--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/anythingllm-vs-librechat/" data_url: "https://onaihq.com/compare/agents/anythingllm-vs-librechat/data.json" generated_at: 2026-10-27 last_checked_at: 2026-10-26 last_cross_checked_at: 2026-10-26 next_check_at: 2026-12-20 publisher: "onAI" --- # AnythingLLM vs LibreChat > Published by onAI. onAI also sells one of the products compared here. Findings about other products link to public sources so you can check them; statements about onAI are marked as stated by onAI. This comparison has 44 criteria with sourced findings for both products, including 44 that a second agent cross-checked for both. 49 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. - AnythingLLM source checks: 2026-10-21 to 2026-10-26. - LibreChat source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/anythingllm-vs-librechat/ - Machine-readable JSON: https://onaihq.com/compare/agents/anythingllm-vs-librechat/data.json - Methodology: https://onaihq.com/compare/agents/methodology/ ## Models ### MOD-01: Model catalogue and providers Judgment rule: List each available model by provider and plan, including reasoning, fast and multimodal variants. Record whether the user picks the model, the product routes automatically, or both. A provider counts only if at least one of its current models is selectable on the scoped plan. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The customer selects provider/model combinations at system, workspace and Agent level; optional routing can choose per message. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - providers: Documented integrations include OpenAI, Azure, Anthropic, Google, Bedrock, Mistral, Cohere, OpenRouter, LiteLLM and local servers. Actual selectable models require configured accounts/endpoints; no endpoint was exercised. - current_models: Which current models are selectable on this plan? A complete current selectable-model catalog was not captured from configured provider accounts. - auto_routing: Model Router supports ordered rules and a fallback model, including LLM-classified rules. A complete chosen-model display/test was not established. - multimodal_input: System/workspace routes can accept image input with compatible models; exact audio/file and per-model behavior was not tested. - providers — Which model providers are available? [partial]: Documented integrations include OpenAI, Azure, Anthropic, Google, Bedrock, Mistral, Cohere, OpenRouter, LiteLLM and local servers. Actual selectable models require configured accounts/endpoints; no endpoint was exercised. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:llmconfig. - current_models — Which current models are selectable on this plan? [unknown]: current_models: Which current models are selectable on this plan? A complete current selectable-model catalog was not captured from configured provider accounts. - user_choice — Can users pick the model per chat? [supported]: System/workspace/Agent selections are configurable; the current built-in provider also has a chat model picker. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:built-in. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [partial]: Model Router supports ordered rules and a fallback model, including LLM-classified rules. A complete chosen-model display/test was not established. Sources: anythingllm:anythingllm:router. - multimodal_input — Which models accept images, audio or files? [partial]: System/workspace routes can accept image input with compatible models; exact audio/file and per-model behavior was not tested. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:constants-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:built-in, anythingllm:anythingllm:router, anythingllm:anythingllm:constants-pin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The model catalog is configured by the customer across first-party provider integrations and custom endpoints. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - providers: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. - current_models: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. - auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. - providers — Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - current_models — Which current models are selectable on this plan? [partial]: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. Sources: librechat:librechat:releases. - user_choice — Can users pick the model per chat? [supported]: Users choose an endpoint/model unless admins enforce model specs or a fixed Agent. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [unknown]: auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input — Which models accept images, audio or files? [partial]: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. Sources: librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr ### MOD-02: Model freshness Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated releases and version-specific changelogs are public, but the three-release lag benchmark was not measured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No paired last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted. - deprecation_notice: How much notice is given before a model is removed? No paired last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted. - version_pinning: Operators choose remote model IDs or download local GGUF models. Provider retention of old remote snapshots is outside the application’s 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 last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted. - changelog — Is there a dated public model changelog? [supported]: GitHub releases and Desktop changelogs document dated changes; v1.18.0 was published 2026-10-13. Sources: anythingllm:anythingllm:releases, anythingllm:anythingllm:changelog. - 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 last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted. - version_pinning — Can an admin keep an older model version? [partial]: Operators choose remote model IDs or download local GGUF models. Provider retention of old remote snapshots is outside the application’s control. Sources: anythingllm:anythingllm:generic, anythingllm:anythingllm:built-in. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:releases, anythingllm:anythingllm:changelog, anythingllm:anythingllm:generic, anythingllm:anythingllm:built-in #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - changelog — Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases. - deprecation_notice — How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning — Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom ### MOD-03: Bring-your-own keys and provider contracts Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial BYO provider keys, customer cloud contracts and generic compatible endpoints are documented; provider spend is separate from software licensing. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - byo_restrictions: Tool use and modalities depend on provider/model support; Cloud has additional explicit platform limits. No universal BYO feature-parity guarantee was established. - own_api_keys — Can the customer use its own provider API keys? [supported]: Customers configure credentials for their selected cloud providers. Managed Cloud also asks customers to bring an LLM API key. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Azure OpenAI, AWS Bedrock and Vertex have distinct documented configuration routes using customer accounts. Sources: anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Generic OpenAI supports an operator-configured compatible provider URL and settings. Sources: anythingllm:anythingllm:generic. - byo_pricing — Does BYO change the licence price? [supported]: The self-hosted repository is MIT with no per-seat fee; customer provider/hosting costs remain separate. Cloud charges for the managed instance and still uses BYO inference. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud. - byo_restrictions — Which features stop working with BYO? [partial]: Tool use and modalities depend on provider/model support; Cloud has additional explicit platform limits. No universal BYO feature-parity guarantee was established. Sources: anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:models. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud, anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex, anythingllm:anythingllm:generic, anythingllm:anythingllm:license, anythingllm:anythingllm:cloud-limits #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. - own_api_keys — Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom. - byo_pricing — Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat. - byo_restrictions — Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code ### MOD-04: Local and self-hosted models Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local chat and local CPU embeddings are documented; built-in-engine availability differs by client and release. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - feature_parity: Chat/RAG are local-capable, but tools and vision depend on model support and optional online services. Cloud explicitly has no bundled built-in LLM. No full offline fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? No vendor-hosted open-weight model service with verified EU/Swiss inference was established. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Ollama and other local providers work as configured endpoints. Desktop’s current built-in engine uses Lemonade/llama.cpp; Docker built-in is opt-in on the latest images and releases after v1.18.0 according to current docs. Sources: anythingllm:anythingllm:ollama, anythingllm:anythingllm:built-in. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: The built-in all-MiniLM-L6-v2 embedder runs locally on CPU; other local embedding routes are configurable. Sources: anythingllm:anythingllm:local-embed, anythingllm:anythingllm:embed. - feature_parity — Which features fail with self-hosted models? [partial]: Chat/RAG are local-capable, but tools and vision depend on model support and optional online services. Cloud explicitly has no bundled built-in LLM. No full offline fixture was run. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:built-in. - 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? No vendor-hosted open-weight model service with verified EU/Swiss inference was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:ollama, anythingllm:anythingllm:built-in, anythingllm:anythingllm:local-embed, anythingllm:anythingllm:embed, anythingllm:anythingllm:models, anythingllm:anythingllm:cloud-limits #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg. - feature_parity — Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code. - vendor_hosted_open_models — Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code ### MOD-05: Model control and usage limits Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspace models and admin roles control settings; non-admin multi-user message quotas have a source-inspected blocking path. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - model_allowlist_by_group: Can admins limit models per group? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run. - data_bound_models: Can admins restrict which models receive connector or knowledge content? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run. - model_allowlist_by_group — Can admins limit models per group? [unknown]: model_allowlist_by_group: Can admins limit models per group? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run. - 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 group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run. - default_model — Can admins set the default model? [supported]: The system LLM is the default, overridden by workspace and Agent model configuration. Sources: anythingllm:anythingllm:llmconfig. - user_limits — What per-user message or token limits apply, and are they published? [supported]: A dailyMessageLimit may be set per user, is system-wide across workspaces, uses a trailing 24-hour count and exempts admins; null means no limit in the inspected function. Sources: anythingllm:anythingllm:user-pin. - limit_behaviour — What happens when a limit is reached? [supported]: Pinned chat endpoints send an abort/quota message and return before generation when the user cannot send another chat. Sources: anythingllm:anythingllm:chat-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:user-pin, anythingllm:anythingllm:chat-pin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. - data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. - model_allowlist_by_group — Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - default_model — Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec. - user_limits — What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod. - limit_behaviour — What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin ## Company knowledge ### KNOW-01: Files in chat Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Files can enter full context or workspace RAG; converters and a PDF OCR fallback are present, with fidelity untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - limits: What size and count limits apply per file and chat? No universal file/count limit was established across these deployments. Cloud documents CPU/memory limits, but they do not define a tested per-file allowance. Shared long/scanned/Excel/PowerPoint fixtures were not uploaded. - ocr: The PDF implementation attempts OCR when initial text extraction returns no pages. No scanned contract or mixed-content PDF was tested. - spreadsheets: XLSX conversion is registered and v1.18.0 reports spreadsheet parsing fixes; preservation of formula semantics and layout was not tested. - formats — Which formats are accepted? [supported]: Pinned converters register PDF, DOCX, PPTX, XLSX, EPUB, text/CSV/JSON, image and audio formats. Legacy DOC is not in the active registered converter map. Sources: anythingllm:anythingllm:constants-pin. - limits — What size and count limits apply per file and chat? [unknown]: limits: What size and count limits apply per file and chat? No universal file/count limit was established across these deployments. Cloud documents CPU/memory limits, but they do not define a tested per-file allowance. Shared long/scanned/Excel/PowerPoint fixtures were not uploaded. - ocr — Are scanned PDFs read? [partial]: The PDF implementation attempts OCR when initial text extraction returns no pages. No scanned contract or mixed-content PDF was tested. Sources: anythingllm:anythingllm:pdf-pin. - spreadsheets — Are Excel tables read with structure intact? [partial]: XLSX conversion is registered and v1.18.0 reports spreadsheet parsing fixes; preservation of formula semantics and layout was not tested. Sources: anythingllm:anythingllm:constants-pin, anythingllm:anythingllm:changelog. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: Current attachment mode injects full extracted text. On context overflow the UI offers cancellation, pruning or embedding; embedded documents retrieve chunks and become workspace-wide. Sources: anythingllm:anythingllm:docchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:constants-pin, anythingllm:anythingllm:pdf-pin, anythingllm:anythingllm:changelog, anythingllm:anythingllm:docchat #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Files can be indexed, injected as extracted text or sent directly to compatible model providers. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - File counts, sizes and provider acceptance depend on deployment settings. - Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested. - formats — Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg. - limits — What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr. - ocr — Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr. - spreadsheets — Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current ### KNOW-02: Knowledge bases and shared collections Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspace embeddings persist across chats and are shared with every authorized workspace user. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - size_limits: What are the collection limits? No fixed collection storage allowance was established; capacity depends on local hardware or managed-instance tier. - persistent_collections — Can users keep document collections across chats? [supported]: Embedding a document into a workspace makes it reusable across that workspace’s threads. Sources: anythingllm:anythingllm:docchat. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [supported]: In Docker multi-user mode, assigned workspace users can use its embedded documents. Admin/Manager roles have broader access; per-original-source ACLs were not established. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:security. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No fixed collection storage allowance was established; capacity depends on local hardware or managed-instance tier. - assistant_binding — Can collections be bound to an assistant? [supported]: Each workspace has configurable chat/Agent models and its embedded knowledge. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:docchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:security, anythingllm:anythingllm:llmconfig #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. - size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - persistent_collections — Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - assistant_binding — Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr ### KNOW-03: Enterprise connectors Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02). #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The source registers import connectors and SQL tools. Mail integrations are single-user features, not verified enterprise multi-user content search. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Source-specific credentials/registrations, Mail skills require single-user mode; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - microsoft_365: An Outlook skill searches/reads/modifies the connected mailbox, but is explicitly single-user only. SharePoint, OneDrive and Teams connectors were not verified for the multi-user deployment. - google_workspace: The Gmail skill is single-user only. A maintained Google Drive enterprise connector and source ACL sync were not verified. - atlassian: The pinned connector catalog includes Confluence import. Jira was not established and Confluence per-user permission synchronization was not tested. - other_systems: The connector catalog includes GitHub/GitLab/Gitea, websites, YouTube, Obsidian and other import sources; registration does not establish tested source access controls. - on_prem_sources: Self-hosted deployments can upload files and connect the SQL Agent to a reachable database. Automatic local-file watching is Desktop-only, not Docker browser upload. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: An Outlook skill searches/reads/modifies the connected mailbox, but is explicitly single-user only. SharePoint, OneDrive and Teams connectors were not verified for the multi-user deployment. Sources: anythingllm:anythingllm:outlook. - google_workspace — Which Google sources are connected? [partial]: The Gmail skill is single-user only. A maintained Google Drive enterprise connector and source ACL sync were not verified. Sources: anythingllm:anythingllm:gmail. - atlassian — Confluence and Jira? [partial]: The pinned connector catalog includes Confluence import. Jira was not established and Confluence per-user permission synchronization was not tested. Sources: anythingllm:anythingllm:connectors-pin, anythingllm:anythingllm:sync. - other_systems — Which other business systems? [partial]: The connector catalog includes GitHub/GitLab/Gitea, websites, YouTube, Obsidian and other import sources; registration does not establish tested source access controls. Sources: anythingllm:anythingllm:connectors-pin. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Self-hosted deployments can upload files and connect the SQL Agent to a reachable database. Automatic local-file watching is Desktop-only, not Docker browser upload. Sources: anythingllm:anythingllm:sql, anythingllm:anythingllm:sync, anythingllm:anythingllm:localdocker. - connector_provider — Who builds and maintains each connector? [supported]: These are built-in Mintplex project skills/import modules; third-party MCP servers remain separately maintained integrations. Sources: anythingllm:anythingllm:connectors-pin, anythingllm:anythingllm:outlook, anythingllm:anythingllm:gmail, anythingllm:anythingllm:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:outlook, anythingllm:anythingllm:gmail, anythingllm:anythingllm:connectors-pin, anythingllm:anythingllm:sync, anythingllm:anythingllm:sql, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:mcp #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. - google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint. - google_workspace — Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian — Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems — Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg. - connector_provider — Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp ### KNOW-04: Permission-aware retrieval Judgment rule: Using two test users, verify that a restricted document in the fixture tenant is never cited or summarised for the user without access, including after a permission change. Record whether permissions are enforced at query time by the source system, mirrored into an index, or not enforced. Record the propagation delay of a revocation. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspace access is enforced as the product sharing boundary; original source permissions after copying remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown. - enforcement_point: Default users only access assigned workspaces, and an embedded file becomes available to every user assigned to its workspace. Continuing source-system ACL checks were not established. - revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown. - admin_scope_controls: Admins control workspace membership and selected documents. Source site/folder/sensitivity-label exclusion was not established. - sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown. - 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 propagation test was run. Purview label enforcement and source ACL fidelity remain unknown. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: Default users only access assigned workspaces, and an embedded file becomes available to every user assigned to its workspace. Continuing source-system ACL checks were not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat. - 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 propagation test was run. Purview label enforcement and source ACL fidelity remain unknown. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Admins control workspace membership and selected documents. Source site/folder/sensitivity-label exclusion was not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat. - 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 propagation test was run. Purview label enforcement and source ACL fidelity remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Product resource ACLs and delegated Microsoft file selection are documented. Continuing source permissions for copied content remain untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - enforcement_point: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. - revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - admin_scope_controls: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. - sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - source_permissions_respected — Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. Sources: librechat:librechat:access, librechat:librechat:sharepoint. - revocation_delay — How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. Sources: librechat:librechat:access, librechat:librechat:agents. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:sharepoint, librechat:librechat:agents ### KNOW-05: Freshness and sync model Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Knowledge is a copied index. Automatic source refresh is preview and differs between remote sources and Desktop local files. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Live document sync preview explicitly enabled for automatic refresh; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - Automatic sync is a preview, not a guaranteed freshness SLA. - No source edit/delete timing fixture was run. - live_or_indexed — Is content searched live or copied into an index? [supported]: Embedded knowledge copies parsed chunks into the selected vector store; attachments instead inject extracted text. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:vector. - sync_interval — How often does an index refresh? [partial]: Preview watched remote sources are checked hourly for staleness, defined as no refresh in seven days; Desktop local watched files are checked every ten minutes while running. No latency fixture was run. Sources: anythingllm:anythingllm:sync. - deletion_propagation — How quickly does a deleted document disappear? [partial]: Deleting a watched local original marks it Not Found and unwatches it while retaining existing content/embeddings. System deletion must be explicit; remote-source deletion timing was not established. Sources: anythingllm:anythingllm:sync, anythingllm:anythingllm:privacy. - index_location — Where is indexed content stored? [supported]: Self-hosting selects the configured local or external vector store and its country. Default local storage is distinct from any selected cloud database. Sources: anythingllm:anythingllm:vector, anythingllm:anythingllm:localdocker. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:vector, anythingllm:anythingllm:sync, anythingllm:anythingllm:privacy, anythingllm:anythingllm:localdocker #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - live_or_indexed — Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr. - sync_interval — How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - index_location — Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin ### KNOW-06: Grounding and retrieval quality Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The client renders source citations and Query mode documents a no-relevant-content response; quality is untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained. - cross_language: Does a question in one language find documents in another? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained. - no_answer_behaviour: Query mode documentation says it reports when no relevant information is found. This is documented behavior, not a passed no-answer fixture. - observed_accuracy: How many of the question set were answered correctly? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained. - citations — Are answers linked to specific sources? [supported]: Pinned client code renders document/link citation details and source metadata. Sources: anythingllm:anythingllm:citation-pin. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained. - 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 DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained. - no_answer_behaviour — Does it say when the corpus has no answer? [partial]: Query mode documentation says it reports when no relevant information is found. This is documented behavior, not a passed no-answer fixture. Sources: anythingllm:anythingllm:chatmodes. - 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 DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:citation-pin, anythingllm:anythingllm:chatmodes #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial File-search citations are documented; retrieval accuracy remains unmeasured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - citations — Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language — Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy — How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access ### KNOW-07: Memory and personal context Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: supported Opt-in personalization stores private global/workspace memories with user controls and admin enablement. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Workspaces keep model/system instructions and may include user/time variables. Sources: anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig. - cross_chat_memory — Does the product remember facts across chats? [supported]: User memories apply across chats within a workspace or globally; limits are 20 workspace and five global memories per user. Sources: anythingllm:anythingllm:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users can add, edit, delete and move memories; selected memories are sent to the configured model in the system prompt. Sources: anythingllm:anythingllm:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Memories are off by default; in multi-user mode only admins enable/disable personalization. Sources: anythingllm:anythingllm:memory. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:memory #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents. - cross_chat_memory — Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access ## Assistants and agents ### AGT-01: Custom assistants Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspaces combine instructions, a model, knowledge and configured Agent skills; a distinct shareable assistant object/catalog was not fully established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - creator_permissions: Admin/Manager roles manage workspaces; Default users only chat in assigned workspaces. A separate assistant-creator permission matrix was not established. - sharing_scope: Docker workspaces can be assigned to users; Desktop is single-user. Group/everyone assistant-sharing and versioned assistant publishing were not established. - catalogue: Is there an internal assistant directory? A complete internal assistant directory/versioning contract and the HR assistant fixture were not verified. - prompt_library: Workspace prompts and no-code Agent Flows can be reused, but a separate organization prompt-template catalog was not verified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: Workspace and Agent settings combine a model, instructions, embedded knowledge and enabled skills/tools. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:docchat. - creator_permissions — Can admins limit who creates them? [partial]: Admin/Manager roles manage workspaces; Default users only chat in assigned workspaces. A separate assistant-creator permission matrix was not established. Sources: anythingllm:anythingllm:security. - sharing_scope — Can assistants be shared with users, groups or everyone? [partial]: Docker workspaces can be assigned to users; Desktop is single-user. Group/everyone assistant-sharing and versioned assistant publishing were not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:desktop. - catalogue — Is there an internal assistant directory? [unknown]: catalogue: Is there an internal assistant directory? A complete internal assistant directory/versioning contract and the HR assistant fixture were not verified. - prompt_library — Are shared prompt templates available? [partial]: Workspace prompts and no-code Agent Flows can be reused, but a separate organization prompt-template catalog was not verified. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:systemprompt. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:docchat, anythingllm:anythingllm:security, anythingllm:anythingllm:desktop, anythingllm:anythingllm:flow, anythingllm:anythingllm:systemprompt #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents. - creator_permissions — Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access. - catalogue — Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents. - prompt_library — Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access ### AGT-02: Tools, actions and MCP Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosted/desktop supports built-in skills, API-call flows and MCP. Managed Cloud explicitly excludes custom coded Agents and MCP. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Separate MCP servers or custom skill configuration, Mail integrations require single-user mode; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - Cloud does not support MCP or custom coded Agents. - Single-user mail approvals do not establish a complete multi-user side-effect policy. - builtin_tools — Which tools are built in? [supported]: Skills include RAG/document search, web browsing, chart/document generation and SQL; single-user mail skills have a narrower scope. Sources: anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:sql, anythingllm:anythingllm:docgen, anythingllm:anythingllm:chart, anythingllm:anythingllm:outlook. - custom_actions — Can admins add API actions? [supported]: No-code flows provide an API-call block and custom skills can be developed for self-hosted/desktop; Cloud excludes custom coded Agents. Sources: anythingllm:anythingllm:flow-api, anythingllm:anythingllm:cloud-limits. - mcp_client — Can it use remote MCP servers, and with what admin control? [partial]: Self-hosted/desktop supports stdio, SSE and Streamable remote MCP with management controls. Managed Cloud explicitly does not support MCP. Sources: anythingllm:anythingllm:mcp, anythingllm:anythingllm:cloud-limits. - tool_auth — Do tools act as the user or as a shared account? [partial]: MCP accepts environment variables/HTTP headers; single-user Outlook uses delegated Entra authorization. A general per-user OAuth model for every multi-user tool was not established. Sources: anythingllm:anythingllm:mcp, anythingllm:anythingllm:outlook. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Outlook/Gmail modifying actions explicitly require approval in single-user mode. A mandatory approval policy for every custom/MCP action was not verified. Sources: anythingllm:anythingllm:outlook, anythingllm:anythingllm:gmail, anythingllm:anythingllm:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:sql, anythingllm:anythingllm:docgen, anythingllm:anythingllm:chart, anythingllm:anythingllm:outlook, anythingllm:anythingllm:flow-api, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:mcp, anythingllm:anythingllm:gmail #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. - builtin_tools — Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images. - custom_actions — Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_auth — Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code ### AGT-03: Web search and deep research Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The web-browsing skill supports explicit search-provider configuration. This claim covers the pinned self-hosted DuckDuckGo route; it makes no assertion about an unconfigured default. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Self-hosted v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, explicitly configured agent_search_provider=duckduckgo-engine; plan=MIT self-hosted deployment with an explicitly selected DuckDuckGo provider; auto-selected defaults, Desktop and managed Cloud defaults are outside this claim; add_ons=Enabled web-browsing skill; explicit agent_search_provider=duckduckgo-engine setting; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - The scope is an explicitly configured provider at one release pin, not an assertion about default routing in other installations. - Search queries leave the application for the selected external endpoint; processing region and a per-group enforcement fixture were not established. - Dedicated research-report quality and citation completeness remain untested. - web_search — Is web search available? [supported]: The Agent web-browsing skill can search the web; this scoped self-hosted configuration explicitly selects the DuckDuckGo engine. Sources: anythingllm:anythingllm:browsing, anythingllm:anythingllm:search-configured-r2. - admin_toggle — Can admins disable it per organisation or group? [partial]: The documented Agent Skills settings and chat prompt controls toggle skills. Separate per-group web-search enforcement under the standard role model was not established. Sources: anythingllm:anythingllm:agent-skills-r2, anythingllm:anythingllm:security. - search_provider — Which search provider handles queries, and where? [partial]: At the pinned v1.18.0 revision, explicit agent_search_provider=duckduckgo-engine invokes _duckDuckGoEngine and sends the query to html.duckduckgo.com/html. Query processing country and a CH/EU residency commitment were not verified. Unconfigured defaults are outside this finding. Sources: anythingllm:anythingllm:search-configured-r2. - deep_research — Is multi-step research with a report available? [partial]: Agent tools/flows can chain research steps; a dedicated tested report workflow and accuracy result were not established. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:agent-usage. - web_citations — Are web sources cited? [partial]: The client renders source citations including links; correctness and completeness of web-source citations were not tested. Sources: anythingllm:anythingllm:citation-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:browsing, anythingllm:anythingllm:search-configured-r2, anythingllm:anythingllm:agent-skills-r2, anythingllm:anythingllm:security, anythingllm:anythingllm:flow, anythingllm:anythingllm:agent-usage, anythingllm:anythingllm:citation-pin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. - web_search — Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents. - admin_toggle — Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web. - search_provider — Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web. - deep_research — Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web. - web_citations — Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access ### AGT-04: Workflows and automation Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial No-code Agent Flows are available on Docker/Desktop. Scheduled Jobs are explicitly single-user only. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Scheduled Jobs require single-user mode; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - scheduled_tasks: Scheduled Jobs run recurring Agent prompts with cron, tool allow-lists and saved traces in single-user mode. They are unavailable in self-hosted multi-user mode. - event_triggers: Can external events start a workflow? A maintained incoming email/form/business-system event-trigger contract was not established; an API call alone is not a named trigger integration. - workflow_builder — Is there a workflow or chain builder? [supported]: The visual flow editor builds reusable agentic skills with steps such as API calls, scraping and file operations. Sources: anythingllm:anythingllm:flow. - scheduled_tasks — Can prompts or assistants run on a schedule? [partial]: Scheduled Jobs run recurring Agent prompts with cron, tool allow-lists and saved traces in single-user mode. They are unavailable in self-hosted multi-user mode. Sources: anythingllm:anythingllm:job. - event_triggers — Can external events start a workflow? [unknown]: event_triggers: Can external events start a workflow? A maintained incoming email/form/business-system event-trigger contract was not established; an API call alone is not a named trigger integration. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Flows target non-coders; custom skill code targets technical users and developers. Sources: anythingllm:anythingllm:flow. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:job #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. - event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. - workflow_builder — Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule. - event_triggers — Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api ### AGT-05: Agentic task execution Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof. #### AnythingLLM Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - No gather-documents, draft-summary and propose-email task was run. - Highly experimental attached workspaces are distinct from ordinary Agent tool use. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code. - visible_steps — Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code. - stop_control — Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases ### AGT-06: Programmable access Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Instance APIs manage workspaces, upload/embed content and run chats using provisioned API keys. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - api_governance: API keys are provisioned by authorized accounts and confer access to their holder. Full UI/API quota, model, audit and per-user boundary parity was not tested. - mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established from the client-MCP and API guides. - chat_api — Is there an API for chat and assistants? [supported]: The documented developer API supports workspace management and chat, with instance OpenAPI docs at /api/docs. Sources: anythingllm:anythingllm:api. - knowledge_api — Can documents be loaded through an API? [supported]: The developer API documents embedding/document management alongside workspace operations. Sources: anythingllm:anythingllm:api. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: API keys are provisioned by authorized accounts and confer access to their holder. Full UI/API quota, model, audit and per-user boundary parity was not tested. Sources: anythingllm:anythingllm:api, anythingllm:anythingllm:config. - 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 from the client-MCP and API guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:api, anythingllm:anythingllm:config #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. - api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. - mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. - chat_api — Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api. - knowledge_api — Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access ## Daily work ### WORK-01: Clients and access points Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Docker serves a browser client, Desktop has native installers and Mobile is Android-only; these are different access/governance modes. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Mobile for Android, AnythingLLM browser content collection extension; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=Windows, macOS, Linux, Android. Limitations: - mobile_apps: A separate free Android app can run local models or pair with Desktop/Cloud/self-hosted servers. iOS and a tested native company-SSO flow were not established. - managed_deployment: Windows silent installer switches are documented for scripted/MDM packaging. Current User install is required; all-users install is unsupported and Enterprise/Server OS use has caveats. No Intune deployment was tested. - web — Is a full web client available? [supported]: Docker provides the browser-accessible multi-user UI; Desktop network discovery exposes API endpoints rather than a web UI. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:docker. - desktop_apps — Windows and macOS apps? [supported]: Desktop installers support Windows, macOS and Linux; the app is single-user rather than a shared company-login client. Sources: anythingllm:anythingllm:desktop. - mobile_apps — iOS and Android apps with SSO? [partial]: A separate free Android app can run local models or pair with Desktop/Cloud/self-hosted servers. iOS and a tested native company-SSO flow were not established. Sources: anythingllm:anythingllm:mobile. - browser_extension — Is there a browser extension or sidebar? [supported]: A content collection extension supports Chrome/Edge/Brave/Firefox and connects with an instance API key. Sources: anythingllm:anythingllm:ext. - managed_deployment — Can IT deploy and configure clients through MDM? [partial]: Windows silent installer switches are documented for scripted/MDM packaging. Current User install is required; all-users install is unsupported and Enterprise/Server OS use has caveats. No Intune deployment was tested. Sources: anythingllm:anythingllm:windows. - client_feature_gaps — Which features are missing on mobile? [supported]: Desktop lacks multi-user/workspace administration; Android is a separate local/pairing client; Desktop-only meeting features currently target Windows/macOS. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:mobile, anythingllm:anythingllm:meeting-intro. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:docker, anythingllm:anythingllm:mobile, anythingllm:anythingllm:ext, anythingllm:anythingllm:windows, anythingllm:anythingllm:meeting-intro #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. - browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. - web — Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local. - desktop_apps — Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps — iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights. - browser_extension — Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps — Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights ### WORK-02: Office suite and Teams integration Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02. #### AnythingLLM Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### WORK-03: Translation and writing Judgment rule: Record document translation preserving layout, the translation engine (LLM or dedicated such as DeepL), glossaries, formality control, supported languages including Swiss German conventions (no ß), and rewriting/proofreading tools. Translate the shared German contract into French and Italian and record layout and glossary results. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Desktop Magic tools support system-wide rewriting, but layout-preserving translation and company glossary controls remain unverified. Availability: generally-available Delivery: native Scope: surfaces=AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=Desktop free Magic allowances; optional Desktop Pro; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=Windows, macOS. Limitations: - document_translation: Can whole documents be translated with formatting kept? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified. - translation_engine: Generative rewrite work uses the selected model. A dedicated document translation engine/workflow was not established. - glossaries: Are company glossaries supported? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified. - formality_and_variants: Can formality and regional variants (de-CH) be set? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified. - document_translation — Can whole documents be translated with formatting kept? [unknown]: document_translation: Can whole documents be translated with formatting kept? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified. - translation_engine — Which engine translates? [partial]: Generative rewrite work uses the selected model. A dedicated document translation engine/workflow was not established. Sources: anythingllm:anythingllm:pro, anythingllm:anythingllm:llmconfig. - glossaries — Are company glossaries supported? [unknown]: glossaries: Are company glossaries supported? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: formality_and_variants: Can formality and regional variants (de-CH) be set? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified. - writing_tools — Are dedicated rewrite and proofreading tools available? [supported]: Desktop Magic Echo/Beacon/Tab offer dictation cleanup, selected-text revision and writing completion, with free allowances and optional Desktop Pro. Sources: anythingllm:anythingllm:pro. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:pro, anythingllm:anythingllm:llmconfig #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### WORK-04: Image generation and editing Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured image providers generate pictures and can edit references where supported. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - image_editing: OpenAI/OpenRouter and compatible Lemonade models use reference-image editing. The documented Ollama route drops image references and generates from text only. - admin_control: Admins configure provider credentials and model. A separate per-group image-generation cost/permission policy was not established. - usage_terms: What usage rights apply to output? Output rights and complete per-image cost visibility depend on the model/provider contract and were not established here. - image_generation — Can users generate images, with which models? [supported]: The /img command uses configured OpenAI, OpenRouter, Ollama or Lemonade providers and an operator-selected model. Sources: anythingllm:anythingllm:images. - image_editing — Can users edit uploaded images? [partial]: OpenAI/OpenRouter and compatible Lemonade models use reference-image editing. The documented Ollama route drops image references and generates from text only. Sources: anythingllm:anythingllm:images. - admin_control — Can admins restrict image generation? [partial]: Admins configure provider credentials and model. A separate per-group image-generation cost/permission policy was not established. Sources: anythingllm:anythingllm:images, anythingllm:anythingllm:security. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Output rights and complete per-image cost visibility depend on the model/provider contract and were not established here. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:images, anythingllm:anythingllm:security #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured Agent image tools generate and edit images; model service rights/costs remain separate. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. - usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. - image_generation — Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images. - image_editing — Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images. - admin_control — Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access ### WORK-05: Voice and meetings Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Audio transcription/read-aloud are configurable. Free meeting capture and local transcription are Desktop-only on Windows/macOS. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Desktop-only Meeting Assistant; downloaded transcription models, Optional provider-specific audio services; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - dictation: Transcription providers and Desktop Magic Echo support spoken input; exact supported dialects and a shared dictation fixture were not verified. - voice_conversation: Is a live voice mode available? No continuous live conversational voice mode or Swiss German recognition quality was verified. - swiss_german_speech: Is Swiss German speech recognised? No continuous live conversational voice mode or Swiss German recognition quality was verified. - dictation — Can users dictate prompts? [partial]: Transcription providers and Desktop Magic Echo support spoken input; exact supported dialects and a shared dictation fixture were not verified. Sources: anythingllm:anythingllm:stt, anythingllm:anythingllm:pro. - read_aloud — Can answers be read aloud? [supported]: System-native, local/browser Piper, self-hosted Kokoro and cloud TTS routes are documented; the chosen engine determines processing. Sources: anythingllm:anythingllm:tts. - voice_conversation — Is a live voice mode available? [unknown]: voice_conversation: Is a live voice mode available? No continuous live conversational voice mode or Swiss German recognition quality was verified. - meeting_summaries — Are meetings transcribed and summarised? [supported]: Desktop Meeting Assistant records/imports meetings, transcribes locally and summarizes with the chosen local/cloud model. A cloud summary sends the transcript to that provider; Linux is not currently supported. Sources: anythingllm:anythingllm:meeting-intro, anythingllm:anythingllm:meeting. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: swiss_german_speech: Is Swiss German speech recognised? No continuous live conversational voice mode or Swiss German recognition quality was verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:stt, anythingllm:anythingllm:pro, anythingllm:anythingllm:tts, anythingllm:anythingllm:meeting-intro, anythingllm:anythingllm:meeting #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified. Limitations: - Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified. - Audio location depends on the chosen engine. No meeting or Swiss German fixture was run. - dictation — Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech. - read_aloud — Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech. - voice_conversation — Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2 ### WORK-06: Data analysis and document output Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Built-in Agent skills generate charts and downloadable Office/PDF documents; executed spreadsheet analysis and iterative canvas editing were not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - data_analysis: Can it analyse spreadsheets with executed code? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter. - canvas_editing: Is there a document or canvas editor for iterating on output? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter. - data_analysis — Can it analyse spreadsheets with executed code? [unknown]: data_analysis: Can it analyse spreadsheets with executed code? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter. - charts — Can it produce charts? [supported]: An enabled chart skill creates charts from prompts or workspace data. Sources: anythingllm:anythingllm:chart. - office_file_output — Can it create Word, Excel or PowerPoint files? [supported]: The built-in Document Generation skill lists text, PDF, Excel, DOCX and PowerPoint outputs; the guide recommends capable models for PowerPoint. Sources: anythingllm:anythingllm:docgen. - canvas_editing — Is there a document or canvas editor for iterating on output? [unknown]: canvas_editing: Is there a document or canvas editor for iterating on output? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:chart, anythingllm:anythingllm:docgen #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. - office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. - canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code. - charts — Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts ### WORK-07: Sharing and team spaces Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Docker workspaces share knowledge with assigned users; shared live conversation behavior remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - share_chats: Can chats be shared inside the organisation? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides. - group_chat: Can several people chat together with the AI? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides. - share_permission_boundary: Embedded files become accessible to every assigned workspace user; this does not preserve an arbitrary original source ACL. A cross-group chat-sharing fixture was not run. - share_chats — Can chats be shared inside the organisation? [unknown]: share_chats: Can chats be shared inside the organisation? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides. - team_spaces — Are shared projects or workspaces available? [supported]: Multi-user workspaces can be assigned to users, who share the embedded knowledge available there. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat. - group_chat — Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Embedded files become accessible to every assigned workspace user; this does not preserve an arbitrary original source ACL. A cross-group chat-sharing fixture was not run. Sources: anythingllm:anythingllm:docchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. - share_chats — Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share. - team_spaces — Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects. - group_chat — Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects ### WORK-08: Interface languages and accessibility Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned frontend registers English, German, French and Italian, with fallback behavior; translation quality and WCAG conformance remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New code findings at v1.19.0 / 9b1fcab141000eaba9f78ed131151de04904454b (published 2026-10-26); earlier accepted facts retain their own pins; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - German administrator labels are present in pinned source; full German/French/Italian screen coverage and naturalness were not observed. - No WCAG conformance statement or full accessibility walkthrough was verified. - ui_languages — Which UI languages are offered? [supported]: The locale implementation registers en, de, fr and it among other resources. Sources: anythingllm:anythingllm: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 full DE/FR/IT UI walkthrough, German admin-screen completeness review or WCAG conformance report was verified. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No full DE/FR/IT UI walkthrough, German admin-screen completeness review or WCAG conformance report was verified. - admin_ui_languages — Is the admin interface available in German? [partial]: The pinned German locale includes user management, invitations, event logs and administrator settings labels. Complete admin-screen coverage, translation quality and WCAG conformance were not observed. Sources: anythingllm:anythingllm:r4-german-admin. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: anythingllm:anythingllm:i18n-pin, anythingllm:anythingllm:r4-german-admin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial English, German, French and Italian UI resources are registered in the pinned client; quality and accessibility conformance were not evaluated. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - ui_languages — Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages — Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin ## Administration and governance ### ADM-01: Single sign-on and authentication Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The standard Docker project documents a privileged simple-SSO passthrough; the commercial Enterprise offer advertises SSO without public protocol details. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Custom trusted login integration for Simple SSO, Quote-only Enterprise for the advertised SSO offer; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - sso_protocols: Simple SSO generates one-use temporary links for existing users through an API key. It is not evidence of built-in SAML/OIDC/LDAP federation; those protocol details were not verified. - sso_plan: Simple passthrough is documented for self-hosted multi-user mode. Quote-only Enterprise separately advertises SSO, with public protocol/feature scope unspecified. - mfa: Can MFA be enforced? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer. - conditional_access: Do Entra conditional-access policies apply? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer. - domain_capture: Can the company claim its email domain? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer. - sso_protocols — Which SSO protocols and identity providers work? [partial]: Simple SSO generates one-use temporary links for existing users through an API key. It is not evidence of built-in SAML/OIDC/LDAP federation; those protocol details were not verified. Sources: anythingllm:anythingllm:config. - sso_plan — Which plan includes SSO? [partial]: Simple passthrough is documented for self-hosted multi-user mode. Quote-only Enterprise separately advertises SSO, with public protocol/feature scope unspecified. Sources: anythingllm:anythingllm:config, anythingllm:anythingllm:cloud. - mfa — Can MFA be enforced? [unknown]: mfa: Can MFA be enforced? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer. - conditional_access — Do Entra conditional-access policies apply? [unknown]: conditional_access: Do Entra conditional-access policies apply? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:config, anythingllm:anythingllm:cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. - domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth. - sso_plan — Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth. - mfa — Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth. - conditional_access — Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra ### ADM-02: User provisioning and lifecycle Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admins or API clients create users and assign workspaces; provisioning standards and leaver asset transfer remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - scim: Is SCIM provisioning supported? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer. - group_sync: Are identity-provider groups synced? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer. - jit_provisioning: Simple SSO explicitly requires a user to exist before login; an external system can create the user through the API. This is custom provisioning, not a verified automatic IdP JIT flow. - deprovisioning: Admin routes implement user deletion and log the event. A fixture verifying chat/knowledge ownership transfer and active-session revocation was not run. - scim — Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer. - group_sync — Are identity-provider groups synced? [unknown]: group_sync: Are identity-provider groups synced? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer. - jit_provisioning — Are users created at first login? [partial]: Simple SSO explicitly requires a user to exist before login; an external system can create the user through the API. This is custom provisioning, not a verified automatic IdP JIT flow. Sources: anythingllm:anythingllm:config. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: Admin routes implement user deletion and log the event. A fixture verifying chat/knowledge ownership transfer and active-session revocation was not run. Sources: anythingllm:anythingllm:admin-pin. - seat_assignment — Can admins assign and reclaim seats? [supported]: Admins create/manage users and workspace membership under the no-seat-fee self-hosted licence. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:config, anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:security, anythingllm:anythingllm:license #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. - seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. - scim — Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - group_sync — Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra. - jit_provisioning — Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth. - seat_assignment — Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license ### ADM-03: Roles, groups and feature permissions Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Standard Docker multi-user governance uses Admin, Manager and Default roles plus workspace membership. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - groups: Can permissions be set per group? An independently configurable local/IdP group object and two-group permission fixture were not established. - feature_toggles: Operators configure available Agent skills, providers and workspaces. A fine-grained per-group feature matrix was not established for standard roles. - multi_entity: Workspaces separate access within one installation; legal-entity tenancy, separate operator boundaries and a multi-entity contract were not verified. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: Admins control the whole system; Managers manage workspaces but cannot change the system LLM/embedder/vector settings; Default users chat in assigned workspaces. Sources: anythingllm:anythingllm:security. - groups — Can permissions be set per group? [unknown]: groups: Can permissions be set per group? An independently configurable local/IdP group object and two-group permission fixture were not established. - feature_toggles — Which features can be switched on or off per group? [partial]: Operators configure available Agent skills, providers and workspaces. A fine-grained per-group feature matrix was not established for standard roles. Sources: anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:security. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Workspaces separate access within one installation; legal-entity tenancy, separate operator boundaries and a multi-entity contract were not verified. Sources: anythingllm:anythingllm:security. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:agent-setup #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Separate admin management UI is preview; the core authorization model is documented as available. - No two-group disabled-feature fixture was run. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access. - groups — Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin. - feature_toggles — Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights ### ADM-04: Usage and adoption analytics Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Authorized accounts can inspect chat/event activity and export chat logs; a full adoption/cost dashboard 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 v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - adoption_dashboard: Is there an adoption dashboard? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow. - breakdowns: Chat logs are available per workspace/user to authorized accounts; complete model/feature/assistant/group adoption breakdowns were not established. - privacy_modes: Can per-person reporting be limited or pseudonymised? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow. - adoption_dashboard — Is there an adoption dashboard? [unknown]: adoption_dashboard: Is there an adoption dashboard? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Chat logs are available per workspace/user to authorized accounts; complete model/feature/assistant/group adoption breakdowns were not established. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:event. - export — Can usage data be exported? [supported]: Chat logs export as CSV, JSON, Alpaca JSON or OpenAI-style JSONL once at least ten logs exist. Sources: anythingllm:anythingllm:logs. - privacy_modes — Can per-person reporting be limited or pseudonymised? [unknown]: privacy_modes: Can per-person reporting be limited or pseudonymised? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:event #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. - export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. - adoption_dashboard — Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens. - export — Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens ### ADM-05: Spend controls and cost allocation Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Per-user message quotas control consumption; monetary budgets and cost-centre allocation were not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - cost_visibility: Authorized users see chat activity by workspace/user. The reviewed sources do not establish actual billed currency cost by group. - budgets: Admins can set per-user daily message quotas. This is a count limit, not a documented CHF/EUR budget or pooled cost-centre allowance. - chargeback: Can costs be exported per cost centre? Monetary spend caps, model downgrades and cost-centre chargeback export were not verified. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Authorized users see chat activity by workspace/user. The reviewed sources do not establish actual billed currency cost by group. Sources: anythingllm:anythingllm:logs. - budgets — Can budgets be set per user or group? [partial]: Admins can set per-user daily message quotas. This is a count limit, not a documented CHF/EUR budget or pooled cost-centre allowance. Sources: anythingllm:anythingllm:user-pin. - budget_enforcement — Does reaching a budget alert, block or downgrade? [supported]: The inspected non-admin multi-user chat route aborts before generation when the trailing-24-hour message quota is reached. Sources: anythingllm:anythingllm:chat-pin, anythingllm:anythingllm:user-pin. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Monetary spend caps, model downgrades and cost-centre chargeback export were not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:user-pin, anythingllm:anythingllm:chat-pin #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. - budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. - chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights. - budgets — Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance. - budget_enforcement — Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin ### ADM-06: Audit logs and compliance export Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Event logs record named administrative/security activity and chats are exportable. Immutable audit retention and legal hold remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - siem_export: Can logs stream to a SIEM or be exported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive. - ediscovery: Are eDiscovery and legal hold supported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive. - log_retention: How long are logs kept? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive. - admin_events — Are admin and security events logged? [supported]: Pinned admin routes log user creation/deletion, invitation and API-key events; docs also name logins, setting changes and uploads. Sources: anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:event. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [supported]: Workspace chat history/logs retain prompts/responses and expose permissioned exports. Retention and external copies depend on the deployment. Sources: anythingllm:anythingllm:logs. - siem_export — Can logs stream to a SIEM or be exported? [unknown]: siem_export: Can logs stream to a SIEM or be exported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive. - log_retention — How long are logs kept? [unknown]: log_retention: How long are logs kept? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:event, anythingllm:anythingllm:logs #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. - content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. - siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. - ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. - admin_events — Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin. - siem_export — Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention — How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin ### ADM-07: Data loss prevention and personal data Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome. #### AnythingLLM Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown. Availability: source-only Delivery: native Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Development-source finding; no running instance or AHV/IBAN fixture. - Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class. - Redaction applies only to eligible fresh Agent text; encrypted originals remain stored. - A dedicated external DLP integration remains unverified. - pii_detection — Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - custom_patterns — Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration. - filter_location — Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318 ### ADM-08: AI policy and guardrails Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workspace instructions can guide models; a mandatory organization-wide policy and violation system remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - org_instructions: Admins/Managers configure workspace/system prompt context and model defaults. A single unavoidable organization policy and its enforcement were not established. - usage_notice: Can users be required to accept a usage policy? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee. - content_filters: Are content filters configurable? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee. - violation_reporting: Are policy hits visible to admins? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee. - org_instructions — Can admins set organisation-wide instructions? [partial]: Admins/Managers configure workspace/system prompt context and model defaults. A single unavoidable organization policy and its enforcement were not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig. - usage_notice — Can users be required to accept a usage policy? [unknown]: usage_notice: Can users be required to accept a usage policy? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee. - content_filters — Are content filters configurable? [unknown]: content_filters: Are content filters configurable? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee. - violation_reporting — Are policy hits visible to admins? [unknown]: violation_reporting: Are policy hits visible to admins? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. - content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. - violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. - org_instructions — Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - usage_notice — Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface. - content_filters — Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod. - violation_reporting — Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod ## Data protection and sovereignty ### DATA-01: Hosting location and data residency Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosted locations are customer-selected. Managed Cloud uses AWS, but a guaranteed country for all storage/inference/support was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - backups_logs_region: Self-hosted logs/storage follow deployment choices; telemetry is optional. Cloud backup/log geography and actual egress were not audited. - support_access_region: Cloud privacy explicitly allows necessary Mintplex team access for debugging/maintenance; support-access country restrictions were not established. - swiss_hosting: Customers can self-host on Swiss infrastructure. A vendor-managed Swiss Cloud region and Swiss inference/support commitment were not established. - residency_plan: Customer-operated placement is available with self-hosting. Public Basic/Pro/Enterprise offers do not establish a complete Swiss/EU data-boundary package. - storage_region — Where are chats, files and indexes stored? [supported]: Docker data/embedding storage is customer configured; Desktop uses its local OS data directory. Managed Cloud documentation identifies AWS but does not establish a country. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:storage, anythingllm:anythingllm:cloud-overview. - inference_region — Where do model calls run, per provider? [supported]: Local endpoints run where the operator deploys them; Azure/AWS/Vertex routes and cloud APIs use the selected provider. Self-hosting the UI does not fix inference geography. Sources: anythingllm:anythingllm:built-in, anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex. - backups_logs_region — Where are backups, logs and telemetry? [partial]: Self-hosted logs/storage follow deployment choices; telemetry is optional. Cloud backup/log geography and actual egress were not audited. Sources: anythingllm:anythingllm:privacy, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:localdocker. - support_access_region — From where can vendor staff access data? [partial]: Cloud privacy explicitly allows necessary Mintplex team access for debugging/maintenance; support-access country restrictions were not established. Sources: anythingllm:anythingllm:privacy-cloud. - swiss_hosting — Is Swiss hosting available? [partial]: Customers can self-host on Swiss infrastructure. A vendor-managed Swiss Cloud region and Swiss inference/support commitment were not established. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:cloud-overview. - residency_plan — Which plan or option provides residency? [partial]: Customer-operated placement is available with self-hosting. Public Basic/Pro/Enterprise offers do not establish a complete Swiss/EU data-boundary package. Sources: anythingllm:anythingllm:docker, anythingllm:anythingllm:cloud. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:storage, anythingllm:anythingllm:cloud-overview, anythingllm:anythingllm:built-in, anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex, anythingllm:anythingllm:privacy, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:docker, anythingllm:anythingllm:cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. - support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. - storage_region — Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote. - inference_region — Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex. - backups_logs_region — Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin. - support_access_region — From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting — Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license. - residency_plan — Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license ### DATA-02: Deployment options Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Docker supports customer-cloud/on-premise operation; Cloud sells isolated managed instances and Desktop is a separate local client. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - multi_tenant_saas: Is a shared SaaS offered? A shared multi-tenant SaaS was not established: the public managed offer describes private isolated instances. - air_gapped: Local models/embeddings can run after assets are downloaded. A full disconnected fixture was not run; online tools and optional periodically validated Desktop Pro need separate treatment. - multi_tenant_saas — Is a shared SaaS offered? [unknown]: multi_tenant_saas: Is a shared SaaS offered? A shared multi-tenant SaaS was not established: the public managed offer describes private isolated instances. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [supported]: The managed Cloud overview describes one isolated AWS instance per customer. Current pricing lists Basic and Pro, with Enterprise custom services; no numeric seat minimum is published in the reviewed offer. Sources: anythingllm:anythingllm:cloud-overview, anythingllm:anythingllm:cloud. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Docker can run on customer-selected servers/cloud accounts without an MIT software seat minimum. Sources: anythingllm:anythingllm:docker, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:license. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: Customers can operate the Docker stack with local providers; commercial Enterprise also advertises on-premise support. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:models, anythingllm:anythingllm:cloud. - air_gapped — Can it run without internet access? [partial]: Local models/embeddings can run after assets are downloaded. A full disconnected fixture was not run; online tools and optional periodically validated Desktop Pro need separate treatment. Sources: anythingllm:anythingllm:built-in, anythingllm:anythingllm:local-embed, anythingllm:anythingllm:pro-key. - mode_feature_gaps — Which features are missing outside SaaS? [supported]: Desktop is single-user; Docker provides multi-user administration; Cloud explicitly excludes built-in inference, custom coded Agents and MCP. Scheduled Jobs and mail skills are single-user only. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:job, anythingllm:anythingllm:outlook. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:cloud-overview, anythingllm:anythingllm:cloud, anythingllm:anythingllm:docker, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:license, anythingllm:anythingllm:models, anythingllm:anythingllm:built-in, anythingllm:anythingllm:local-embed, anythingllm:anythingllm:pro-key, anythingllm:anythingllm:desktop, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:job, anythingllm:anythingllm:outlook #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The project documents local and customer-cloud installs. A free public demo is separate from a production managed service. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. - dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. - mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. - multi_tenant_saas — Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin. - air_gapped — Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg. - mode_feature_gaps — Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code ### DATA-03: Training use and provider retention Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Application locality and provider retention are separate; no universal no-training or zero-retention contract was verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - vendor_training: The Desktop policy describes local chat/document storage and optional anonymous telemetry. Cloud terms grant platform-improvement usage rights without a specific reviewed model-training exclusion. This is not a blanket no-training assurance. - provider_training: Do model providers train on it under this product's contracts? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - zero_retention: Is zero data retention available, and on which plan? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - human_review: Can provider staff review content? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - vendor_training — Does the vendor train on customer content? [partial]: The Desktop policy describes local chat/document storage and optional anonymous telemetry. Cloud terms grant platform-improvement usage rights without a specific reviewed model-training exclusion. This is not a blanket no-training assurance. Sources: anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:terms-cloud. - 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 configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - 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 configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:terms-cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. - provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - vendor_training — Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat. - provider_training — Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat ### DATA-04: Retention and deletion Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Removing workspace access differs from full document erasure; managed Cloud states immediate unrecoverable deletion on cancellation. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - default_retention: Self-hosted documents/history remain in local storage until removed; a universal duration covering chats, indexes, logs, backups and memory was not established. - admin_retention: Can admins set retention periods? A general time-based admin retention scheduler and verified deletion of backups/external-provider copies were not established. - default_retention — What is retained and for how long by default? [partial]: Self-hosted documents/history remain in local storage until removed; a universal duration covering chats, indexes, logs, backups and memory was not established. Sources: anythingllm:anythingllm:privacy, anythingllm:anythingllm:storage. - admin_retention — Can admins set retention periods? [unknown]: admin_retention: Can admins set retention periods? A general time-based admin retention scheduler and verified deletion of backups/external-provider copies were not established. - user_deletion — Can users delete their chats and files permanently? [supported]: Workspace removal deletes that workspace’s vectors but retains the reusable document. My Documents deletion removes the parsed source/cache and all workspace copies according to the privacy guide. Sources: anythingllm:anythingllm:privacy. - contract_end_deletion — What is deleted at contract end, and when? [supported]: For managed Cloud only, the current policy and generic terms state permanent non-recoverable instance/data deletion at cancellation, nonpayment or manual termination. No grace period is promised. Sources: anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:privacy, anythingllm:anythingllm:storage, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. - contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. - default_retention — What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention. - admin_retention — Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention. - user_deletion — Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings. - contract_end_deletion — What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings ### DATA-05: Sub-processors and foreign-law exposure Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment. #### AnythingLLM Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. - transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_list — Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification — Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy — Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner ### DATA-06: Contracts and regulatory coverage Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Generic Cloud terms specify California law; a negotiated DPA and regulatory or sector package were not verified. Availability: generally-available Delivery: native Scope: surfaces=AnythingLLM Cloud managed instance, Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - dpa: Is a DPA available, and is it negotiable? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - revdsg_gdpr: Does the DPA cover revDSG and GDPR? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - governing_law: Managed Cloud terms specify California, United States law and explicitly exclude self-hosted deployments. A specific court and enterprise override were not established. - ai_act_materials: Is EU AI Act documentation provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - sector_materials: Are FINMA or other sector materials provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - dpa — Is a DPA available, and is it negotiable? [unknown]: dpa: Is a DPA available, and is it negotiable? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [unknown]: revdsg_gdpr: Does the DPA cover revDSG and GDPR? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - governing_law — Which law and court govern the contract? [partial]: Managed Cloud terms specify California, United States law and explicitly exclude self-hosted deployments. A specific court and enterprise override were not established. Sources: anythingllm:anythingllm:terms-cloud. - ai_act_materials — Is EU AI Act documentation provided? [unknown]: ai_act_materials: Is EU AI Act documentation provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. - sector_materials — Are FINMA or other sector materials provided? [unknown]: sector_materials: Are FINMA or other sector materials provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:terms-cloud #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### DATA-07: Certifications and attestations Judgment rule: Record each certificate or report separately: ISO 27001, 27017, 27018, 27701, 42001; SOC 2 Type I/II with period; BSI C5; TISAX; national schemes. Record issuer, scope (which product and entity), validity and access route. A cloud provider's certificate does not certify the product. #### AnythingLLM Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### DATA-08: Encryption and key control Judgment rule: Record encryption at rest and in transit, customer-managed keys (BYOK/HYOK), key location, and private networking (private link, IP allow-lists, VPN). #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Private deployment and managed-instance isolation are documented; default encryption of all content and a product key-custody service were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - encryption_at_rest: Is data encrypted at rest? Default encryption-at-rest/transit settings for every database, file, backup and provider route were not verified. - customer_managed_keys: Self-hosted operators control infrastructure/secrets. A product-level BYOK/HYOK content-encryption contract was not established. - tenant_isolation: Managed Cloud describes private isolated AWS instances and resources per customer. This was not independently tested and is separate from source/workspace access control. - encryption_at_rest — Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? Default encryption-at-rest/transit settings for every database, file, backup and provider route were not verified. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Self-hosted operators control infrastructure/secrets. A product-level BYOK/HYOK content-encryption contract was not established. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:config. - private_networking — Is private connectivity or IP restriction available? [supported]: Docker can be placed on customer infrastructure; Desktop API listens on loopback unless optional network discovery is enabled. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:desktop. - tenant_isolation — How are customers separated in shared SaaS? [partial]: Managed Cloud describes private isolated AWS instances and resources per customer. This was not independently tested and is separate from source/workspace access control. Sources: anythingllm:anythingllm:cloud-overview. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:config, anythingllm:anythingllm:desktop, anythingllm:anythingllm:cloud-overview #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Network and storage security depend on the customer’s deployment; application authentication does not certify encryption of all stored content. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - customer_managed_keys: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. - tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - encryption_at_rest — Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. Sources: librechat:librechat:auth, librechat:librechat:compose-pin. - private_networking — Is private connectivity or IP restriction available? [supported]: Operators deploy the stack on their own network and configure reverse proxies/HTTPS for remote access. Sources: librechat:librechat:remote, librechat:librechat:local. - tenant_isolation — How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:auth, librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:local ### DATA-09: Professional secrecy Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local/self-hosted and managed Cloud content-access paths differ. Cloud permits necessary operational team access; a Mintplex staff/sub-processor professional-secrecy undertaking and its plan/add-on terms remain unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation and managed-service terms retrieved 2026-10-21; this row does not infer contract terms from the source-code licence; plan=Mixed modes identified per answer: Docker/Desktop on customer infrastructure; Basic/Pro managed Cloud dedicated AWS instance; Enterprise custom services checked separately; add_ons=none stated; deployment_mode=not specified; region=Customer-selected Docker/Desktop location; managed Cloud AWS country and provider/support staff locations unverified; no DE/CH secrecy-contract variant established; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: Exact Cloud staff/sub-processor plain-text access, provider human access and deployment-specific operator grants remain unverified. - 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 § 203 StGB / Art. 321 StGB or equivalent professional-secrecy undertaking binding Mintplex staff was obtained from the reviewed Cloud terms/privacy, Desktop privacy, pricing and product documentation. Generic privacy commitments are not recorded as that undertaking. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:privacy-desktop. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: The Cloud policy names AWS, Stripe and PostHog, but no professional-secrecy undertaking extending to covered sub-processors and their personnel was obtained. Customer-selected model/tool services require separate terms; coverage of their staff remains unknown. Sources: anythingllm:anythingllm:privacy-cloud. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: The public Basic, Pro and quote-only Enterprise descriptions did not establish a professional-secrecy package, paid add-on, plan entitlement or price. Availability under a separately negotiated Enterprise agreement remains unknown; no sales contact was made. Sources: anythingllm:anythingllm:cloud. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Docker data is held on customer-mounted storage; Desktop documents local chat/file storage. Local or external models can be selected. For the separate managed Cloud service, the policy permits necessary Mintplex team instance access for debugging and maintenance and names AWS infrastructure; configured remote models process inference requests. The documents do not establish exactly which plain-text fields operational staff/sub-processors can see or each provider’s human-access permissions. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:secrecy-cloud-access, anythingllm:anythingllm:secrecy-model-routing. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public Cloud terms/privacy, Desktop privacy and setup guides provide general data-handling information. No product-scoped DE/CH secrecy contract template, staff/sub-processor annex or professional-body guidance was located in the reviewed public sources and targeted searches. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:secrecy-cloud-access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:cloud, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:secrecy-cloud-access, anythingllm:anythingllm:secrecy-model-routing #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified. - Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom ## Commercials and vendor ### VEN-01: Pricing model and list prices Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The current public offer page advertises Cloud Basic at $50/month and Pro at $99/month. These are advertised card prices; legacy tier identities, capacities and checkout entitlements are not mapped here. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public offer cards and Desktop Pro documentation retrieved 2026-10-21; no inference of renamed checkout/legacy tier equivalence; plan=MIT self-hosted/core Desktop; advertised Cloud Basic/Pro cards and quote-only Enterprise; optional Desktop Pro is a separate offer; add_ons=none stated; deployment_mode=not specified; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - This claim quotes advertised offer-card prices only; it does not assert that Basic/Pro and Starter/Professional are equivalent SKUs. - Legacy-tier capacity limits are excluded. Current-card capacity, model-credit allowances, ISO currency and Desktop Pro numeric pricing remain unverified. - pricing_unit — What is the pricing unit? [supported]: Self-hosted software has no per-seat MIT licence fee. The current Cloud cards quote a private instance per month; optional Desktop Pro is a separate licence. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud-cards-r2, anythingllm:anythingllm:pro. - list_prices — What are list prices per plan, with date and currency? [partial]: As retrieved 2026-10-21, the public Cloud cards advertise Basic $50/month and Pro $99/month; Enterprise requires a quote. The page does not give an ISO currency code. These prices are not mapped to Starter/Professional checkout identifiers; Desktop Pro pricing remains unverified. Sources: anythingllm:anythingllm:cloud-cards-r2, anythingllm:anythingllm:pro-key. - included_usage — What usage is included? [partial]: The Basic card explicitly requires a customer LLM API key. Included model credits, overage tariffs and quantified capacity/entitlements for the current Basic/Pro cards were not established. Legacy limitations-page tier names are not used to infer them. Sources: anythingllm:anythingllm:cloud-cards-r2. - add_ons — Which features cost extra? [partial]: Optional Desktop Pro removes Magic-feature daily limits and document watermarks. Its price and custom Enterprise integration/support prices remain unverified; Cloud Pro is a separate product offer. Sources: anythingllm:anythingllm:pro, anythingllm:anythingllm:cloud-cards-r2. - overage — What do usage beyond limits and premium models cost? [partial]: Customer-selected model/tool accounts incur their own provider charges. No current-card included allowance or AnythingLLM token-overage tariff was verified. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud-cards-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud-cards-r2, anythingllm:anythingllm:pro, anythingllm:anythingllm:pro-key, anythingllm:anythingllm:models #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. - overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. - pricing_unit — What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat. - list_prices — What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat. - included_usage — What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat. - add_ons — Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images. - overage — What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens ### VEN-02: Scenario cost Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts. #### AnythingLLM 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 v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; 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: anythingllm:anythingllm:license, anythingllm:anythingllm:cost-vm, anythingllm:anythingllm:cost-pg, anythingllm:anythingllm:cost-fx, anythingllm:anythingllm:cost-model, anythingllm:anythingllm: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: anythingllm:anythingllm:license, anythingllm:anythingllm:cost-vm, anythingllm:anythingllm:cost-pg, anythingllm:anythingllm:cost-fx, anythingllm:anythingllm:cost-model, anythingllm:anythingllm: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: anythingllm:anythingllm:license, anythingllm:anythingllm:cost-vm, anythingllm:anythingllm:cost-pg, anythingllm:anythingllm:cost-fx, anythingllm:anythingllm:cost-model, anythingllm:anythingllm: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: anythingllm:anythingllm:cost-model, anythingllm:anythingllm: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. The shared PostgreSQL reference budget is not AnythingLLM’s default storage architecture; application/vector storage, extra services and capacity validation remain unpriced. Paid Desktop Pro, managed Cloud and Enterprise are excluded from this self-hosted scenario. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: anythingllm:anythingllm:cost-vm, anythingllm:anythingllm:cost-pg, anythingllm:anythingllm:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cost-vm, anythingllm:anythingllm:cost-pg, anythingllm:anythingllm:cost-fx, anythingllm:anythingllm:cost-model, anythingllm:anythingllm:cost-effort #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified. Limitations: - ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise. - The budget is a floor because named infrastructure and service costs are unpriced. - cost_200 — Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_1000 — Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_5000 — Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - variable_share — Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort. - unknown_parts — Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort ### VEN-03: Evaluation access Judgment rule: Distinguish free tier, self-serve trial, sales-led pilot, paid proof of concept and open-source self-install. Record card requirement, duration, seat limit, and which features (SSO, connectors, admin) the trial includes. Map which shared scenarios can be run without sales approval. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-installation and free Desktop permit evaluation without sales; managed Cloud offers paid self-serve instance checkout. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - self_serve_trial: Free self-install has no software trial clock/card requirement. Cloud has paid self-serve signup links, but a free business Cloud trial and its card/duration terms were not established. - trial_scope: Docker self-install includes standard multi-user administration and workspace knowledge; Enterprise SSO/custom service scope is quote-only and Cloud excludes MCP/custom Agents. - sales_gate: Standard self-install and paid public Cloud tiers have self-serve paths. Custom Enterprise services require a quote; no vendor was contacted. - free_tier — Is there a free tier for business use? [supported]: MIT self-hosting and the core Desktop download are free; Magic features have a free allowance with optional Desktop Pro. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:desktop, anythingllm:anythingllm:pro. - self_serve_trial — Is a self-serve business trial available? [partial]: Free self-install has no software trial clock/card requirement. Cloud has paid self-serve signup links, but a free business Cloud trial and its card/duration terms were not established. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:cloud. - trial_scope — Do trials include SSO, connectors and admin features? [partial]: Docker self-install includes standard multi-user administration and workspace knowledge; Enterprise SSO/custom service scope is quote-only and Cloud excludes MCP/custom Agents. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:cloud, anythingllm:anythingllm:cloud-limits. - sales_gate — Does meaningful evaluation require sales contact? [partial]: Standard self-install and paid public Cloud tiers have self-serve paths. Custom Enterprise services require a quote; no vendor was contacted. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:localdocker. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:desktop, anythingllm:anythingllm:pro, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:cloud, anythingllm:anythingllm:security, anythingllm:anythingllm:cloud-limits #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Customers can self-install without licence payment; the public demo is an evaluation-only alternative. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - free_tier — Is there a free tier for business use? [supported]: MIT self-installation permits organizational use without a software licence fee. Sources: librechat:librechat:license. - self_serve_trial — Is a self-serve business trial available? [supported]: Self-installation has no trial clock or software card requirement; the free hosted Demo can be tried separately under its terms. Sources: librechat:librechat:local, librechat:librechat:demo. - trial_scope — Do trials include SSO, connectors and admin features? [supported]: Self-installed instances can configure SSO, Agents, file retrieval and administration with their own service accounts. It is not evidence that every experimental add-on is enabled by default. Sources: librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag. - sales_gate — Does meaningful evaluation require sales contact? [supported]: The documented Docker install does not require sales approval; optional third-party services have separate account requirements. Sources: librechat:librechat:local, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:demo, librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag, librechat:librechat:firstchat ### VEN-04: Contract terms and pricing transparency Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The self-hosted MIT grant has no seat commitment; Cloud publishes monthly prices and cancellation terms, with immediate deletion. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - minimum_commitment: The MIT grant has no user-count minimum; Cloud per-instance pricing lists no numeric seat floor. Enterprise minima were not established. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR billing from a European contracting entity and Enterprise-specific renewal/price-change terms were not established. - transparency_class: Self-host licensing and Cloud Basic/Pro headlines are disclosed. Enterprise service scope, Desktop Pro tariff and full all-in provider spend are only partially specified or unknown. - minimum_commitment — What seat or spend minimum applies? [partial]: The MIT grant has no user-count minimum; Cloud per-instance pricing lists no numeric seat floor. Enterprise minima were not established. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud. - contract_length — What contract lengths are offered? [supported]: Cloud Basic/Pro are listed monthly; MIT software use has no subscription term. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:license. - cancellation — How can the contract be cancelled or reduced? [supported]: Cloud can be cancelled via the dashboard or email under the generic terms, with immediate non-recoverable deletion and a stated prorated-current-cycle refund provision. Self-hosted service contracts are separate. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud. - 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 billing from a European contracting entity and Enterprise-specific renewal/price-change terms were not established. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Self-host licensing and Cloud Basic/Pro headlines are disclosed. Enterprise service scope, Desktop Pro tariff and full all-in provider spend are only partially specified or unknown. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:pro-key, anythingllm:anythingllm:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud, anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:pro-key #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. - minimum_commitment — What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license. - contract_length — What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license. - cancellation — How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat ### VEN-05: Source licence Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned main repository is MIT. Paid hosted/Desktop entitlements must be distinguished from that source licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - enterprise_features_closed: Cloud Enterprise and Desktop Pro add commercial services/entitlements. Whether particular enterprise-only implementations are closed or separately licensed was not established from the main MIT file. - licence_type — Which licence applies to each component? [supported]: The pinned main client/server repository at v1.18.0 uses MIT. Mobile, browser extension and optional paid-service components require their own component licence review. Sources: anythingllm:anythingllm:license. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: MIT requires notice preservation but has no UI-branding or user-count clause. Optional Desktop Pro removes watermarks from generated documents; that is a paid feature entitlement, not a restriction in the main MIT source licence. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:pro. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: Cloud Enterprise and Desktop Pro add commercial services/entitlements. Whether particular enterprise-only implementations are closed or separately licensed was not established from the main MIT file. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:pro, anythingllm:anythingllm:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:pro, anythingllm:anythingllm:cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. - licence_type — Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code ### VEN-06: Data export and exit Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Authorized accounts can export chat logs; a complete assistant/knowledge exit fixture was not run. Cloud cancellation leaves no recovery window. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - assistant_export: Can assistants and prompts be exported in a reusable format? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms. - knowledge_export: Can knowledge bases and their sources be exported? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms. - chat_export — Can admins export all chats? [supported]: Permissioned exports cover workspace/user chat logs in CSV, JSON, Alpaca JSON or OpenAI-style JSONL once at least ten logs exist. No all-organization export fixture was run. Sources: anythingllm:anythingllm:logs. - assistant_export — Can assistants and prompts be exported in a reusable format? [unknown]: assistant_export: Can assistants and prompts be exported in a reusable format? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms. - export_format — Are formats documented and machine-readable? [supported]: Documented chat-log formats are machine-readable. This does not establish complete source-file, assistant or index portability. Sources: anythingllm:anythingllm:logs. - post_termination_window — How long can data be retrieved after termination? [supported]: Managed Cloud policy states permanent unrecoverable data deletion at cancellation/nonpayment/termination, so no post-termination retrieval window is promised. Self-hosted data remains under operator control. Sources: anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. - assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. - knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - chat_export — Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - export_format — Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin. - post_termination_window — How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api ### VEN-07: Support and service levels Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public community/team support routes and the generic managed Cloud no-offline-credit terms are documented. No bespoke Enterprise SLA or Pro response-time entitlement is established by this claim. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, AnythingLLM Cloud managed instance; version=Public support guide and generic Cloud terms (last updated 2024-07-01) retrieved 2026-10-21; plan=Self-hosted community/team support and managed Cloud under the published generic terms only; separately negotiated Enterprise SLAs and advertised Pro response terms are outside verified contractual scope; add_ons=none stated; deployment_mode=not specified; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - Generic Cloud contract facts are not extended to a bespoke Enterprise agreement. - Advertised support timing is excluded from contractual uptime/compensation findings. - Support languages, hours, regional staffing and a status history remain unverified. - support_channels — Which support channels are available on each plan? [supported]: The public guide lists GitHub issues, team email and community Discord, recommending GitHub/email for direct team assistance. These channels do not establish contracted response hours. Sources: anythingllm:anythingllm:support-r2. - support_languages — Is support available in German, French or Italian? [unknown]: Contracted German, French or Italian support coverage, service hours and time zones were not established in the scoped guide and generic terms. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: A CH/DACH support entity, staffed local presence or named support partner was not verified from these sources. - uptime_sla — Is there an uptime SLA with credits? [partial]: The generic managed Cloud terms deny refunds/credits for an offline instance and do not establish an uptime percentage/credit schedule. This is a finding about those generic terms only; no executed Enterprise override or contractual definition of advertised Pro support timing was reviewed. Sources: anythingllm:anythingllm:cloud-terms-r2. - status_page — Is there a public status page with history? [unknown]: A first-party public service-status page with incident history was not verified in the support/contract sources. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:support-r2, anythingllm:anythingllm:cloud-terms-r2 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public project/community channels are available; a binding business support SLA was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. - support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - support_channels — Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat. - support_languages — Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla — Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page — Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat ### VEN-08: Onboarding, training and adoption Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings. #### AnythingLLM Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public setup/skill tutorials are available and Enterprise advertises custom services; a priced workforce adoption package 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 v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified. Limitations: - onboarding_service: Is guided onboarding included? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified. - user_training: Is end-user training offered, in which languages? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified. - use_case_library: Public Agent Flow, SQL, mail, document-generation and meeting guides provide use-case examples. A formal role-based workforce curriculum was not established. - adoption_programme: Is there a champion or adoption programme? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified. - service_cost: Enterprise premium service/custom integrations/on-premise support are quote-only. Included rollout/training deliverables and prices were not established. - onboarding_service — Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified. - 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, DE/FR/IT end-user training, champion programme or change-management package was verified. - use_case_library — Are role-based use cases and templates provided? [partial]: Public Agent Flow, SQL, mail, document-generation and meeting guides provide use-case examples. A formal role-based workforce curriculum was not established. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:docgen, anythingllm:anythingllm:meeting, anythingllm:anythingllm:sql. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified. - service_cost — Which services cost extra? [partial]: Enterprise premium service/custom integrations/on-premise support are quote-only. Included rollout/training deliverables and prices were not established. Sources: anythingllm:anythingllm:cloud. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:docgen, anythingllm:anythingllm:meeting, anythingllm:anythingllm:sql, anythingllm:anythingllm:cloud #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. - adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - onboarding_service — Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training — Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library — Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost — Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat ## Sources ### anythingllm:anythingllm:models Language models. The product documents multiple cloud and local provider integrations, with selected models supplied by the connected account/server. - URL: https://docs.anythingllm.com/features/language-models - Locator: Supported local/cloud providers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:llmconfig LLM configuration. System defaults can be overridden per workspace and separately for agent use. - URL: https://docs.anythingllm.com/setup/llm-configuration/overview - Locator: System, Workspace and Agent LLMs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:built-in Built-in local model engine. Desktop is moving its built-in engine from Ollama to Lemonade/llama.cpp; current Docker documentation describes opt-in local inference on images after v1.18.0. - URL: https://docs.anythingllm.com/setup/llm-configuration/local/built-in - Locator: Lemonade/llama.cpp; Desktop migration; Docker opt-in - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:router Model Router. Self-hosted and Desktop installations can route messages by ordered calculated or model-classified rules, with a fallback provider/model. - URL: https://docs.anythingllm.com/model-router/overview - Locator: Availability; rule types; fallback - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:constants-pin AnythingLLM file converter registration. The pinned collector registers PDF, DOCX, PPTX, XLSX, EPUB, text, image and audio converters; legacy DOC is commented out. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/collector/utils/constants.js - Locator: collector/utils/constants.js, accepted MIME and converter maps - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: collector/utils/constants.js ### 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 ### anythingllm:anythingllm:generic Generic OpenAI configuration. Operators can configure an OpenAI-compatible provider, with endpoint-specific behavior and configuration caveats. - URL: https://docs.anythingllm.com/setup/llm-configuration/cloud/openai-generic - Locator: Compatible API route - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:changelog Desktop v1.18.0 changelog. Desktop v1.18.0 changes the built-in engine from Ollama to Lemonade/llama.cpp and records format/sync fixes. - URL: https://docs.anythingllm.com/changelog/v1.18.0 - Locator: Lemond/Lemonade migration; reasoning controls; fixes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:releases AnythingLLM v1.18.0 release. The latest retrieved stable GitHub release is v1.18.0, published 2026-10-13. - URL: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.18.0 - Locator: Release date and change list - Evidence kind: documented - Source date: 2026-10-13 - Retrieved: 2026-10-21 ### anythingllm:anythingllm:azure Azure OpenAI configuration. The Azure route uses the customer Azure subscription and its model access. - URL: https://docs.anythingllm.com/setup/llm-configuration/cloud/azure-openai - Locator: Customer Azure subscription - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:bedrock AWS Bedrock configuration. Bedrock is a separately configured customer cloud-account route. - URL: https://docs.anythingllm.com/setup/llm-configuration/cloud/aws-bedrock - Locator: Credentials and provider settings - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:vertex Google Vertex AI configuration. Vertex uses customer Google Cloud credentials and deployment configuration. - URL: https://docs.anythingllm.com/setup/llm-configuration/cloud/google-vertex - Locator: Service account, project and region - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:cloud AnythingLLM Cloud pricing. Current public pricing lists private Cloud Basic at $50/month, Pro at $99/month and quote-only Enterprise with SSO/custom services. - URL: https://anythingllm.com/cloud - Locator: Basic, Pro and Enterprise offer table - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:cloud-limits Cloud limitations. Managed Cloud explicitly excludes built-in inference, custom coded Agents and MCP; local/self-hosted capabilities cannot be assumed there. - URL: https://docs.anythingllm.com/cloud/limitations - Locator: No built-in LLM; no custom Agents; no MCP - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:license AnythingLLM v1.18.0 licence. The pinned main repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/LICENSE - Locator: LICENSE, MIT grant and notice - 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 ### anythingllm:anythingllm:ollama Ollama configuration. A separately installed Ollama endpoint can provide customer-operated chat inference. - URL: https://docs.anythingllm.com/setup/llm-configuration/local/ollama - Locator: Local provider setup - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:local-embed Built-in embedding provider. The built-in all-MiniLM-L6-v2 embedder runs on CPU and is primarily trained on English; it must first be downloaded. - URL: https://docs.anythingllm.com/setup/embedder-configuration/local/built-in - Locator: CPU model and download - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:embed Embedding models. Retrieval embedding providers are configured separately from chat inference. - URL: https://docs.anythingllm.com/features/embedding-models - Locator: Local and cloud embedding options - 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 ### anythingllm:anythingllm:user-pin AnythingLLM user quota implementation. The pinned user quota counts chats over the preceding 24 hours for non-admin multi-user accounts; null limits and admins are exempt. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/server/models/user.js - Locator: server/models/user.js, canSendChat and dailyMessageLimit validation - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: server/models/user.js ### anythingllm:anythingllm:chat-pin AnythingLLM chat quota enforcement. The pinned chat endpoints abort before generation when a multi-user account reaches its configured 24-hour quota. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/server/endpoints/chat.js - Locator: server/endpoints/chat.js, multiUserMode and canSendChat checks - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: server/endpoints/chat.js ### 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 ### anythingllm:anythingllm:docchat Documents in chat, current interface. Attachments inject full text while embedded documents are retrieved as chunks and become available to every authorized workspace user. - URL: https://docs.anythingllm.com/chatting-with-documents/introduction - Locator: v1.8.5+; attachment vs embedding; context; workspace scope - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:pdf-pin AnythingLLM PDF extraction implementation. The pinned PDF handler attempts OCR when its initial text loader returns no pages, without establishing scan accuracy. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/collector/processSingleFile/convert/asPDF/index.js - Locator: collector/processSingleFile/convert/asPDF/index.js, no-text fallback - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: collector/processSingleFile/convert/asPDF/index.js ### 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 ### anythingllm:anythingllm:security Security and access. Docker multi-user roles are Admin, Manager and Default; Default users only chat in explicitly assigned workspaces. - URL: https://docs.anythingllm.com/features/security-and-access - Locator: Docker only; single-user vs multi-user; roles - 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 ### anythingllm:anythingllm:sync Automatic document sync preview. Preview sync refreshes watched sources; removing a watched Desktop original leaves existing parsed content and embeddings in place. - URL: https://docs.anythingllm.com/beta-preview/active-features/live-document-sync - Locator: Docker vs Desktop scope; intervals; missing local file - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:mcp MCP compatibility. Self-hosted/desktop MCP supports local stdio and remote SSE/Streamable transports with configured credentials/headers. - URL: https://docs.anythingllm.com/mcp-compatibility/overview - Locator: Configuration file; management UI; transport types - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:outlook Outlook Agent. The single-user Outlook skill uses a customer Entra application and requests approval for mailbox-modifying operations. - URL: https://docs.anythingllm.com/agent/usage/outlook-agent - Locator: Single-user only; delegated scopes; approvals - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:gmail Gmail Agent. The Gmail skill is single-user only and distinguishes read actions from modifying actions requiring approval. - URL: https://docs.anythingllm.com/agent/usage/gmail-agent - Locator: Single-user only; setup; action approvals - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:sql SQL Agent. A configurable SQL Agent can query a separately connected database. - URL: https://docs.anythingllm.com/agent/usage/sql-agent - Locator: Database connection and tool use - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:localdocker Local Docker installation. Self-hosting runs the application in customer-controlled infrastructure and mounted storage. - URL: https://docs.anythingllm.com/installation-docker/local-docker - Locator: Volumes; local network; configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:connectors-pin AnythingLLM connector registration. The pinned UI registers Confluence, repository, website, YouTube, Obsidian and other import connectors; no source ACL test was performed. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/frontend/src/components/Modals/ManageWorkspace/DataConnectors/index.jsx - Locator: frontend/src/components/Modals/ManageWorkspace/DataConnectors/index.jsx - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: frontend/src/components/Modals/ManageWorkspace/DataConnectors/index.jsx ### 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 ### anythingllm:anythingllm:vector Vector databases. The application supports configurable local and external vector databases rather than a single fixed vendor region. - URL: https://docs.anythingllm.com/features/vector-databases - Locator: Local and cloud storage choices - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:privacy Privacy and data handling. Telemetry is optional; deleting a document from a workspace differs from deleting it from My Documents and all workspaces. - URL: https://docs.anythingllm.com/features/privacy-and-data-handling - Locator: Telemetry; document removal vs full erasure - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:compose-pin LibreChat Docker service configuration. The pinned example runs a MongoDB primary store and a separate PGVector/RAG service with customer-mounted data. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/docker-compose.yml - Locator: docker-compose.yml, api/mongodb/vectordb/rag_api services - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: docker-compose.yml ### anythingllm:anythingllm:chatmodes Chat modes. Agent mode uses configured tools; Query mode is documented to report when it finds no relevant document information. - URL: https://docs.anythingllm.com/features/chat-modes - Locator: Agent, Chat and Query modes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:citation-pin AnythingLLM source citation rendering. The pinned client renders citation sources with file/link/provider metadata and source-detail controls. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/Citation/index.jsx - Locator: frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/Citation/index.jsx - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/Citation/index.jsx ### anythingllm:anythingllm:memory Memories and personalization. Admins enable user-scoped workspace/global memory, and users can edit/delete it; selected memories go to the configured model. - URL: https://docs.anythingllm.com/features/memories - Locator: Off by default; user scope; limits; extraction - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:systemprompt System prompt variables. Workspace system prompts can include dynamic user/time context; this does not establish a mandatory organization policy. - URL: https://docs.anythingllm.com/features/system-prompt-variables - Locator: Workspace prompt variables and context - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:memory User memory. Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats. - URL: https://www.librechat.ai/docs/features/memory - Locator: Key/value store; controls; disabled by default - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:agent-setup Agent setup. Operators configure Agent models and skills per workspace; the setup guide still names DuckDuckGo as the default search engine. - URL: https://docs.anythingllm.com/agent/setup - Locator: Workspace model; enabled skills; search configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:flow Agent Flows. A visual no-code flow editor creates reusable Agent skills; code skills remain a separate developer route. - URL: https://docs.anythingllm.com/agent-flows/overview - Locator: No-code builder; Desktop vs Docker - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:desktop Desktop installation overview. Desktop supports Windows/macOS/Linux, is single-user and exposes only its API when optional LAN discovery is enabled. - URL: https://docs.anythingllm.com/installation-desktop/overview - Locator: OS support; single-player; network discovery - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:flow-api Agent Flow API-call block. A flow block calls a configured API and passes its result into later flow steps. - URL: https://docs.anythingllm.com/agent-flows/blocks/api-call - Locator: HTTP action configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:docgen Document generation skill. The enabled built-in skill generates text, PDF, Excel, DOCX and PowerPoint files, with model-dependent results. - URL: https://docs.anythingllm.com/agent/usage/document-generation-agent - Locator: Availability; document types - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:chart Chart generation skill. An Agent chart skill generates charts from prompts and workspace data. - URL: https://docs.anythingllm.com/agent/usage/chart-generation - Locator: Examples and workspace data - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:images Image generation and editing. Agents can use configured image tools for generation/editing; provider credentials and model parameters are separate. - URL: https://www.librechat.ai/docs/features/image_gen - Locator: OpenAI Image Tools; provider setup; admin configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:agent-usage Using agents. Agent sessions use configured skills and tool-capable models. - URL: https://docs.anythingllm.com/agent/usage/overview - Locator: Skills and tool use - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:browsing Agent web browsing. The web-browsing skill searches the internet from an Agent request. - URL: https://docs.anythingllm.com/agent/usage/web-browsing - Locator: Built-in search skill - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:search-configured-r2 AnythingLLM v1.18.0 explicitly configured DuckDuckGo route. At the pinned revision, explicit agent_search_provider=duckduckgo-engine routes queries to the DuckDuckGo HTML search endpoint; this finding makes no default-provider claim. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/server/utils/agents/aibitat/plugins/web-browsing.js - Locator: agent_search_provider lookup; duckduckgo-engine switch case at lines 96-98; _duckDuckGoEngine at lines 1117-1210 - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: server/utils/agents/aibitat/plugins/web-browsing.js ### anythingllm:anythingllm:agent-skills-r2 AnythingLLM Agent skill controls. The setup guide documents skill selection in Settings > Agent Skills and tool toggles from the chat prompt menu. - URL: https://docs.anythingllm.com/agent/setup - Locator: Configure your available skills, excluding the unversioned default-search example - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### anythingllm:anythingllm:job Scheduled Jobs. Recurring Agent jobs are available only in single-user mode, with allowed tools, execution history and generated-file downloads. - URL: https://docs.anythingllm.com/scheduled-jobs/overview - Locator: Single-user restriction; schedules; run traces - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:schedule Scheduled Chats. Opt-in experimental schedules execute saved Agents with cron/time zones and recheck access and balance before running. - URL: https://www.librechat.ai/docs/features/scheduled_chats - Locator: Experimental and disabled by default; runtime and permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:api Agents API beta. The beta API exposes chat/Responses inference, Agent/Skill management and authenticated event delivery. - URL: https://www.librechat.ai/docs/features/agents_api - Locator: Inference; management; Agent Events; authentication - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:api Developer API. Instance APIs manage workspaces, document embedding and chat; API keys confer access and must be protected. - URL: https://docs.anythingllm.com/features/api - Locator: Instance /api/docs; key management; workspace APIs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:config Configuration. Simple SSO issues short-lived one-use login links for already-provisioned users through a privileged API key; it is not a native SAML/OIDC protocol implementation. - URL: https://docs.anythingllm.com/configuration - Locator: Simple SSO passthrough; multi-user prerequisites - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:docker Docker installation overview. Docker provides the shared browser/server deployment with multi-user administration; Desktop is a separate single-user application. - URL: https://docs.anythingllm.com/installation-docker/overview - Locator: Desktop/Docker comparison; server deployment - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:windows Windows installation. Silent installation can support MDM packaging, but all-users installation is explicitly unsupported and Enterprise/Server OS use has caveats. - URL: https://docs.anythingllm.com/installation-desktop/windows - Locator: Current User only; silent install and uninstall - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:ext Browser extension installation. The extension sends pages/selected text into workspaces using an API connection; it does not by itself enforce original web content ACLs. - URL: https://docs.anythingllm.com/browser-extension/install - Locator: Supported browsers; API connection; collected content - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:mobile Mobile overview. A separate Android app runs local models and can pair with Desktop or server instances; iOS is not currently available. - URL: https://docs.anythingllm.com/mobile/overview - Locator: Android only; local models; pairing; feature set - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:meeting-intro Meeting Assistant introduction. Free Desktop meeting recording/transcription is local on Windows/macOS; a selected cloud summary model receives the transcript. - URL: https://docs.anythingllm.com/meeting-assistant/introduction - Locator: Desktop exclusivity; supported OS; privacy - 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 ### anythingllm:anythingllm:pro AnythingLLM Pro overview. Optional Desktop Pro removes daily Magic-feature limits and generated-document watermarks; it is separate from Cloud Pro. - URL: https://docs.anythingllm.com/pro/overview - Locator: Desktop v1.15+; Magic features; document watermarks - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:images Image generation. Configured OpenAI/OpenRouter/Lemonade tools can edit reference images, while the documented Ollama route generates without using references. - URL: https://docs.anythingllm.com/features/image-generation - Locator: Provider table; reference-image editing; /img - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:tts Text to speech. Read-aloud uses configured local/browser or external TTS engines, depending on the selected provider. - URL: https://docs.anythingllm.com/features/text-to-speech - Locator: Provider engines and configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:stt Transcription models. Audio transcription is a separately configurable provider route. - URL: https://docs.anythingllm.com/features/transcription-models - Locator: Transcription provider overview - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:meeting Meeting Assistant features. The Desktop meeting workflow records/imports audio, identifies speakers, allows transcript corrections and summarizes meetings. - URL: https://docs.anythingllm.com/meeting-assistant/features - Locator: Transcription; speakers; editable text; summaries - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### librechat:librechat:artifacts Artifacts. Artifacts render generated React, HTML and Mermaid content in the chat interface. - URL: https://www.librechat.ai/docs/features/artifacts - Locator: React, HTML and Mermaid previews - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:share Shareable links. Shared links publish a transcript branch and optional file snapshots independently of the owner’s live file ACL. - URL: https://www.librechat.ai/docs/features/shareable_links - Locator: Authentication defaults; file snapshots; continuation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:i18n-pin AnythingLLM locale registration. The pinned frontend registers English, German, French and Italian resources; completeness and naturalness are not established. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/frontend/src/locales/resources.js - Locator: frontend/src/locales/resources.js, English/German/French/Italian imports - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: frontend/src/locales/resources.js ### anythingllm:anythingllm:r4-german-admin AnythingLLM German administrator locale. German locale resources include user/invite/event-log and administrator settings labels. This establishes partial admin localization, not completeness or naturalness. - URL: https://github.com/Mintplex-Labs/anything-llm/blob/9b1fcab141000eaba9f78ed131151de04904454b/frontend/src/locales/de/common.js - Locator: settings users, invites, event-logs and role/admin labels - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 9b1fcab141000eaba9f78ed131151de04904454b - Path: frontend/src/locales/de/common.js ### 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 ### anythingllm:anythingllm:admin-pin AnythingLLM administrative events. The pinned admin routes record user creation/deletion, invitation and API-key lifecycle events. - URL: https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba/server/endpoints/admin.js - Locator: server/endpoints/admin.js, user, invite and API-key routes - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba - Path: server/endpoints/admin.js ### anythingllm:anythingllm:logs Workspace chat logs. Authorized users export workspace/user chat logs in CSV, JSON, Alpaca JSON or JSONL once at least ten logs are available. - URL: https://docs.anythingllm.com/features/chat-logs - Locator: Permissions; export formats; minimum log count - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:event Event logs. The UI records login attempts, messages, setting changes and uploads with user/time details, without a stated immutable retention model. - URL: https://docs.anythingllm.com/features/event-logs - Locator: Events and fields - 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 ### 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 ### 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 ### anythingllm:anythingllm:cloud-overview Cloud overview. Mintplex describes each managed customer instance as isolated AWS infrastructure operated and updated by its team. - URL: https://docs.anythingllm.com/cloud/overview - Locator: Private managed instance - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm:privacy-cloud Cloud privacy policy. The managed-service policy excludes self-hosting, names AWS/Stripe/PostHog, permits necessary team access and states deletion at cancellation. - URL: https://docs.anythingllm.com/cloud/privacy-policy - Locator: Service scope; AWS; operational access; deletion - Evidence kind: documented - Source date: 2024-07-01 - Retrieved: 2026-10-21 ### anythingllm:anythingllm:storage Desktop storage. Desktop data is stored in an OS-specific local data directory controlled by its user. - URL: https://docs.anythingllm.com/installation-desktop/storage - Locator: Data location and backup - 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 ### anythingllm:anythingllm:pro-key Desktop Pro activation. A purchased Desktop Pro key is periodically validated; free feature allowances remain without a subscription. - URL: https://docs.anythingllm.com/pro/getting-started - Locator: Periodic licence validation; free allowances - Evidence kind: documented - Source date: Not stated - 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 ### anythingllm:anythingllm:terms-cloud Cloud terms. Managed-service terms name Mintplex Labs Inc in California, California law, cancellation deletion and no credits for offline service under the generic terms. - URL: https://docs.anythingllm.com/cloud/terms-and-conditions - Locator: Scope; entity; payment; cancellation; offline credits; law - Evidence kind: documented - Source date: 2024-07-01 - Retrieved: 2026-10-21 ### anythingllm:anythingllm:privacy-desktop Desktop privacy policy. The policy describes local Desktop data and optional telemetry; connected external models still need separately scoped data processing. - URL: https://docs.anythingllm.com/installation-desktop/privacy - Locator: Desktop-only scope; telemetry - 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 ### 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 ### anythingllm:anythingllm:secrecy-cloud-access AnythingLLM Cloud operational access policy. The managed-only policy permits operational team instance access, names AWS infrastructure and excludes self-hosted deployments; it does not enumerate plain-text field permissions. - URL: https://docs.anythingllm.com/cloud/privacy-policy - Locator: Instance Access and Management; Third-Party Services; Data Storage and Security; policy scope - Evidence kind: documented - Source date: 2024-07-01 - Retrieved: 2026-10-21 ### anythingllm:anythingllm:secrecy-model-routing AnythingLLM local and cloud model routing. System, workspace and agent models can use local or cloud providers; the selected inference path is separate from where the application is hosted. - URL: https://docs.anythingllm.com/setup/llm-configuration/overview - Locator: System LLM; Workspace LLM; Agent LLM; Supported LLM Providers - Evidence kind: documented - Source date: Not stated - 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 ### anythingllm:anythingllm:cloud-cards-r2 AnythingLLM advertised Cloud plan cards. The current offer page advertises Basic at $50/month and Pro at $99/month, with Enterprise by quote; Basic explicitly asks for an LLM API key. - URL: https://anythingllm.com/cloud - Locator: Basic $50/month, Pro $99/month and quote-only Enterprise cards; Basic BYO LLM key - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### anythingllm:anythingllm: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 ### anythingllm:anythingllm: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 ### anythingllm:anythingllm: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 ### anythingllm:anythingllm: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 ### anythingllm:anythingllm: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 ### 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 ### 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 ### anythingllm:anythingllm:cloud-terms-r2 AnythingLLM generic managed Cloud contract scope. The published generic terms cover managed Cloud, exclude self-hosting and deny offline-service credits; no bespoke Enterprise override was reviewed. - URL: https://docs.anythingllm.com/cloud/terms-and-conditions - Locator: Scope of Agreement; Instance Offline Recovery; last-updated date - Evidence kind: documented - Source date: 2024-07-01 - Retrieved: 2026-10-21 ### anythingllm:anythingllm:support-r2 AnythingLLM public support channels. Public support routes are GitHub, team email and community Discord; the guide recommends GitHub/email for direct team assistance. - URL: https://docs.anythingllm.com/support - Locator: GitHub Issues; team email; Discord Community; direct-assistance note - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21