--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/librechat-vs-open-webui/" data_url: "https://onaihq.com/compare/agents/librechat-vs-open-webui/data.json" generated_at: 2026-10-27 last_checked_at: 2026-10-26 last_cross_checked_at: 2026-10-26 next_check_at: 2026-12-20 publisher: "onAI" --- # LibreChat vs Open WebUI > 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 46 criteria with sourced findings for both products, including 46 that a second agent cross-checked for both. 48 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation: they are scoped, fresh and cite public resolved sources. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. "Stated by onAI" marks the publisher's own statements about its product (evidence type vendor-statement), which cite no third-party source. Humans approve the rubric, templates and generator; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent. - LibreChat source checks: 2026-10-21 to 2026-10-26. - Open WebUI source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/librechat-vs-open-webui/ - Machine-readable JSON: https://onaihq.com/compare/agents/librechat-vs-open-webui/data.json - Methodology: https://onaihq.com/compare/agents/methodology/ ## Models ### MOD-01: Model catalogue and providers Judgment rule: List each available model by provider and plan, including reasoning, fast and multimodal variants. Record whether the user picks the model, the product routes automatically, or both. A provider counts only if at least one of its current models is selectable on the scoped plan. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The model catalog is configured by the customer across first-party provider integrations and custom endpoints. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - providers: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. - current_models: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. - auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. - providers — Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - current_models — Which current models are selectable on this plan? [partial]: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. Sources: librechat:librechat:releases. - user_choice — Can users pick the model per chat? [supported]: Users choose an endpoint/model unless admins enforce model specs or a fixed Agent. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [unknown]: auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input — Which models accept images, audio or files? [partial]: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. Sources: librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customers connect local servers and cloud model endpoints and choose models in chat. The available catalog depends on their endpoints and credentials. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - providers: Documented routes include OpenAI, Anthropic, Azure OpenAI, Mistral, DeepSeek and gateways such as OpenRouter; models must be enabled in the connected account. No endpoint was exercised. - current_models: Which current models are selectable on this plan? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - auto_routing: Does the product route between models automatically, and is the chosen model shown? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - multimodal_input: Vision and file context depend on the chosen model and configured extraction. No model-by-model audio/image acceptance matrix or fixture run was established. - providers — Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Azure OpenAI, Mistral, DeepSeek and gateways such as OpenRouter; models must be enabled in the connected account. No endpoint was exercised. Sources: open-webui:open-webui:provider, open-webui:open-webui:compat. - current_models — Which current models are selectable on this plan? [unknown]: current_models: Which current models are selectable on this plan? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - user_choice — Can users pick the model per chat? [supported]: Users select connected models in the chat selector and can compare several models. Sources: open-webui:open-webui:provider. - 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? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - multimodal_input — Which models accept images, audio or files? [partial]: Vision and file context depend on the chosen model and configured extraction. No model-by-model audio/image acceptance matrix or fixture run was established. Sources: open-webui:open-webui:rag, open-webui:open-webui:extraction. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:provider, open-webui:open-webui:compat, open-webui:open-webui:rag, open-webui:open-webui:extraction ### MOD-02: Model freshness Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - changelog — Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases. - deprecation_notice — How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning — Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated upstream releases are public. A measured three-release availability lag and model retirement notice remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - changelog: GitHub release notes are dated and sometimes mention model/protocol changes; they are not a complete provider model availability timeline. - deprecation_notice: How much notice is given before a model is removed? No matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - version_pinning: An admin can list explicit provider model/deployment IDs and keep a chosen local model. Provider removal still controls remote model availability. - 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 matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - changelog — Is there a dated public model changelog? [partial]: GitHub release notes are dated and sometimes mention model/protocol changes; they are not a complete provider model availability timeline. Sources: open-webui:open-webui: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 matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - version_pinning — Can an admin keep an older model version? [partial]: An admin can list explicit provider model/deployment IDs and keep a chosen local model. Provider removal still controls remote model availability. Sources: open-webui:open-webui:openai, open-webui:open-webui:provider. