail/Docs/Sheets add-ons were not established. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. - licence_prerequisites — Which licences or consents are needed? [partial]: Featured connectors require an authorized source account and OAuth consent; custom remote MCP configuration requires an administrator. The complete source licence and tenant-admin consent matrix was not established. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-connectors-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:m-mcp-20261026 ### 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. #### 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. #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Canvas supports instructed translation and rewriting; dedicated layout-preserving translation/glossary behavior remains untested. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: document_translation, translation_engine, glossaries, formality_and_variants. - document_translation — Can whole documents be translated with formatting kept? [unknown]: Unknown. Canvas and legacy translation examples do not establish a dedicated translation engine, enforced glossary or tested format/de-CH fidelity; no contract translation fixture was run. - translation_engine — Which engine translates? [unknown]: Unknown. Canvas and legacy translation examples do not establish a dedicated translation engine, enforced glossary or tested format/de-CH fidelity; no contract translation fixture was run. - glossaries — Are company glossaries supported? [unknown]: Unknown. Canvas and legacy translation examples do not establish a dedicated translation engine, enforced glossary or tested format/de-CH fidelity; no contract translation fixture was run. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: Unknown. Canvas and legacy translation examples do not establish a dedicated translation engine, enforced glossary or tested format/de-CH fidelity; no contract translation fixture was run. - writing_tools — Are dedicated rewrite and proofreading tools available? [supported]: Canvas offers inline rewrite/translate requests, direct edits and revisions; custom instructions set tone/style. Sources: mistral-vibe:mistral-vibe:m-files, mistral-vibe:mistral-vibe:m-instructions. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-files, mistral-vibe:mistral-vibe:m-instructions ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Work generates and edits images using Black Forest Labs, with Workspace controls and plan limits. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team and Enterprise hosted Vibe Work after account migration; feature-specific beta/preview and Enterprise-only controls retained below; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - image_generation: The Work guide names Black Forest Labs as image provider; the exact current model revision was not established. - usage_terms: Commercial terms define generated-output rights subject to third-party content and usage restrictions; a model-specific image licence review was not completed. - image_generation — Can users generate images, with which models? [partial]: The Work guide names Black Forest Labs as image provider; the exact current model revision was not established. Sources: mistral-vibe:mistral-vibe:m-image-20261026. - image_editing — Can users edit uploaded images? [supported]: Users can refine generated images or upload an existing image and request changes. Sources: mistral-vibe:mistral-vibe:m-image-20261026. - admin_control — Can admins restrict image generation? [supported]: Administrators can disable Image Generation per Workspace. Sources: mistral-vibe:mistral-vibe:m-adminvibe-20261026. - usage_terms — What usage rights apply to output? [partial]: Commercial terms define generated-output rights subject to third-party content and usage restrictions; a model-specific image licence review was not completed. Sources: mistral-vibe:mistral-vibe:m-commercial-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-image-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026, mistral-vibe:mistral-vibe:m-commercial-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Voice transcription and uploaded meeting analysis are documented; live voice and Swiss German performance remain open. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration, Vibe iOS/Android apps; version=not specified; plan=All plans for dictation, explicitly stated by the Work voice guide; uploaded-meeting analysis unspecified plan; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: read_aloud, voice_conversation, swiss_german_speech. - The general Work/Workspace documentation does not establish Team or Enterprise entitlement for every feature here. Unspecified-plan findings remain candidates; no plan inheritance is assumed. - dictation — Can users dictate prompts? [supported]: Web and iOS/Android voice transcribes a prompt for review or autosend; DE/FR/IT are listed languages. Sources: mistral-vibe:mistral-vibe:m-voice, mistral-vibe:mistral-vibe:m-voice-entitlement-correction. - read_aloud — Can answers be read aloud? [unknown]: Unknown. A supported end-user answer read-aloud control was not established in the retrieved Work voice guide. - voice_conversation — Is a live voice mode available? [unknown]: Unknown. The voice guide has a conversation-mode heading but does not provide sufficient behavior/plan detail to establish live bidirectional voice. - meeting_summaries — Are meetings transcribed and summarised? [partial]: Uploaded recordings can be transcribed and summarized with action items; a live meeting-bot integration was not established. Sources: mistral-vibe:mistral-vibe:m-files. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Unknown. No de-CH/Swiss German transcription evidence or fixture was obtained. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-voice, mistral-vibe:mistral-vibe:m-files, mistral-vibe:mistral-vibe:m-voice-entitlement-correction ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paid Work executes code, charts data and generates editable spreadsheet/slide artifacts. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Hosted paid-plan documentation does not establish equivalent behavior in every private Enterprise deployment. - data_analysis — Can it analyse spreadsheets with executed code? [partial]: Code Interpreter executes Python/TypeScript in an isolated no-internet sandbox; workbook accuracy was not tested. Sources: mistral-vibe:mistral-vibe:m-interpreter. - charts — Can it produce charts? [supported]: The interpreter supports matplotlib/TypeScript charts from user data. Sources: mistral-vibe:mistral-vibe:m-interpreter. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: Paid spreadsheets export XLSX and Canvas exports PowerPoint and tables; DOCX generation was not fully verified. Sources: mistral-vibe:mistral-vibe:m-sheets, mistral-vibe:mistral-vibe:m-files. - canvas_editing — Is there a document or canvas editor for iterating on output? [supported]: Canvas supports direct edits, inline AI requests, version navigation and file exports. Sources: mistral-vibe:mistral-vibe:m-files. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-interpreter, mistral-vibe:mistral-vibe:m-sheets, mistral-vibe:mistral-vibe:m-files ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspaces and Projects scope context; share links are output snapshots, with recipient source-access behavior still untested. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team and Enterprise hosted Vibe Work after account migration; feature-specific beta/preview and Enterprise-only controls retained below; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - team_spaces: Workspaces scope conversations/resources and access; Projects group task context. Collaborative project membership was not fully established. - group_chat: No simultaneous multi-person chat-with-AI workflow was established. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/admin/workspaces/your-first-workspace.md, https://docs.mistral.ai/vibe/work/projects.md. No additional scoped evidence established this answer. - share_permission_boundary: No two-recipient sharing fixture established whether a shared output reveals content the recipient lacks in source systems. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/admin/workspaces/your-first-workspace.md, https://docs.mistral.ai/vibe/work/projects.md. No additional scoped evidence established this answer. - share_chats — Can chats be shared inside the organisation? [supported]: Canvas documentation describes sharing the full chat including Canvas content. Sources: mistral-vibe:mistral-vibe:m-files-20261026. - team_spaces — Are shared projects or workspaces available? [partial]: Workspaces scope conversations/resources and access; Projects group task context. Collaborative project membership was not fully established. Sources: mistral-vibe:mistral-vibe:m-workspace-20261026, mistral-vibe:mistral-vibe:m-projects-20261026. - group_chat — Can several people chat together with the AI? [unknown]: No simultaneous multi-person chat-with-AI workflow was established. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/admin/workspaces/your-first-workspace.md, https://docs.mistral.ai/vibe/work/projects.md. No additional scoped evidence established this answer. - share_permission_boundary — Does sharing respect the recipient's access to sources? [unknown]: No two-recipient sharing fixture established whether a shared output reveals content the recipient lacks in source systems. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/files-and-canvas.md, https://docs.mistral.ai/admin/workspaces/your-first-workspace.md, https://docs.mistral.ai/vibe/work/projects.md. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:m-workspace-20261026, mistral-vibe:mistral-vibe:m-projects-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe 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. ## 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise organization SSO is SAML 2.0 with verified domains and first-login provisioning. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - mfa: Individual accounts can enable TOTP two-factor authentication and generate recovery codes. A mandatory organization-wide policy or IdP enforcement matrix was not established. - conditional_access: No Entra conditional-access compatibility test or precise policy guarantee was retrieved. Search on 2026-10-26: https://docs.mistral.ai/admin/set-up-organization/sign-in-method/saml-sso.md, https://mistral.ai/pricing/, https://docs.mistral.ai/admin/workspaces/workspaces-in-vibe.md. No additional scoped evidence established this answer. - sso_protocols — Which SSO protocols and identity providers work? [supported]: Enterprise organization SSO supports SAML 2.0 identity providers; the guide explicitly says OIDC is not supported for organization SSO. Sources: mistral-vibe:mistral-vibe:m-sso-20261026. - sso_plan — Which plan includes SSO? [supported]: SAML SSO requires Enterprise; domain verification is listed on Team. Sources: mistral-vibe:mistral-vibe:m-sso-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026. - mfa — Can MFA be enforced? [partial]: Individual accounts can enable TOTP two-factor authentication and generate recovery codes. A mandatory organization-wide policy or IdP enforcement matrix was not established. Sources: mistral-vibe:mistral-vibe:account-mfa-20261026. - conditional_access — Do Entra conditional-access policies apply? [unknown]: No Entra conditional-access compatibility test or precise policy guarantee was retrieved. Search on 2026-10-26: https://docs.mistral.ai/admin/set-up-organization/sign-in-method/saml-sso.md, https://mistral.ai/pricing/, https://docs.mistral.ai/admin/workspaces/workspaces-in-vibe.md. No additional scoped evidence established this answer. - domain_capture — Can the company claim its email domain? [supported]: A matching verified-domain email routes to the configured IdP, with first-sign-in organization provisioning. Sources: mistral-vibe:mistral-vibe:m-sso-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-sso-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:account-mfa-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial JIT seats, user/group administration and external identity sync are documented; leaver data outcomes remain untested. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - The partial atomic answers state their documentation or verification limits. - scim — Is SCIM provisioning supported? [partial]: The groups guide recognizes SCIM-managed identities/groups, but a complete supported SCIM setup/plan matrix was not retrieved. Sources: mistral-vibe:mistral-vibe:m-groups. - group_sync — Are identity-provider groups synced? [partial]: Externally managed group fields are controlled by the IdP and updated on sync; delay was not verified. Sources: mistral-vibe:mistral-vibe:m-groups. - jit_provisioning — Are users created at first login? [supported]: Enterprise SAML first login provisions users and can assign available product seats automatically. Sources: mistral-vibe:mistral-vibe:m-sso. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: User removal revokes organization/Workspace permissions. Content ownership transfer and deletion were not tested. Sources: mistral-vibe:mistral-vibe:m-users, mistral-vibe:mistral-vibe:m-provision. - seat_assignment — Can admins assign and reclaim seats? [supported]: Admins assign/reclaim Vibe/product seats in member subscription settings. Sources: mistral-vibe:mistral-vibe:m-users. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-groups, mistral-vibe:mistral-vibe:m-sso, mistral-vibe:mistral-vibe:m-users, mistral-vibe:mistral-vibe:m-provision ### 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. #### 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 #### Mistral Vibe 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. ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise usage APIs expose user/agent activity and billing metrics; anonymized reporting controls remain unknown. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Enterprise Admin API activity export; Team/Enterprise Workspace UI as documented; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - adoption_dashboard: The Admin API documents product activity including user message/file/image counts and last activity; end-user UI completeness was not verified. - breakdowns: Documented API breakdowns include user/agent activity and Workspace model/token/capability consumption; a complete group/feature matrix was not established. - privacy_modes: A user-report pseudonymization, aggregation-only or works-council privacy mode was not established. Search on 2026-10-26: https://docs.mistral.ai/admin/admin-api/usage-metrics.md, https://docs.mistral.ai/admin/workspaces/usage-limits.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. - adoption_dashboard — Is there an adoption dashboard? [partial]: The Admin API documents product activity including user message/file/image counts and last activity; end-user UI completeness was not verified. Sources: mistral-vibe:mistral-vibe:m-usage-api-20261026. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Documented API breakdowns include user/agent activity and Workspace model/token/capability consumption; a complete group/feature matrix was not established. Sources: mistral-vibe:mistral-vibe:m-usage-api-20261026, mistral-vibe:mistral-vibe:m-limits-20261026. - export — Can usage data be exported? [supported]: Enterprise usage endpoints return machine-readable metrics with an Admin API key; access requires separately enabled Enterprise administration. Sources: mistral-vibe:mistral-vibe:m-usage-api-20261026. - privacy_modes — Can per-person reporting be limited or pseudonymised? [unknown]: A user-report pseudonymization, aggregation-only or works-council privacy mode was not established. Search on 2026-10-26: https://docs.mistral.ai/admin/admin-api/usage-metrics.md, https://docs.mistral.ai/admin/workspaces/usage-limits.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-usage-api-20261026, mistral-vibe:mistral-vibe:m-limits-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspace and organization spending caps are documented, with explicit API suspension behavior and incomplete Vibe UI enforcement detail. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise Workspace usage and limits; API cap behavior does not establish a Work-chat hard stop; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - cost_visibility: Workspace usage shows month-to-date spend, token/model and capability usage; per-person complete cost allocation was not established. - budget_enforcement: Unknown for hosted Vibe Work. The guide specifies API suspension at the cap, which does not establish Work chat enforcement; no Work budget-stop fixture was run. Search on 2026-10-26: https://docs.mistral.ai/admin/workspaces/usage-limits.md, https://docs.mistral.ai/admin/billing-usage/billing.md, https://docs.mistral.ai/admin/admin-api/usage-metrics.md. No additional scoped evidence established this answer. - chargeback: Enterprise usage APIs provide billing/Workspace data for allocation; a native cost-centre export schema was not established. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Workspace usage shows month-to-date spend, token/model and capability usage; per-person complete cost allocation was not established. Sources: mistral-vibe:mistral-vibe:m-limits-20261026. - budgets — Can budgets be set per user or group? [supported]: Admins can set Workspace monthly spending limits bounded by the organization cap; defaults have no Workspace cap. Sources: mistral-vibe:mistral-vibe:m-limits-20261026, mistral-vibe:mistral-vibe:m-billing-20261026. - budget_enforcement — Does reaching a budget alert, block or downgrade? [unknown]: Unknown for hosted Vibe Work. The guide specifies API suspension at the cap, which does not establish Work chat enforcement; no Work budget-stop fixture was run. Search on 2026-10-26: https://docs.mistral.ai/admin/workspaces/usage-limits.md, https://docs.mistral.ai/admin/billing-usage/billing.md, https://docs.mistral.ai/admin/admin-api/usage-metrics.md. No additional scoped evidence established this answer. - chargeback — Can costs be exported per cost centre? [partial]: Enterprise usage APIs provide billing/Workspace data for allocation; a native cost-centre export schema was not established. Sources: mistral-vibe:mistral-vibe:m-usage-api-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-limits-20261026, mistral-vibe:mistral-vibe:m-billing-20261026, mistral-vibe:mistral-vibe:m-usage-api-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise event logs have a defined event taxonomy but no verified retention/integrity model; the overview explicitly excludes export. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: content_logging, ediscovery, log_retention. - admin_events — Are admin and security events logged? [supported]: Enterprise automatically records authentication, user/role changes, API-key and organization/Workspace events plus conversation lifecycle events. Sources: mistral-vibe:mistral-vibe:m-audit, mistral-vibe:mistral-vibe:m-audit-ref. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [unknown]: Unknown. Conversation tracing exists, but exact prompt/response compliance capture and integrity configuration were not verified. - siem_export — Can logs stream to a SIEM or be exported? [unsupported]: The audit overview explicitly says log export is not supported; no SIEM streaming route was verified. Sources: mistral-vibe:mistral-vibe:m-audit. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: Unknown. A legal-hold/eDiscovery feature was not established. - log_retention — How long are logs kept? [unknown]: Unknown. The public event guide/reference does not establish a current retention duration and tamper-resistance model. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-audit, mistral-vibe:mistral-vibe:m-audit-ref ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Knowledge Base has sensitive-memory controls; general pre-model PII/DLP redaction remains unverified. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Migrated Team/Enterprise Knowledge Base public preview; sensitive-memory policy only; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - pii_detection: Knowledge Base documents exclusions for government IDs, banking details and credentials; this is memory storage policy rather than tested prompt/file PII screening. - pii_action: Admins can prevent sensitive knowledge saving; whole-prompt redaction/masking/blocking before model inference was not established. - custom_patterns: No Work-specific source or AHV/IBAN fixture established this custom pattern, external DLP integration or filter execution location; generic Studio moderation was not carried over. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/knowledge.md, https://mistral.ai/pricing/, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - dlp_integration: No Work-specific source or AHV/IBAN fixture established this custom pattern, external DLP integration or filter execution location; generic Studio moderation was not carried over. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/knowledge.md, https://mistral.ai/pricing/, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - filter_location: No Work-specific source or AHV/IBAN fixture established this custom pattern, external DLP integration or filter execution location; generic Studio moderation was not carried over. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/knowledge.md, https://mistral.ai/pricing/, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - pii_detection — Is personal data detected in prompts and files? [partial]: Knowledge Base documents exclusions for government IDs, banking details and credentials; this is memory storage policy rather than tested prompt/file PII screening. Sources: mistral-vibe:mistral-vibe:m-memory-20261026. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: Admins can prevent sensitive knowledge saving; whole-prompt redaction/masking/blocking before model inference was not established. Sources: mistral-vibe:mistral-vibe:m-memory-20261026. - custom_patterns — Can admins add custom patterns or terms? [unknown]: No Work-specific source or AHV/IBAN fixture established this custom pattern, external DLP integration or filter execution location; generic Studio moderation was not carried over. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/knowledge.md, https://mistral.ai/pricing/, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: No Work-specific source or AHV/IBAN fixture established this custom pattern, external DLP integration or filter execution location; generic Studio moderation was not carried over. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/knowledge.md, https://mistral.ai/pricing/, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. - filter_location — Where does filtering run? [unknown]: No Work-specific source or AHV/IBAN fixture established this custom pattern, external DLP integration or filter execution location; generic Studio moderation was not carried over. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/knowledge.md, https://mistral.ai/pricing/, https://docs.mistral.ai/resources/release-notes.md. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-memory-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026, mistral-vibe:mistral-vibe:m-release-notes-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admins can force-enable Skills and disable tools; global policy acknowledgements and enforced topical controls need verification. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise Work Skills and Workspace settings; no global policy-acceptance entitlement established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - org_instructions: Admins may force-enable Workspace Skills with reusable instructions. Model compliance with instructions is not an independently enforced boundary. - usage_notice: No mandatory company acceptable-use acknowledgement flow was established. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://docs.mistral.ai/vibe/work/image-generation.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. - content_filters: Images may be safety-filtered, but an administrator-configurable organization-wide content-filter matrix was not established. - violation_reporting: No central policy-hit reporting feature was established from audit/tracing docs. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://docs.mistral.ai/vibe/work/image-generation.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. - org_instructions — Can admins set organisation-wide instructions? [partial]: Admins may force-enable Workspace Skills with reusable instructions. Model compliance with instructions is not an independently enforced boundary. Sources: mistral-vibe:mistral-vibe:m-skills-20261026. - usage_notice — Can users be required to accept a usage policy? [unknown]: No mandatory company acceptable-use acknowledgement flow was established. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://docs.mistral.ai/vibe/work/image-generation.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. - content_filters — Are content filters configurable? [partial]: Images may be safety-filtered, but an administrator-configurable organization-wide content-filter matrix was not established. Sources: mistral-vibe:mistral-vibe:m-image-20261026. - violation_reporting — Are policy hits visible to admins? [unknown]: No central policy-hit reporting feature was established from audit/tracing docs. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://docs.mistral.ai/vibe/work/image-generation.md, https://mistral.ai/pricing/. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:m-image-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ## 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Mistral states EU hosting by default with feature-specific foreign transfers; private Enterprise locations are contract-scoped. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: backups_logs_region, support_access_region, swiss_hosting. - storage_region — Where are chats, files and indexes stored? [partial]: The official help article states EU default hosting, and Libraries say European cloud storage; exact countries/backups were not established. Sources: mistral-vibe:mistral-vibe:m-location, mistral-vibe:mistral-vibe:m-libraries. - inference_region — Where do model calls run, per provider? [partial]: The help article warns feature data may temporarily leave the EU; exact chat/image/search/provider inference regions were not fully established. Sources: mistral-vibe:mistral-vibe:m-location. - backups_logs_region — Where are backups, logs and telemetry? [unknown]: Unknown. A complete backup/log/telemetry regional map was not obtained. - support_access_region — From where can vendor staff access data? [unknown]: Unknown. Default EU hosting does not establish a European-only staff access rule; no such boundary was verified. - swiss_hosting — Is Swiss hosting available? [unknown]: Unknown. No named Swiss managed-hosting region or offer was established. - residency_plan — Which plan or option provides residency? [partial]: Enterprise can disable some transfer-triggering features and is offered private/on-prem deployment; exact location guarantees require its order. Sources: mistral-vibe:mistral-vibe:m-location, mistral-vibe:mistral-vibe:m-home. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-location, mistral-vibe:mistral-vibe:m-libraries, mistral-vibe:mistral-vibe:m-home ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise explicitly offers private cloud and on-premise Vibe; deployment thresholds and hosted/private parity are not public in the inspected sources. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration, Enterprise private Vibe deployment; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=not specified; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: air_gapped, mode_feature_gaps. - multi_tenant_saas — Is a shared SaaS offered? [supported]: Self-serve Free/Pro/Team use hosted Vibe; Enterprise may also use Mistral Cloud. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-home. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [partial]: Enterprise markets private deployments, but a distinct single-tenant SaaS configuration and seat threshold were not established. Sources: mistral-vibe:mistral-vibe:m-pricing. - customer_cloud — Can it run in the customer's own cloud account, from what size? [partial]: The product FAQ offers Enterprise private-cloud deployment; operator, supported clouds and minimum size were not established. Sources: mistral-vibe:mistral-vibe:m-home. - on_premise — Can the whole platform run on customer infrastructure, from what size? [partial]: Enterprise on-premise deployment is explicitly offered, with no public seat threshold in the retrieved page. Sources: mistral-vibe:mistral-vibe:m-home. - air_gapped — Can it run without internet access? [unknown]: Unknown. The coding CLI supports offline operation, but whole-platform air-gapped Vibe Work was not established. - mode_feature_gaps — Which features are missing outside SaaS? [unknown]: Unknown. No supported feature/connector/model parity matrix or operating responsibility for private deployments was obtained. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-home ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise general-content opt-out and Team/Enterprise voice opt-out are separately documented. Team general-chat training defaults remain unknown; Work/Chat has no ZDR entitlement. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Enterprise for the general-content training default; Team voice only where explicitly stated; Team general-content default unknown; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: provider_retention, human_review. - The general Work/Workspace documentation does not establish Team or Enterprise entitlement for every feature here. Unspecified-plan findings remain candidates; no plan inheritance is assumed. - The Team voice rule is not generalized to text, files, Libraries or Knowledge Base. Their default remains a gap rather than an inferred no-training promise. - vendor_training — Does the vendor train on customer content? [partial]: Enterprise is opted out by default, subject to the commercial opt-in, feedback, order and Labs/Preview exceptions. The voice guide separately excludes Team/Enterprise voice messages by default; that does not establish Team text/file defaults. Team admins can disable training, but the general-content default remains unknown. Sources: mistral-vibe:mistral-vibe:m-commercial, mistral-vibe:mistral-vibe:m-training, mistral-vibe:mistral-vibe:m-optout, mistral-vibe:mistral-vibe:m-voice-entitlement-correction. - provider_training — Do model providers train on it under this product's contracts? [partial]: Featured connector source content is described as excluded from training, while conversations using it follow plan policies; third-party image/MCP terms need separate review. Sources: mistral-vibe:mistral-vibe:m-connectors. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [unknown]: Unknown. The API default 30-day abuse window is not assumed to cover every hosted Work tool/provider; a full provider matrix was not obtained. - zero_retention — Is zero data retention available, and on which plan? [unsupported]: The ZDR guide explicitly excludes Vibe Work and Chat, Libraries, agents and conversations. Approved stateless API/CLI routes are separate. Sources: mistral-vibe:mistral-vibe:m-zdr. - human_review — Can provider staff review content? [unknown]: Unknown. Complete plan/provider-specific human content review conditions were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-commercial, mistral-vibe:mistral-vibe:m-training, mistral-vibe:mistral-vibe:m-optout, mistral-vibe:mistral-vibe:m-connectors, mistral-vibe:mistral-vibe:m-zdr, mistral-vibe:mistral-vibe:m-voice-entitlement-correction ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admins can set Workspace chat retention and users delete content, with legal/backend retention exceptions. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise hosted Work under commercial DPA; Workspace retention configuration documented separately; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - default_retention: Library content persists while the Library/account is active; hosted chat is retained for history, but an exact universal default chat/log term was not established. - default_retention — What is retained and for how long by default? [partial]: Library content persists while the Library/account is active; hosted chat is retained for history, but an exact universal default chat/log term was not established. Sources: mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:m-delete-20261026. - admin_retention — Can admins set retention periods? [supported]: Workspace chat/artifact retention can be 30, 90, 180 or 365 days, or never, subject to organization restrictions. Sources: mistral-vibe:mistral-vibe:m-adminvibe-20261026. - user_deletion — Can users delete their chats and files permanently? [supported]: Users can delete chats/Libraries/knowledge; user-visible chat removal does not promise immediate purge of backend/legal copies. Sources: mistral-vibe:mistral-vibe:m-delete-20261026, mistral-vibe:mistral-vibe:m-libraries-20261026. - contract_end_deletion — What is deleted at contract end, and when? [supported]: DPA section 10 provides return/deletion under its policies and says personal data is inaccessible after 30 days following product-access termination; legal records may persist. Sources: mistral-vibe:mistral-vibe:m-dpa-20261026, mistral-vibe:mistral-vibe:m-retention-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:m-delete-20261026, mistral-vibe:mistral-vibe:m-adminvibe-20261026, mistral-vibe:mistral-vibe:m-dpa-20261026, mistral-vibe:mistral-vibe:m-retention-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Mistral contracts under a French entity and uses contractual transfer safeguards; the complete current subprocessor table was not readable. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - subprocessor_list: The Trust Center/subprocessors endpoint returned a client-rendered non-substantive page; a dated complete list was not obtained. Search on 2026-10-26: https://legal.mistral.ai/terms/data-processing-addendum/, https://legal.mistral.ai/terms/commercial-terms-of-service/, https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data. No additional scoped evidence established this answer. - subprocessor_countries: Foreign feature transfers are acknowledged, but the complete provider/country mapping was not obtained. Search on 2026-10-26: https://legal.mistral.ai/terms/data-processing-addendum/, https://legal.mistral.ai/terms/commercial-terms-of-service/, https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data. No additional scoped evidence established this answer. - transfer_mechanism: The location help describes GDPR Article 46 safeguards/SCCs for non-adequate-country providers; complete Swiss-specific adaptations were not verified. - government_access_policy: DPA section 3.1 requires notice of legally required processing unless notification is prohibited or an important public-interest ground applies. A complete public law-enforcement request/transparency policy was not established. - subprocessor_list — Is a dated sub-processor list published? [unknown]: The Trust Center/subprocessors endpoint returned a client-rendered non-substantive page; a dated complete list was not obtained. Search on 2026-10-26: https://legal.mistral.ai/terms/data-processing-addendum/, https://legal.mistral.ai/terms/commercial-terms-of-service/, https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data. No additional scoped evidence established this answer. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: Foreign feature transfers are acknowledged, but the complete provider/country mapping was not obtained. Search on 2026-10-26: https://legal.mistral.ai/terms/data-processing-addendum/, https://legal.mistral.ai/terms/commercial-terms-of-service/, https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data. No additional scoped evidence established this answer. - change_notification — Are customers notified of sub-processor changes? [supported]: DPA provides reasonable prior subprocessor-change notice and a 10-day written objection window on data-protection grounds. Sources: mistral-vibe:mistral-vibe:m-dpa-20261026. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [supported]: Commercial terms name Mistral AI, a French corporation in Paris, or an order-specified affiliate. No ownership change was established. Sources: mistral-vibe:mistral-vibe:m-commercial-20261026. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [partial]: The location help describes GDPR Article 46 safeguards/SCCs for non-adequate-country providers; complete Swiss-specific adaptations were not verified. Sources: mistral-vibe:mistral-vibe:m-location-20261026, mistral-vibe:mistral-vibe:m-dpa-20261026. - government_access_policy — Is there a published government-access or transparency policy? [partial]: DPA section 3.1 requires notice of legally required processing unless notification is prohibited or an important public-interest ground applies. A complete public law-enforcement request/transparency policy was not established. Sources: mistral-vibe:mistral-vibe:m-dpa-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-dpa-20261026, mistral-vibe:mistral-vibe:m-commercial-20261026, mistral-vibe:mistral-vibe:m-location-20261026 ### 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. #### 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. #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial A public commercial DPA and France/Paris governing-law clause exist; Swiss secrecy and sector assurances remain unverified. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: ai_act_materials, sector_materials. - dpa — Is a DPA available, and is it negotiable? [partial]: A public Data Processing Addendum supplements commercial terms. Negotiability/offline execution was not verified. Sources: mistral-vibe:mistral-vibe:m-dpa. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [partial]: The DPA explicitly defines GDPR. A specific Swiss revDSG/FADP undertaking was not identified in the inspected text. Sources: mistral-vibe:mistral-vibe:m-dpa. - governing_law — Which law and court govern the contract? [supported]: For customers outside Americas/APAC, the commercial terms specify French law and exclusive Paris courts, subject to the applicable order. Sources: mistral-vibe:mistral-vibe:m-commercial. - ai_act_materials — Is EU AI Act documentation provided? [unknown]: Unknown. No Vibe-specific EU AI Act provider/deployer document pack was obtained. - sector_materials — Are FINMA or other sector materials provided? [unknown]: Unknown. No FINMA, banking-secrecy or scoped sector-contract package was obtained; generic confidentiality is not professional secrecy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-dpa, mistral-vibe:mistral-vibe:m-commercial ### 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. #### 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. #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial SOC 2 II and ISO 27001/27701 are vendor claims until reports, entity scope and validity are inspected. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: c5, pentest. - iso_27001 — ISO 27001 with scope and validity? [partial]: Mistral claims ISO 27001; certificate issuer, exact product/entity scope and validity were not retrieved. Sources: mistral-vibe:mistral-vibe:m-cert. - soc2 — SOC 2 type, period and covered service? [partial]: Mistral claims SOC 2 Type II; audit period and scoped report were not inspected. Sources: mistral-vibe:mistral-vibe:m-cert. - c5 — BSI C5 attestation? [unknown]: Unknown. No current product-scoped C5 attestation was retrieved. - other_certifications — Which other certificates (27701, 42001, TISAX)? [partial]: ISO 27701 is also claimed, without an inspected certificate and validity. Sources: mistral-vibe:mistral-vibe:m-cert. - report_access — How can customers obtain reports? [partial]: The official help directs compliance-report requests to the Trust Center, whose client-rendered reports were not accessible in this pass. Sources: mistral-vibe:mistral-vibe:m-cert. - pentest — Are independent penetration test summaries available? [unknown]: Unknown. No independent penetration-test summary was retrieved. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-cert ### 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). #### 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 #### Mistral Vibe 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-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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Profession-specific secrecy undertaking and add-on remain unknown; general confidentiality and scoped content-access controls do not establish §203 StGB or Art.321 StGB coverage. Availability: unknown Delivery: unknown Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Work Team/Enterprise; private/partner-served support access scoped separately; add_ons=none stated; deployment_mode=not specified; region=No profession-specific DE/CH contractual scope verified; deployment/provider regions follow the other scoped claims.; os=not specified. Limitations: - Contract facts only; no legal suitability assessment. No profession-specific commitment or paid option inferred from generic confidentiality, hosting, encryption or no-training terms. - Public, unauthenticated source pass only; no sales contact, NDA request or authenticated access-control test. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Unknown. Reviewed Mistral commercial terms, DPA, Vibe security/deployment documentation and targeted first-party searches for professional secrecy, secret professionnel, §203 and Art.321. No Vibe-specific secrecy contract template, dedicated plan/add-on or flow-down undertaking was retrieved. A DPA or no-training clause alone does not answer whether a profession-specific undertaking is signed. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Unknown. No retrieved §203/Art.321 undertaking establishes flow-down to all relevant subcontractors/model providers. General DPA confidentiality is not equivalent. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: Unknown. No documented profession-specific plan, dedicated instance option or paid secrecy add-on and its entitlements/pricing were established. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: DPA3.1 binds authorised Mistral personnel and subprocessors to confidentiality. Annex1 includes debugging/testing and partner-served support processing. The exact role-by-role plaintext-access matrix, private-deployment support controls and external model-provider access were not established; confidentiality is not a profession-specific undertaking. Sources: mistral-vibe:mistral-vibe:m-dpa. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Unknown. Reviewed Mistral commercial terms, DPA, Vibe security/deployment documentation and targeted first-party searches for professional secrecy, secret professionnel, §203 and Art.321. No Vibe-specific secrecy contract template, dedicated plan/add-on or flow-down undertaking was retrieved. General data-flow/security pages are available but do not document such a secrecy offering. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-dpa ## 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial The public USD page lists Team at USD 24.99/user/month and Enterprise custom. Exact Pro checkout price and API-credit allowance are not established from conflicting rendered variants. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Free / Pro / Team public pricing as rendered in USD on 2026-10-21; Enterprise quote-only; Pro checkout variants unverified; add_ons=Optional prepaid usage; private Enterprise/custom-model costs unknown; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - The partial atomic answers state their documentation or verification limits. - The general Work/Workspace documentation does not establish Team or Enterprise entitlement for every feature here. Unspecified-plan findings remain candidates; no plan inheritance is assumed. - Pro price and included-credit selection remain explicit gaps; neither rendered variant is treated as the purchased entitlement. - pricing_unit — What is the pricing unit? [supported]: Pro is per account, Team per user/month, Enterprise custom; included usage and prepaid usage extension span named product routes. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-subscription. - list_prices — What are list prices per plan, with date and currency? [partial]: Team is displayed at USD 24.99/user/month excluding taxes and Enterprise is custom. The Pro page mixes education/card variants and a normal-price FAQ; the applicable Pro checkout price, currency and billing selection were not verified. Sources: mistral-vibe:mistral-vibe:m-pricing. - included_usage — What usage is included? [partial]: Team advertises up to 30 GB/user and relative allowances. A fixed Pro API-credit entitlement is unknown: the rendered card includes USD 25.5 and USD 15 monthly variants without an established selection. No Pro credit amount is credited. Sources: mistral-vibe:mistral-vibe:m-pricing. - add_ons — Which features cost extra? [supported]: PAYG prepaid credits extend eligible usage after included allowances; Enterprise private services and custom models are separately scoped. Sources: mistral-vibe:mistral-vibe:m-billing, mistral-vibe:mistral-vibe:m-home. - overage — What do usage beyond limits and premium models cost? [partial]: PAYG uses model/API rates for eligible routes, but no exact default Work model tariff and allowance sufficiency for the shared workload were established. Sources: mistral-vibe:mistral-vibe:m-subscription, mistral-vibe:mistral-vibe:m-pricing. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-subscription, mistral-vibe:mistral-vibe:m-billing, mistral-vibe:mistral-vibe:m-home ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial ALM-14 shared cost assumptions v1.4, 2026-10-21: Team licence illustrations plus unknown variable/enterprise costs; no complete total is claimed. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team displayed USD rate, 12 months, excluding VAT; Enterprise quote separate; add_ons=Unknown usage extension, support/implementation; no bulk discount assumed; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Mix: 60% at 100, 30% at 400 and 10% at 1,500 messages/user/month, 330 average. Separately billed messages assume 3,000 input + 600 output tokens; no product-tariff proxy used. - ECB 2026-10-20: EUR 1 = USD 1.1215 = CHF 0.9237; EUR = USD / 1.1215, CHF = EUR × 0.9237. - These are displayed-rate Team licence illustrations; complete Enterprise/private totals remain unknown. - cost_200 — Year-one cost at 200 users? [partial]: Team displayed-rate licence illustration: USD 59,976.00 = EUR 53,478.38 = CHF 49,397.98 for 200 seats × 12 × USD 24.99, excluding VAT, plus unknown usage/support/implementation. Enterprise/private deployment and SAML terms require their own quote; applicability of Team at this size was not verified. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:fx-ecb. - cost_1000 — Year-one cost at 1,000 users? [partial]: Team displayed-rate licence illustration: USD 299,880.00 = EUR 267,391.89 = CHF 246,989.88 for 1,000 seats × 12 × USD 24.99, excluding VAT, plus unknown usage/support/implementation. Enterprise/private deployment and SAML terms require their own quote; applicability of Team at this size was not verified. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:fx-ecb. - cost_5000 — Year-one cost at 5,000 users? [partial]: Team displayed-rate licence illustration: USD 1,499,400.00 = EUR 1,336,959.43 = CHF 1,234,949.42 for 5,000 seats × 12 × USD 24.99, excluding VAT, plus unknown usage/support/implementation. Enterprise/private deployment and SAML terms require their own quote; applicability of Team at this size was not verified. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:fx-ecb. - variable_share — Which part depends on usage? [partial]: Included allowance is consumed before eligible prepaid PAYG; exact Work default model/tariff, fair-use sufficiency and tool charges remain unknown. Sources: mistral-vibe:mistral-vibe:m-subscription, mistral-vibe:mistral-vibe:m-pricing. - unknown_parts — Which costs could not be priced? [partial]: Unknown: Enterprise/private licence quote, bulk eligibility/commitment, exact included credits, separately charged Work usage at the shared mix, deployment/operations, support and implementation. No tariff proxy or discount is invented. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-subscription. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:fx-ecb, mistral-vibe:mistral-vibe:m-subscription ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Free self-serve exploration exists; SAML, private deployments and gated administration cannot be assumed included. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: self_serve_trial, trial_scope. - free_tier — Is there a free tier for business use? [partial]: The public Free plan offers limited chat/search/tools; business contractual suitability and enterprise controls were not verified. Sources: mistral-vibe:mistral-vibe:m-pricing. - self_serve_trial — Is a self-serve business trial available? [unknown]: Unknown. No time-limited business-plan trial duration, card or seat limit was verified; the Free plan is a different access route. - trial_scope — Do trials include SSO, connectors and admin features? [unknown]: Unknown. No trial verified Enterprise SSO, admin, connectors and fixture entitlement together. - sales_gate — Does meaningful evaluation require sales contact? [supported]: Free/paid self-service exploration is offered, while private Enterprise and Admin API activation require contact. No contact was made. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-provision. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-provision ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-serve prices are partly public; enterprise terms and commitment/pricing details require the applicable order. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: minimum_commitment. - minimum_commitment — What seat or spend minimum applies? [unknown]: Unknown. The rendered Team calculator shows a subtotal but does not establish an exact contractual minimum or maximum for the requested seat sizes. - contract_length — What contract lengths are offered? [partial]: Commercial terms charge as provided by the order/confirmation; exact Team monthly/annual commitment alternatives were not established. Sources: mistral-vibe:mistral-vibe:m-commercial. - cancellation — How can the contract be cancelled or reduced? [partial]: Commercial terms make paid amounts non-refundable/non-cancellable; a complete self-serve downgrade/cancellation workflow was not verified. Sources: mistral-vibe:mistral-vibe:m-commercial. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [partial]: A French contracting entity and USD/EUR price selector are public; actual CHF/EUR enterprise invoicing terms were not verified. Sources: mistral-vibe:mistral-vibe:m-commercial, mistral-vibe:mistral-vibe:m-pricing. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [supported]: Partially specified: self-serve displayed prices exist, while Enterprise/private quotes, exact credits and scenario usage charges remain unresolved. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-subscription. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-commercial, mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-subscription ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hosted Work is a commercial service; separate CLI/model licences do not license the whole workspace. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - The partial atomic answers state their documentation or verification limits. - licence_type — Which licence applies to each component? [partial]: Commercial terms reserve Mistral product IP and grant limited service use. Open-weight model/CLI component terms are separate and were not exhaustively audited. Sources: mistral-vibe:mistral-vibe:m-commercial. - branding_restrictions — Do licence terms restrict branding or user counts? [partial]: Enterprise pricing lists white label/dedicated hostname; contractual branding rights and seat restrictions require that order. Sources: mistral-vibe:mistral-vibe:m-pricing. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: Enterprise lists custom deployment, SAML and audit features under commercial terms; component-by-component source availability was not established. Sources: mistral-vibe:mistral-vibe:m-pricing, mistral-vibe:mistral-vibe:m-commercial. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-commercial, mistral-vibe:mistral-vibe:m-pricing ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Personal exports and original Library downloads are documented; full administrator portability remains untested. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise personal Data Export and Library/Knowledge downloads; complete administrator portability unverified; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - chat_export: A personal data export tool is documented; all-user administrator chat export completeness was not verified. - assistant_export: Legacy agents can be duplicated and Skills contain reusable files, but a complete portable assistant/tool/knowledge export package was not verified. Search on 2026-10-26: https://help.mistral.ai/en/articles/347623-how-do-i-export-my-data-from-vibe, https://docs.mistral.ai/vibe/work/libraries.md, https://docs.mistral.ai/vibe/work/knowledge.md. No additional scoped evidence established this answer. - knowledge_export: Users can download original Library documents and export personal Knowledge Base data; complete admin index/ACL export was not verified. - export_format: Canvas offers PPTX/table files and spreadsheets XLSX, but the full personal-data/agent/index export schema was not established. - post_termination_window: The DPA says personal data is no longer accessible 30 days after access/use termination; a guaranteed complete post-termination export service was not established. - chat_export — Can admins export all chats? [partial]: A personal data export tool is documented; all-user administrator chat export completeness was not verified. Sources: mistral-vibe:mistral-vibe:m-export-20261026. - assistant_export — Can assistants and prompts be exported in a reusable format? [unknown]: Legacy agents can be duplicated and Skills contain reusable files, but a complete portable assistant/tool/knowledge export package was not verified. Search on 2026-10-26: https://help.mistral.ai/en/articles/347623-how-do-i-export-my-data-from-vibe, https://docs.mistral.ai/vibe/work/libraries.md, https://docs.mistral.ai/vibe/work/knowledge.md. No additional scoped evidence established this answer. - knowledge_export — Can knowledge bases and their sources be exported? [partial]: Users can download original Library documents and export personal Knowledge Base data; complete admin index/ACL export was not verified. Sources: mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:m-memory-20261026. - export_format — Are formats documented and machine-readable? [partial]: Canvas offers PPTX/table files and spreadsheets XLSX, but the full personal-data/agent/index export schema was not established. Sources: mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:m-sheets-20261026, mistral-vibe:mistral-vibe:m-export-20261026. - post_termination_window — How long can data be retrieved after termination? [partial]: The DPA says personal data is no longer accessible 30 days after access/use termination; a guaranteed complete post-termination export service was not established. Sources: mistral-vibe:mistral-vibe:m-dpa-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-export-20261026, mistral-vibe:mistral-vibe:m-libraries-20261026, mistral-vibe:mistral-vibe:m-memory-20261026, mistral-vibe:mistral-vibe:m-files-20261026, mistral-vibe:mistral-vibe:m-sheets-20261026, mistral-vibe:mistral-vibe:m-dpa-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public support routes and custom Enterprise SLA marketing exist; status access and concrete service terms remain gaps. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Hosted Vibe Team / Enterprise; Free and Pro or CLI are named only where separately established; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - Remaining atomic gaps: support_languages, regional_presence, status_page. - support_channels — Which support channels are available on each plan? [supported]: Pro/Team pricing lists chat/email support and Enterprise advertises dedicated support. Sources: mistral-vibe:mistral-vibe:m-pricing. - support_languages — Is support available in German, French or Italian? [unknown]: Unknown. German/French/Italian support language/hours commitments were not retrieved. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: Unknown. The commercial entity is Paris-based; a named DACH/Swiss implementation team/partner was not verified. - uptime_sla — Is there an uptime SLA with credits? [partial]: Enterprise advertises custom SLAs; uptime percentage, exclusions, response times and credits were not obtained. Sources: mistral-vibe:mistral-vibe:m-pricing. - status_page — Is there a public status page with history? [unknown]: Unknown. The public status endpoint returned HTTP 403 to direct retrieval; no incident history was independently read. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-pricing ### 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. #### 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 #### Mistral Vibe Verification status: Agent cross-checked (agent-cross-checked) Support: partial Built-in onboarding and reusable role/task Skills support self-service adoption; service entitlements and prices remain open. Availability: unknown Delivery: native Scope: surfaces=Hosted Vibe Work web app after migration; version=not specified; plan=Team/Enterprise plan-included Work Skills and public self-service documentation; managed services unverified; add_ons=none stated; deployment_mode=multi-tenant-saas; region=EU-hosted by default, with feature-specific external transfers; private deployment by contract; os=not specified. Limitations: - onboarding_service: Vendor-led onboarding inclusion was not established; no sales/demo contact was made. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://mistral.ai/pricing/, https://legal.mistral.ai/terms/commercial-terms-of-service/. No additional scoped evidence established this answer. - user_training: A built-in vibe-work-onboarding Skill and public guides exist; live training and language coverage were not established. - adoption_programme: No scoped champion or change-management programme entitlement was retrieved. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://mistral.ai/pricing/, https://legal.mistral.ai/terms/commercial-terms-of-service/. No additional scoped evidence established this answer. - service_cost: Implementation/partner/training service prices were not obtained. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://mistral.ai/pricing/, https://legal.mistral.ai/terms/commercial-terms-of-service/. No additional scoped evidence established this answer. - onboarding_service — Is guided onboarding included? [unknown]: Vendor-led onboarding inclusion was not established; no sales/demo contact was made. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://mistral.ai/pricing/, https://legal.mistral.ai/terms/commercial-terms-of-service/. No additional scoped evidence established this answer. - user_training — Is end-user training offered, in which languages? [partial]: A built-in vibe-work-onboarding Skill and public guides exist; live training and language coverage were not established. Sources: mistral-vibe:mistral-vibe:m-skills-20261026. - use_case_library — Are role-based use cases and templates provided? [supported]: Built-in Skills and examples cover research, extraction, onboarding, stakeholder communication and repeated procedures. Sources: mistral-vibe:mistral-vibe:m-skills-20261026. - adoption_programme — Is there a champion or adoption programme? [unknown]: No scoped champion or change-management programme entitlement was retrieved. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://mistral.ai/pricing/, https://legal.mistral.ai/terms/commercial-terms-of-service/. No additional scoped evidence established this answer. - service_cost — Which services cost extra? [unknown]: Implementation/partner/training service prices were not obtained. Search on 2026-10-26: https://docs.mistral.ai/vibe/work/skills.md, https://mistral.ai/pricing/, https://legal.mistral.ai/terms/commercial-terms-of-service/. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: mistral-vibe:mistral-vibe:m-skills-20261026, mistral-vibe:mistral-vibe:plan-matrix-20261026 ## Sources ### 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 ### mistral-vibe:mistral-vibe:plan-matrix-20261026 Mistral Vibe public plan comparison. The table includes Skills, web, connectors and custom MCP on Team/Enterprise, labels connectors beta, gives Team 30 GB/user Libraries, and includes Canvas, scheduling, workflows, image generation and data export. Knowledge connectors are Team/Enterprise; Admin API, audit logs, SAML SSO and custom deployment are Enterprise. Enterprise infinity icons are not fixed quotas. - URL: https://mistral.ai/pricing/ - Locator: Vibe comparison table, ordered Free / Pro / Team / Enterprise columns, including inclusion and exclusion SVG icons rather than text-only extraction; HTTP 200, body SHA256 650153212b270213cd4e18baa9d973a2dceb5fe2af5403ca421efadcd9a723dd - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-release-notes-20261026 Mistral release notes. Chat-to-Work migration is phased, with Enterprise migration starting October 1 and an approximate six-month administrator window. - URL: https://docs.mistral.ai/resources/release-notes.md - Locator: 2026-09-22: simpler Vibe experience; Knowledge Base; spreadsheets; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 2e5b0d700fa3426538fedfdd02bc63bbab6d2b97b91c1f72c6460a3a6ea0d07b on 2026-10-26 - Evidence kind: documented - Source date: 2026-09-22 - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-home-20261026 Mistral Vibe product. Mistral combines Work/Chat and coding under Vibe and offers Enterprise on-premise/private-cloud deployments. - URL: https://mistral.ai/products/vibe/ - Locator: FAQ: name, deployment, voice and integrations; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 0246e627184ac60f05c6672201cd99be89752c34cae3e7b4a1e899be9508869b on 2026-10-26 - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-image-20261026 Generate images. Image generation uses Black Forest Labs models and supports uploaded-image edits with plan limits. - URL: https://docs.mistral.ai/vibe/work/image-generation.md - Locator: Model provider; editing; limits; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 ea76aed6c7b591368c3ae678e2e772ed8be592a7d01931f63e5cc001ab915f23 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-files-20261026 Work with Files and Canvas. Files and Canvas support documents, scanned images, audio analysis, editable outputs and PowerPoint/table export. - URL: https://docs.mistral.ai/vibe/work/files-and-canvas.md - Locator: Supported formats; image/audio/spreadsheet analysis; Canvas exports; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 69c16ff45099cba600e79f8ed219a4765adc73d4b015f332be1f4fc28b3fb6b6 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-release-notes Mistral release notes. Chat-to-Work migration is phased, with Enterprise migration starting October 1 and an approximate six-month administrator window. - URL: https://docs.mistral.ai/resources/release-notes.md - Locator: 2026-09-22: simpler Vibe experience; Knowledge Base; spreadsheets - Evidence kind: documented - Source date: 2026-09-22 - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-releases Mistral changelog. A public dated model/API changelog exists, but it does not establish per-plan Vibe availability lag. - URL: https://docs.mistral.ai/resources/changelogs.md - Locator: Dated model/API entries - Evidence kind: documented - 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 ### 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 ### mistral-vibe:mistral-vibe:m-pricing Mistral pricing. The USD page lists Pro 14.99/month and Team 24.99/user/month excluding taxes, with custom Enterprise and usage/fair-use conditions. - URL: https://mistral.ai/pricing/ - Locator: Free/Pro/Team/Enterprise cards; feature table; FAQs - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-libraries Add context with Libraries. Libraries persist uploaded/indexed knowledge, allow individual/organization sharing and provide numbered source references. - URL: https://docs.mistral.ai/vibe/work/libraries.md - Locator: Upload and limits; sharing; source references; data and privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-subscription Subscriptions. The plan spans Vibe/Studio/API, while included allowance and prepaid PAYG have product-specific behavior. - URL: https://docs.mistral.ai/admin/billing-usage/subscriptions.md - Locator: Global plan; monthly usage; PAYG - 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 ### mistral-vibe:mistral-vibe:m-files Work with Files and Canvas. Files and Canvas support documents, scanned images, audio analysis, editable outputs and PowerPoint/table export. - URL: https://docs.mistral.ai/vibe/work/files-and-canvas.md - Locator: Supported formats; image/audio/spreadsheet analysis; Canvas exports - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-sheets Spreadsheets. Paid Work supports spreadsheet generation/editing and downloadable XLSX output; fidelity requires testing. - URL: https://docs.mistral.ai/vibe/work/spreadsheets.md - Locator: Paid-plan availability; formulas; export - 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 ### 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 ### mistral-vibe:mistral-vibe:m-connectors-20261026 Connect tools with Connectors. Featured connectors use OAuth and live retrieval; source content and conversations have separately stated storage/training policies. - URL: https://docs.mistral.ai/vibe/work/connectors.md - Locator: Featured connectors; approval; data and privacy; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 3cc3745b35cceeb58b7e3055a0f9b3c0e59363853336f857c30f2a589e04bc36 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-mcp-20261026 MCP Connectors. Admins add HTTPS MCP servers with OAuth/Bearer/Basic or no authentication; users may preauthorize individual functions. - URL: https://docs.mistral.ai/vibe/work/connectors/mcp-connectors.md - Locator: Custom configuration; authentication; per-function permissions; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 5e97d5e51b4f26d358561bcd3533c6bf7e666845874071508428b023e9457666 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### 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 ### mistral-vibe:mistral-vibe:m-libraries-20261026 Add context with Libraries. Libraries persist uploaded/indexed knowledge, allow individual/organization sharing and provide numbered source references. - URL: https://docs.mistral.ai/vibe/work/libraries.md - Locator: Upload and limits; sharing; source references; data and privacy; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 8c7fe6f7c1aba5acc314428ee145b6df19e6bd24c2c14139f419a8e27e1fcfd5 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:connector-data-controls-20261026 Mistral connected-tool data controls. Request-time connectors have no persistent connector index. Knowledge connectors index selected content, propagate source deletions after synchronization and schedule indexed-data deletion after administrator disconnection. Updated source permissions govern retrieval; no timing SLA is stated. - URL: https://help.mistral.ai/en/articles/661571-how-can-i-control-or-delete-data-connected-to-third-party-tools - Locator: Request-time connectors versus indexed Knowledge Connectors, source deletion and permission changes; HTTP 200, body SHA256 66ff17f717a1e1387b8e1320d1a7bfe1d843902cdec51525b02acc068c26e54a - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-26 ### 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 ### mistral-vibe:mistral-vibe:m-adminvibe-20261026 Workspaces in Vibe. Admins configure per-Workspace features, chat retention and tracing; linked connector accounts are not isolated per Workspace. - URL: https://docs.mistral.ai/admin/workspaces/workspaces-in-vibe.md - Locator: Connector accounts; feature toggles; retention; tracing; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 ceefc4c8001e86724007c916e453c861c23beb3ca2da96d97ad78073d7f07dfa on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-instructions-20261026 Set custom instructions. Users set persistent role/tone/output instructions; these are instructions to the model, not an independently enforced policy. - URL: https://docs.mistral.ai/vibe/work/custom-instructions.md - Locator: Persistent preferences; tone; limitations; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 51d552c0953898b24c8524746b24f1370bb5d3cc72ec01ef36902437e1823a54 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-projects-20261026 Group tasks with Projects. Projects apply shared context/instructions to their own conversations; deleting a project retains its chats in main history. - URL: https://docs.mistral.ai/vibe/work/projects.md - Locator: Project instructions/context; chat organization; deletion; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 ff0dd2912de917c2747e25ed4f83f6b3569f00a09c06a6de2c14d6a8cb0b43aa on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-memory-20261026 Knowledge Base. Work stores cross-chat personal knowledge with view/edit/delete/export controls and administrator settings, including sensitive-data restrictions. - URL: https://docs.mistral.ai/vibe/work/knowledge.md - Locator: User and admin controls; sensitive data; related features; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 613f78a4a63a8c05c84a120f66cdf8f3489d547124b13d1118abeb6784fce56f on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-legacy-agents-20261026 Agents, legacy Chat. Legacy Chat Agents have instructions/knowledge/tools and sharing, but cannot be called programmatically and are being replaced by Skills. - URL: https://docs.mistral.ai/vibe/chat-legacy/agents.md - Locator: Migration warning; configuration; sharing; Agents and API; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 542944a04b534264b9275f8181e3b7646cc00cade371ea6593f7e2ce42975836 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-skills-20261026 Reuse work with Skills. Skills package reusable instructions/resources and can be Workspace-shared or force-enabled by an administrator. - URL: https://docs.mistral.ai/vibe/work/skills.md - Locator: Built-in skills; personal/Workspace; force-enable; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 2f0b7278ab361694b57ff14e93efd7122bbb79dc84a57250a366092156f1b825 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### 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 ### mistral-vibe:mistral-vibe:m-admincon-20261026 Admin connector controls. Admins can connect organization-level GitHub/Slack bot accounts and allow/restrict/block connector tools per Workspace. - URL: https://docs.mistral.ai/admin/identity-access/connectors - Locator: App Connections; credentials; permissions; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 cb054ecf6a8d510006abc7d3d67519376efb3d8f3afe1f4958733b2e6edb8298 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-web-20261026 Search the web. Work offers live web search with citations, Open URL and Deep Research as a Skill; generic search-processing location is not specified. - URL: https://docs.mistral.ai/vibe/work/web-search-open-url.md - Locator: Web search; news partners; Open URL; Deep Research; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 5b610273811ca8dc13326556bfd819d407822bde50c8f72fc3d24db734321479 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-interpreter-20261026 Code Interpreter. Paid Work can execute Python/TypeScript without sandbox internet access and return charts and downloadable transformed files. - URL: https://docs.mistral.ai/vibe/work/code-interpreter.md - Locator: Paid plans; isolated Python/TypeScript sandbox; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 7010e49b18df7a09c06815a2d6a473387727dafaeba1600dbdfc2130add0fd79 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-workflows-20261026 Run Workflows. Developers build/publish coded Studio workflows which users invoke explicitly from Work; Skills are not deterministic workflows. - URL: https://docs.mistral.ai/vibe/work/workflows.md - Locator: Studio-built workflows; Skills vs Workflows; limits; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 f76422c0bf363fb3247af96cca668f446507fd25a4689a320b9546dc07176d6f on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-safety-20261026 Safety and approvals. Work exposes task progress and tool inputs/results; writes require approval unless preauthorized, and stop does not undo completed external actions. - URL: https://docs.mistral.ai/vibe/work/safety-and-approvals.md - Locator: Continue/Always allow/Decline; stop; todos and tool calls; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 d666f33e5341293b71de8e998b7c360c42ca2b44cd735749d071dffb3ad4e229 on 2026-10-26 - 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 ### mistral-vibe:mistral-vibe:m-groups-20261026 User groups. Enterprise groups assign roles/access to Workspaces, including externally managed identity-provider groups. - URL: https://docs.mistral.ai/admin/identity-access/groups.md - Locator: Enterprise availability; externally managed groups; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 03c1b2de931a321ff17def3092c12f0b3ad8530165a22b9e3e747cdcbcbb318d on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### 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 ### mistral-vibe:mistral-vibe:m-schedule-20261026 Schedule tasks. Work scheduling is public preview and time-triggered; unattended writes need preauthorization and no current event-trigger support is promised. - URL: https://docs.mistral.ai/vibe/work/scheduled-tasks.md - Locator: Public Preview; time-based triggers; approvals; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 e4c6a01ef68d7989ed26518a38cc835790d8f3215240c678de3434f6223a1e44 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-legacy-agents Agents, legacy Chat. Legacy Chat Agents have instructions/knowledge/tools and sharing, but cannot be called programmatically and are being replaced by Skills. - URL: https://docs.mistral.ai/vibe/chat-legacy/agents.md - Locator: Migration warning; configuration; sharing; Agents and API - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-provision User provisioning with the Admin API. An Enterprise Admin API supports user/group/Workspace lifecycle actions but requires separately enabled access. - URL: https://docs.mistral.ai/admin/admin-api/user-provisioning.md - Locator: Enterprise access gate; users; groups; removal - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-usage-api Usage metrics with the Admin API. Enterprise API endpoints expose billing and product usage, including messages/files/images and agent activity by user or agent. - URL: https://docs.mistral.ai/admin/admin-api/usage-metrics.md - Locator: Billing usage; lechat per-user/per-agent metrics - 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 ### mistral-vibe:mistral-vibe:m-home Mistral Vibe product. Mistral combines Work/Chat and coding under Vibe and offers Enterprise on-premise/private-cloud deployments. - URL: https://mistral.ai/products/vibe/ - Locator: FAQ: name, deployment, voice and integrations - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-voice Use Voice mode. Voice prompts are transcribed on web/mobile; the guide lists DE/FR/IT and says Team/Enterprise voice is training-opted-out by default. - URL: https://docs.mistral.ai/vibe/work/voice-mode.md - Locator: Web/mobile; transcription; languages; privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-instructions Set custom instructions. Users set persistent role/tone/output instructions; these are instructions to the model, not an independently enforced policy. - URL: https://docs.mistral.ai/vibe/work/custom-instructions.md - Locator: Persistent preferences; tone; limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-commercial-20261026 Commercial terms of service. Commercial terms apply to Vibe and reserve product IP, with conditional training permissions and feedback/Labs exceptions. - URL: https://legal.mistral.ai/terms/commercial-terms-of-service/ - Locator: 4 Training; 5 Rights; fees; regional governing law; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 cf72086a4255c8704eadbc59bb26581dcaf2c3c4d5af8fd3f51261313e66d390 on 2026-10-26 - 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 ### mistral-vibe:mistral-vibe:m-voice-entitlement-correction Use Voice mode. Dictation is documented for web and mobile on all plans; the Team/Enterprise no-training default in this guide is specifically for voice messages. - URL: https://docs.mistral.ai/vibe/work/voice-mode - Locator: Opening availability paragraph; Privacy - 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 ### mistral-vibe:mistral-vibe:m-interpreter Code Interpreter. Paid Work can execute Python/TypeScript without sandbox internet access and return charts and downloadable transformed files. - URL: https://docs.mistral.ai/vibe/work/code-interpreter.md - Locator: Paid plans; isolated Python/TypeScript sandbox - 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 ### mistral-vibe:mistral-vibe:m-workspace-20261026 Create your first Workspace. An organization can have up to 500 active Workspaces; organization admins retain access to each Workspace. - URL: https://docs.mistral.ai/admin/workspaces/your-first-workspace.md - Locator: Workspace boundary; cap; administrator access; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 38dc85c7eccf438f1cf95c4ed94a21825fb86886403c46946b1a124710c71c02 on 2026-10-26 - 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 ### 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 ### mistral-vibe:mistral-vibe:account-mfa-20261026 Mistral account password and 2FA settings. Account holders can enable TOTP authenticator-based two-factor authentication and generate recovery codes. The guide does not establish organization-wide enforced MFA or Entra conditional-access behavior. - URL: https://help.mistral.ai/en/articles/448331-how-do-i-update-my-account-information-email-password-and-2fa - Locator: Manage multi-factor authentication, authenticator setup and recovery codes; HTTP 200, body SHA256 9b5a8da7485f1b58da8ab3060534e4a1f6cb2c60cc266a6c9e511cd4c330c7a7 - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-sso-20261026 Single sign-on. Enterprise SSO uses SAML 2.0, explicitly not OIDC, and provisions users at first sign-in with optional seat assignment. - URL: https://docs.mistral.ai/admin/set-up-organization/sign-in-method/saml-sso.md - Locator: Enterprise requirement; SAML 2.0; first sign-in; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 7cfb898b71db3443ba264a673b8c2455840424eccd072f19573d6063d255a1c6 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-groups User groups. Enterprise groups assign roles/access to Workspaces, including externally managed identity-provider groups. - URL: https://docs.mistral.ai/admin/identity-access/groups.md - Locator: Enterprise availability; externally managed groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-sso Single sign-on. Enterprise SSO uses SAML 2.0, explicitly not OIDC, and provisions users at first sign-in with optional seat assignment. - URL: https://docs.mistral.ai/admin/set-up-organization/sign-in-method/saml-sso.md - Locator: Enterprise requirement; SAML 2.0; first sign-in - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-users User management. Admins invite/remove members and assign product seats; removal from the organization removes Workspace permissions. - URL: https://docs.mistral.ai/admin/identity-access/user-management.md - Locator: Seats; removal; roles - 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 ### mistral-vibe:mistral-vibe:m-usage-api-20261026 Usage metrics with the Admin API. Enterprise API endpoints expose billing and product usage, including messages/files/images and agent activity by user or agent. - URL: https://docs.mistral.ai/admin/admin-api/usage-metrics.md - Locator: Billing usage; lechat per-user/per-agent metrics; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 406f6ae09c2762cf72a004e5ed3c1f7d1065c3e72c2bc4ee89e5066f52b92a74 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-limits-20261026 Workspace usage and limits. Workspace caps default to none and support model/token/spend reporting; the defined limit action suspends API access. - URL: https://docs.mistral.ai/admin/workspaces/usage-limits.md - Locator: Spending cap; rate limits; usage breakdown; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 4c54c5e3d67d54e6a75d2c311603fb83246e6f5f93cbfa61cdc00345fc4d3066 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-billing-20261026 Billing. Billing supports prepaid credits, organizational limits and invoice downloads; API/Code credit exhaustion has documented failure behavior. - URL: https://docs.mistral.ai/admin/billing-usage/billing.md - Locator: Credits; 402 exhaustion; monthly spending limit; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 4c4d5c9b62f949224e58d971fb6d0049ae350e3fc53662164f43725f08cd1f3d on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### 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 ### mistral-vibe:mistral-vibe:m-audit Audit logs overview. Enterprise audit records administrative/authentication and conversation lifecycle events; this guide explicitly says log export is unsupported. - URL: https://docs.mistral.ai/admin/monitor-comply/audit-logs/overview.md - Locator: Enterprise availability; captured activities; limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-audit-ref Audit logs reference. The reference defines actor, target and event fields, but event names do not prove full prompt-body capture or retention. - URL: https://docs.mistral.ai/admin/monitor-comply/audit-logs/reference.md - Locator: Event types and response fields - 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 ### 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 ### mistral-vibe:mistral-vibe:m-location Where is data stored?. Mistral states default EU hosting with feature-dependent extra-EU transfers; some Enterprise features can be disabled to reduce transfers. - URL: https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data - Locator: EU default; feature transfers; Enterprise controls - Evidence kind: documented - Source date: 2026-08-12 - 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 ### mistral-vibe:mistral-vibe:m-connectors Connect tools with Connectors. Featured connectors use OAuth and live retrieval; source content and conversations have separately stated storage/training policies. - URL: https://docs.mistral.ai/vibe/work/connectors.md - Locator: Featured connectors; approval; data and privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-zdr Zero data retention. ZDR covers approved stateless paid API routes and explicitly excludes Vibe Work/Chat, libraries, conversations and agents. - URL: https://docs.mistral.ai/admin/monitor-comply/zero-data-retention.md - Locator: Coverage; exclusions; request - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-training Do you use user data for model training?. Enterprise defaults to training opt-out, generic Vibe defaults differ, and submitted feedback can authorize related-data use. - URL: https://help.mistral.ai/en/articles/347617-do-you-use-my-user-data-to-train-your-artificial-intelligence-models - Locator: Controls on Vibe; Enterprise; feedback - Evidence kind: documented - Source date: 2026-08-31 - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-optout Training opt-out controls. The September article says Team admins may disable training and Enterprise defaults to opt-out; Vibe and API controls are separate. - URL: https://help.mistral.ai/en/articles/455207-can-i-opt-out-of-my-input-or-output-data-being-used-for-training - Locator: Vibe, Team and Enterprise; separate API toggle - Evidence kind: documented - Source date: 2026-09-03 - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-commercial Commercial terms of service. Commercial terms apply to Vibe and reserve product IP, with conditional training permissions and feedback/Labs exceptions. - URL: https://legal.mistral.ai/terms/commercial-terms-of-service/ - Locator: 4 Training; 5 Rights; fees; regional governing law - 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 ### mistral-vibe:mistral-vibe:m-delete-20261026 Can I delete a chat conversation?. User-visible deletion is irreversible but backend copies can remain for legal, policy and monitoring purposes. - URL: https://help.mistral.ai/en/articles/347613-can-i-delete-a-chat-conversation - Locator: Manual deletion; backend retention; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 e5e32e605a4886b543b62a4efcbe743bcb55a66a560c26540fd49b38269172e5 on 2026-10-26 - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-dpa-20261026 Data Processing Addendum. The DPA defines GDPR processing, prior subprocessor notice with a 10-day objection period and loss of data access 30 days after termination. - URL: https://legal.mistral.ai/terms/data-processing-addendum/ - Locator: Definitions; subprocessors; 10 Return/destruction; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 b578ac8d9fbe2ccebf7a70e127c5b3052d24219c6195cf7ffb97a71d051552f7 on 2026-10-26 - Evidence kind: documented - Source date: 2026-07-27 - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-retention-20261026 How long is data stored?. Retention differs by data type; account identity, technical and invoicing records can outlast the user contract. - URL: https://help.mistral.ai/en/articles/347628-how-long-do-you-store-my-data - Locator: Account/technical/legal retention examples; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 2c1a0e2ffbc481905cedc6f24e4831034ae1eec0dfc566ceecbcf8633390f8fe on 2026-10-26 - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-26 ### 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 ### mistral-vibe:mistral-vibe:m-location-20261026 Where is data stored?. Mistral states default EU hosting with feature-dependent extra-EU transfers; some Enterprise features can be disabled to reduce transfers. - URL: https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data - Locator: EU default; feature transfers; Enterprise controls; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 6e6c908ef3d6f98376804f8bc0da9a4869329875eca81dff6fc211c329412509 on 2026-10-26 - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-dpa Data Processing Addendum. The DPA defines GDPR processing, prior subprocessor notice with a 10-day objection period and loss of data access 30 days after termination. - URL: https://legal.mistral.ai/terms/data-processing-addendum/ - Locator: Definitions; subprocessors; 10 Return/destruction - Evidence kind: documented - Source date: 2026-07-27 - Retrieved: 2026-10-21 ### mistral-vibe:mistral-vibe:m-cert SOC 2 and ISO certification help. Mistral claims SOC 2 Type II and ISO 27001/27701 and directs report requests to its Trust Center; underlying reports were not retrieved. - URL: https://help.mistral.ai/en/articles/347638-do-you-have-soc-2-or-iso-27001-certification - Locator: Claim and report-request path - Evidence kind: vendor-claimed - Source date: 2026-08-12 - 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 ### mistral-vibe:mistral-vibe:m-billing Billing. Billing supports prepaid credits, organizational limits and invoice downloads; API/Code credit exhaustion has documented failure behavior. - URL: https://docs.mistral.ai/admin/billing-usage/billing.md - Locator: Credits; 402 exhaustion; monthly spending limit - 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 ### mistral-vibe:mistral-vibe:fx-ecb ECB historical euro reference rates. EUR 1 equals USD 1.1215 and CHF 0.9237 on the agreed reference date. - 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: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 ### mistral-vibe:mistral-vibe:m-export-20261026 Export data from Vibe. The help article documents a personal-data download tool without specifying a complete admin migration package. - URL: https://help.mistral.ai/en/articles/347623-how-do-i-export-my-data-from-vibe - Locator: Personal-data export button; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 7720137dff42f992da58d1fb0285c3c3148aa82682a597c9d155968b53feba05 on 2026-10-26 - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-sheets-20261026 Spreadsheets. Paid Work supports spreadsheet generation/editing and downloadable XLSX output; fidelity requires testing. - URL: https://docs.mistral.ai/vibe/work/spreadsheets.md - Locator: Paid-plan availability; formulas; export; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 6d2da02b3a2bb619965459522efa076d818db859fc89ab6b7b652abb2a89476a on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### mistral-vibe:mistral-vibe:m-rename Le Chat is now Vibe. The August 12 notice renames Le Chat to Vibe while preserving accounts, plans and conversations. - URL: https://help.mistral.ai/en/articles/682992-le-chat-is-now-vibe - Locator: What changed; modes; account continuity - Evidence kind: documented - Source date: 2026-08-12 - Retrieved: 2026-10-21