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:releases, open-webui:open-webui:openai, open-webui:open-webui:provider ### MOD-03: Bring-your-own keys and provider contracts Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. - own_api_keys — Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom. - byo_pricing — Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat. - byo_restrictions — Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-held keys, Azure deployments and compatible endpoints are documented. The standard software licence does not include provider usage. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Customer provider accounts or separately operated compatible gateway; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - byo_restrictions: Compatibility and tools depend on the provider protocol and model. The sources do not promise identical functionality across all BYO endpoints. - own_api_keys — Can the customer use its own provider API keys? [supported]: Administrators supply customer provider keys in Connections. Sources: open-webui:open-webui:openai, open-webui:open-webui:compat. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Azure OpenAI is documented using the customer Azure endpoint, deployment names and API key. Bedrock is also documented through a compatible route; Vertex contract behavior was not separately verified. Sources: open-webui:open-webui:openai, open-webui:open-webui:compat. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Administrators can set an OpenAI-compatible base URL and credentials. Sources: open-webui:open-webui:compat. - byo_pricing — Does BYO change the licence price? [supported]: Branding-intact standard use is free; external provider bills and optional Enterprise rights are separate. Sources: open-webui:open-webui:enterprise. - byo_restrictions — Which features stop working with BYO? [partial]: Compatibility and tools depend on the provider protocol and model. The sources do not promise identical functionality across all BYO endpoints. Sources: open-webui:open-webui:compat, open-webui:open-webui:models. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:openai, open-webui:open-webui:compat, open-webui:open-webui:enterprise, open-webui:open-webui:models ### MOD-04: Local and self-hosted models Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg. - feature_parity — Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code. - vendor_hosted_open_models — Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Ollama, llama.cpp and vLLM are documented local inference routes; local retrieval requires local embedding and extraction services. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - feature_parity: Local chat and RAG are possible. Tool reliability depends on model support, and online search, remote providers or cloud OCR require network access. No parity fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? No first-party commitment to vendor-operated open-weight inference in EU or Switzerland was established in the deployment and provider guides. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Chat can use customer-operated Ollama, llama.cpp or vLLM endpoints. Sources: open-webui:open-webui:provider. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: Retrieval can use local embedding models; the offline guide requires these assets to be downloaded before disconnecting. Sources: open-webui:open-webui:rag, open-webui:open-webui:offline. - feature_parity — Which features fail with self-hosted models? [partial]: Local chat and RAG are possible. Tool reliability depends on model support, and online search, remote providers or cloud OCR require network access. No parity fixture was run. Sources: open-webui:open-webui:offline, open-webui:open-webui:memory. - 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 first-party commitment to vendor-operated open-weight inference in EU or Switzerland was established in the deployment and provider guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:provider, open-webui:open-webui:rag, open-webui:open-webui:offline, open-webui:open-webui:memory ### MOD-05: Model control and usage limits Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. - data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. - model_allowlist_by_group — Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - default_model — Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec. - user_limits — What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod. - limit_behaviour — What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial User/group model grants are documented. Optional custom filters can limit request rates; built-in recurring token/message quotas and monetary budgets remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New extension/locale findings inspected at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16; earlier accepted documented facts retained; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - data_bound_models: Knowledge attached to a model scopes its retrieval, while user/resource grants control access. This does not establish a hard policy binding each source to an allowed outbound provider. - user_limits: What per-user message or token limits apply, and are they published? No configured quota or bounded two-user enforcement test was run; budget controls remain in progress on the public roadmap. - limit_behaviour: What happens when a limit is reached? No configured quota or bounded two-user enforcement test was run; budget controls remain in progress on the public roadmap. - model_allowlist_by_group — Can admins limit models per group? [supported]: Private model grants can be assigned to users and groups. Permissions accumulate, so a second group may grant access. Sources: open-webui:open-webui:groups. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [partial]: Knowledge attached to a model scopes its retrieval, while user/resource grants control access. This does not establish a hard policy binding each source to an allowed outbound provider. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:privacy. - default_model — Can admins set the default model? [supported]: The groups guide documents default models per group. Sources: open-webui:open-webui:groups. - user_limits — What per-user message or token limits apply, and are they published? [partial]: An optional official Filter example implements configurable requests per user per minute. It is customer-installed code with process-local counters, not an enabled recurring message/token allowance or monetary budget. No configured deployment was tested. Sources: open-webui:open-webui:r4-rate-limit-example, open-webui:open-webui:r4-filter-implementation. - limit_behaviour — What happens when a limit is reached? [partial]: The optional rate-limit example rejects an inlet request by raising an exception at its per-minute threshold; the inspected backend propagates inlet failures. Distributed enforcement, persistent quota balances and monetary overshoot behavior remain unverified. Sources: open-webui:open-webui:r4-rate-limit-example, open-webui:open-webui:r4-filter-implementation. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:groups, open-webui:open-webui:knowledge, open-webui:open-webui:privacy, open-webui:open-webui:r4-rate-limit-example, open-webui:open-webui:r4-filter-implementation ## Company knowledge ### KNOW-01: Files in chat Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Files can be indexed, injected as extracted text or sent directly to compatible model providers. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - File counts, sizes and provider acceptance depend on deployment settings. - Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested. - formats — Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg. - limits — What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr. - ocr — Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr. - spreadsheets — Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Documents can be attached and parsed for RAG or full-context injection. Scans depend on extraction configuration; spreadsheet fidelity was not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - formats: PDF and common text/Office documents are documented; parser choice controls formats. Temporary browser-only extraction has DOCX limitations. - ocr: Scanned PDFs can use a configured OCR-capable engine. No scanned fixture was tested. - spreadsheets: Are Excel tables read with structure intact? The shared Excel/formula, scanned contract and long-document fixtures were not uploaded, so structure preservation and observed failures are unknown. - formats — Which formats are accepted? [partial]: PDF and common text/Office documents are documented; parser choice controls formats. Temporary browser-only extraction has DOCX limitations. Sources: open-webui:open-webui:extraction, open-webui:open-webui:rag. - limits — What size and count limits apply per file and chat? [supported]: Administrators configure maximum document MB, upload count and allowed extensions with RAG_FILE_MAX_SIZE, RAG_FILE_MAX_COUNT and RAG_ALLOWED_FILE_EXTENSIONS; these are instance settings rather than a universal vendor allowance. Sources: open-webui:open-webui:env. - ocr — Are scanned PDFs read? [partial]: Scanned PDFs can use a configured OCR-capable engine. No scanned fixture was tested. Sources: open-webui:open-webui:extraction. - spreadsheets — Are Excel tables read with structure intact? [unknown]: spreadsheets: Are Excel tables read with structure intact? The shared Excel/formula, scanned contract and long-document fixtures were not uploaded, so structure preservation and observed failures are unknown. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: Users can select focused chunk retrieval or entire-document context; attached model knowledge has mode-specific behavior described in the guide. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:rag. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:extraction, open-webui:open-webui:rag, open-webui:open-webui:env, open-webui:open-webui:knowledge ### KNOW-02: Knowledge bases and shared collections Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. - size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - persistent_collections — Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - assistant_binding — Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Knowledge bases persist across chats and can attach to a model or conversation, with user/group/public sharing. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - size_limits: What are the collection limits? No fixed collection capacity was established; limits depend on operator configuration, storage and the selected database. - persistent_collections — Can users keep document collections across chats? [supported]: Knowledge bases store reusable document collections across chats. Sources: open-webui:open-webui:knowledge. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [supported]: Private knowledge resources can grant read/write access to named users and groups, or be public within the instance. Sources: open-webui:open-webui:groups, open-webui:open-webui:knowledge. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No fixed collection capacity was established; limits depend on operator configuration, storage and the selected database. - assistant_binding — Can collections be bound to an assistant? [supported]: A model preset can bind one or more knowledge bases. Sources: open-webui:open-webui:models, open-webui:open-webui:knowledge. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:groups, open-webui:open-webui:models ### KNOW-03: Enterprise connectors Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02). #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. - google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint. - google_workspace — Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian — Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems — Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg. - connector_provider — Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native file pickers and the separately operated official oikb companion provide different connector paths, including oikb Teams and Gmail sync. Source permission preservation remains untested. Availability: generally-available Delivery: official-integration Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Microsoft/Google application registration for native file pickers, Separately deployed official oikb, Open WebUI 0.9.6+ and a user API key, Source credentials: Teams tenant/client/secret; Gmail Google credentials and the optional gmail extra; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - Teams/Gmail are oikb companion connectors, not native per-user live file pickers. - Operator setup, source credentials and source-specific consent are required; permissions after indexing/revocation were not tested. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: Native OneDrive for Business/SharePoint pickers require delegated application permissions and admin consent. Separately, oikb lists SharePoint and Teams; Teams uses TEAMS_TENANT_ID, TEAMS_CLIENT_ID and TEAMS_CLIENT_SECRET. This is a companion sync path. Outlook, exact Teams consent scopes and source-ACL preservation were not verified. Sources: open-webui:open-webui:onedrive, open-webui:open-webui:sync-connectors-r2. - google_workspace — Which Google sources are connected? [partial]: The native Drive picker imports selected files. Separately, official oikb lists Google Drive and Gmail using GOOGLE_APPLICATION_CREDENTIALS; Gmail has an optional installation extra. Mailbox delegation/consent scope and continuing source-ACL preservation were not tested. Sources: open-webui:open-webui:rag, open-webui:open-webui:sync-connectors-r2. - atlassian — Confluence and Jira? [partial]: Official companion oikb lists Confluence and Jira. Its separate credentials, runtime and source-specific configuration are required; source-permission sync was not verified. Sources: open-webui:open-webui:sync. - other_systems — Which other business systems? [partial]: oikb lists GitHub, Notion, Slack and S3 among its sources; these are copied-content integrations rather than native per-user live search. Sources: open-webui:open-webui:sync. - on_prem_sources — Can on-prem file shares or databases be connected? [supported]: A local folder can be mirrored using directory sync or the separate oikb tool. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:sync. - connector_provider — Who builds and maintains each connector? [supported]: Open WebUI documents the native file pickers and maintains the official, separately installed oikb companion. MCP/OpenAPI connectors depend on their own maintainers and credentials. Sources: open-webui:open-webui:onedrive, open-webui:open-webui:rag, open-webui:open-webui:sync-connectors-r2, open-webui:open-webui:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:onedrive, open-webui:open-webui:sync-connectors-r2, open-webui:open-webui:rag, open-webui:open-webui:sync, open-webui:open-webui:knowledge, open-webui:open-webui: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. #### 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 #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Open WebUI knowledge-resource grants are documented. Enforcement of the original enterprise source permissions after copying has not passed the required test. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - source_permissions_respected: Are source permissions enforced per user? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - enforcement_point: Open WebUI resource grants govern access to its knowledge bases. Microsoft delegated permission limits the picker at import time; continuing source-system checks for the copied content were not established. - revocation_delay: How quickly does a removed permission take effect? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - admin_scope_controls: Admins choose knowledge grants and which collections a model uses. Source site/folder/label exclusion and label propagation need connector-specific verification. - sensitivity_labels: Are Microsoft Purview or similar labels respected? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - source_permissions_respected — Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: Open WebUI resource grants govern access to its knowledge bases. Microsoft delegated permission limits the picker at import time; continuing source-system checks for the copied content were not established. Sources: open-webui:open-webui:groups, open-webui:open-webui:onedrive. - revocation_delay — How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Admins choose knowledge grants and which collections a model uses. Source site/folder/label exclusion and label propagation need connector-specific verification. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:groups. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:groups, open-webui:open-webui:onedrive, open-webui:open-webui:knowledge ### KNOW-05: Freshness and sync model Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - live_or_indexed — Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr. - sync_interval — How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - index_location — Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Uploaded knowledge is copied into an operator-selected index. Manual directory sync or a separate daemon updates it. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - sync_interval: Directory sync runs when invoked; oikb offers scheduled/on-demand synchronization. No universal connector interval or SLA applies. - deletion_propagation: Directory sync removes files missing from the local manifest during cleanup. Elapsed propagation time was not measured. - live_or_indexed — Is content searched live or copied into an index? [supported]: Uploaded documents are parsed and indexed; an experimental external-vector-source mode queries a pre-existing customer index without re-ingestion. Sources: open-webui:open-webui:rag, open-webui:open-webui:knowledge. - sync_interval — How often does an index refresh? [partial]: Directory sync runs when invoked; oikb offers scheduled/on-demand synchronization. No universal connector interval or SLA applies. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:sync. - deletion_propagation — How quickly does a deleted document disappear? [partial]: Directory sync removes files missing from the local manifest during cleanup. Elapsed propagation time was not measured. Sources: open-webui:open-webui:knowledge. - index_location — Where is indexed content stored? [supported]: The operator selects the database or external vector source and its deployment location; there is no fixed vendor region for this self-hosted scope. Sources: open-webui:open-webui:rag, open-webui:open-webui:privacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:rag, open-webui:open-webui:knowledge, open-webui:open-webui:sync, open-webui:open-webui:privacy ### KNOW-06: Grounding and retrieval quality Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial File-search citations are documented; retrieval accuracy remains unmeasured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - citations — Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language — Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy — How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Citations are documented; citation accuracy and multilingual retrieval outcomes are untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - cross_language: Does a question in one language find documents in another? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - no_answer_behaviour: Does it say when the corpus has no answer? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - observed_accuracy: How many of the question set were answered correctly? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - citations — Are answers linked to specific sources? [supported]: RAG answers can include source references; chunk metadata may add details such as page numbers. Sources: open-webui:open-webui:rag. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - 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 corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - 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 DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - 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 corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:rag ### KNOW-07: Memory and personal context Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents. - cross_chat_memory — Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can manage persistent memory and admins can disable or group-restrict it. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - custom_instructions: Model presets provide persistent system instructions and users can save instructions as memory. A separate personal-instructions setting was not inspected here. - custom_instructions — Can users set persistent instructions? [partial]: Model presets provide persistent system instructions and users can save instructions as memory. A separate personal-instructions setting was not inspected here. Sources: open-webui:open-webui:models, open-webui:open-webui:memory. - cross_chat_memory — Does the product remember facts across chats? [supported]: User-scoped memories carry facts and preferences between conversations. Sources: open-webui:open-webui:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Settings permits adding, editing and deleting memories. Sources: open-webui:open-webui:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Global and per-group switches disable memory access and server-side context use. Sources: open-webui:open-webui:memory. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:memory ## Assistants and agents ### AGT-01: Custom assistants Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents. - creator_permissions — Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access. - catalogue — Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents. - prompt_library — Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: supported Model presets are reusable assistants combining instructions, a base model, knowledge and tools. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: The Models workspace creates presets with instructions, knowledge, tools, skills and parameters. Sources: open-webui:open-webui:models. - creator_permissions — Can admins limit who creates them? [supported]: Workspace permission toggles control who can create resources. Sources: open-webui:open-webui:permissions. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Model grants may target users, groups or public instance visibility. Sources: open-webui:open-webui:groups, open-webui:open-webui:models. - catalogue — Is there an internal assistant directory? [supported]: The Models workspace lists available presets and model selectors expose those the user can access. Sources: open-webui:open-webui:models. - prompt_library — Are shared prompt templates available? [supported]: Workspace prompt permissions cover creating and sharing reusable prompt resources. Sources: open-webui:open-webui:permissions. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:permissions, open-webui:open-webui:groups ### AGT-02: Tools, actions and MCP Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. - builtin_tools — Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images. - custom_actions — Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_auth — Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native/custom tools and MCP are documented. The optional interactive Tool Permissions approval mode is experimental and off by default; automations and channel replies bypass it. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current Tools/MCP documentation retrieved 2026-10-21; beta availability qualifies the optional experimental approval mode, not all tool integrations; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Optional separately operated MCP/OpenAPI tool servers or stdio bridge; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - The row uses beta for the experimental approval subfeature; ordinary tool integrations are documented separately. - Approval is opt-in for interactive chats and is bypassed in automations/channel replies; no mandatory side-effect policy was established. - builtin_tools — Which tools are built in? [supported]: Knowledge, memory, web and other built-in tool categories are configured per model. Sources: open-webui:open-webui:models. - custom_actions — Can admins add API actions? [supported]: Admins can install Python tools or connect OpenAPI tool servers. Sources: open-webui:open-webui:tools. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: The dedicated current guide documents admin-configured Streamable HTTP MCP. Local stdio requires a separately deployed bridge such as mcpo. Sources: open-webui:open-webui:mcp, open-webui:open-webui:tools. - tool_auth — Do tools act as the user or as a shared account? [supported]: Configured modes include bearer credentials and user OAuth/OAuth 2.1; the resulting access depends on the server and granted scopes. Sources: open-webui:open-webui:mcp. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Admins control tool access and may enable experimental Tool Permissions (off by default). Interactive users can select Ask for approval with sequential Allow/Deny prompts; Full access remains the default. Automations and channel replies always use full access. A mandatory policy for every side effect and an external-call boundary fixture were not verified. Sources: open-webui:open-webui:approvals-r2, open-webui:open-webui:groups. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:tools, open-webui:open-webui:mcp, open-webui:open-webui:approvals-r2, open-webui:open-webui:groups ### AGT-03: Web search and deep research Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. - web_search — Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents. - admin_toggle — Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web. - search_provider — Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web. - deep_research — Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web. - web_citations — Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Search and multi-step page research are documented and require an external search provider or local metasearch deployment. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - search_provider: Provider choice includes external search services and self-operated options. The actual provider region and query processing contract depend on the chosen service. - deep_research: Native function calling can perform repeated search and URL fetching. No bounded research-report task was exercised. - web_search — Is web search available? [supported]: Admins configure web search and users can enable it in a chat. Sources: open-webui:open-webui:web. - admin_toggle — Can admins disable it per organisation or group? [supported]: Feature permissions grant web search per group; global configuration can turn it off. Sources: open-webui:open-webui:permissions, open-webui:open-webui:web. - search_provider — Which search provider handles queries, and where? [partial]: Provider choice includes external search services and self-operated options. The actual provider region and query processing contract depend on the chosen service. Sources: open-webui:open-webui:web, open-webui:open-webui:offline. - deep_research — Is multi-step research with a report available? [partial]: Native function calling can perform repeated search and URL fetching. No bounded research-report task was exercised. Sources: open-webui:open-webui:agent-search. - web_citations — Are web sources cited? [supported]: Retrieved web sources are exposed as conversation references/citations. Sources: open-webui:open-webui:agent-search. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:web, open-webui:open-webui:permissions, open-webui:open-webui:offline, open-webui:open-webui:agent-search ### AGT-04: Workflows and automation Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. - event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. - workflow_builder — Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule. - event_triggers — Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Recurring prompts execute on the operator’s server. Developer extensions can add chains; a business workflow builder was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New extension/locale findings inspected at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16; earlier accepted documented facts retained; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - workflow_builder: Is there a workflow or chain builder? The automation, tool and webhook documentation did not establish a complete business workflow builder or incoming email/form event trigger contract. - event_triggers: Can external events start a workflow? The automation, tool and webhook documentation did not establish a complete business workflow builder or incoming email/form event trigger contract. - builder_audience: Schedules use a user-facing editor; custom Python tools and integrations require technical operators. No general no-code multi-system workflow designer was verified. - workflow_builder — Is there a workflow or chain builder? [unknown]: workflow_builder: Is there a workflow or chain builder? The automation, tool and webhook documentation did not establish a complete business workflow builder or incoming email/form event trigger contract. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Automations support hourly/daily/weekly/monthly and RRULE schedules, manual runs, pause and execution history. Sources: open-webui:open-webui:automation. - event_triggers — Can external events start a workflow? [partial]: A token-validated channel webhook publishes a message-created event that configured Python Event functions can handle. Developers must supply the downstream workflow logic; an incoming email/form connector or no-code multi-system workflow contract was not established. Sources: open-webui:open-webui:r4-incoming-channel-webhook, open-webui:open-webui:r4-event-dispatch. - builder_audience — Is building aimed at business users, IT or developers? [partial]: Schedules use a user-facing editor; custom Python tools and integrations require technical operators. No general no-code multi-system workflow designer was verified. Sources: open-webui:open-webui:automation, open-webui:open-webui:tools. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:automation, open-webui:open-webui:tools, open-webui:open-webui:r4-incoming-channel-webhook, open-webui:open-webui:r4-event-dispatch ### AGT-05: Agentic task execution Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - No gather-documents, draft-summary and propose-email task was run. - Highly experimental attached workspaces are distinct from ordinary Agent tool use. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code. - visible_steps — Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code. - stop_control — Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native tool calls and optional Open Terminal support agent tasks. Interactive tool approval is experimental and off by default, and never gates scheduled automations or channel replies. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current Tools/Open Terminal documentation retrieved 2026-10-21; beta availability qualifies optional experimental approvals; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Optional separately deployed Open Terminal; Terminals orchestration is a separate component with unverified pinned licence terms; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - Beta availability refers to optional experimental approvals; the documented native tool mode is separate. - Automations and channel replies always use full access. - No gather-documents, draft-summary and propose-email fixture or background cancellation test was run. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Tool-capable models can use knowledge and external tools; separately connected Open Terminal adds file and command execution. Sources: open-webui:open-webui:models, open-webui:open-webui:terminal. - visible_steps — Are steps and tool calls shown? [supported]: Interactive tool calls display their results and, when experimental Ask for approval is enabled, pending/allowed/denied state. Sources: open-webui:open-webui:approvals-r2. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Experimental Tool Permissions is disabled by default and users must select Ask for approval. Full access executes immediately; automations and channel replies always bypass approval. The documented control is not a mandatory confirmation policy for every side effect. Sources: open-webui:open-webui:approvals-r2. - stop_control — Can the user stop a running task? [partial]: In an interactive reply waiting for approval, Stop finalizes the reply and denies pending calls. This is a pending-call control; cancellation of background tasks and effects already executed was not tested. Sources: open-webui:open-webui:approvals-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:terminal, open-webui:open-webui:approvals-r2 ### AGT-06: Programmable access Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. - api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. - mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. - chat_api — Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api. - knowledge_api — Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Authenticated APIs cover chat, models and knowledge ingestion; product RBAC applies to API users. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - api_governance: API users use their account permissions; optional audit capture can log requests. Enforced spend budgets and full API/UI parity were not demonstrated. - mcp_server: Does the product expose itself to other agents over MCP? No supported native MCP server exposing the whole product was established in the API and MCP-client guides. - chat_api — Is there an API for chat and assistants? [supported]: OpenAI-compatible chat completion and model management endpoints accept API keys or session JWTs. Sources: open-webui:open-webui:api. - knowledge_api — Can documents be loaded through an API? [supported]: File upload and knowledge attachment are documented APIs. Sources: open-webui:open-webui:api, open-webui:open-webui:knowledge. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: API users use their account permissions; optional audit capture can log requests. Enforced spend budgets and full API/UI parity were not demonstrated. Sources: open-webui:open-webui:api, open-webui:open-webui:hardening. - 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? No supported native MCP server exposing the whole product was established in the API and MCP-client guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:api, open-webui:open-webui:knowledge, open-webui:open-webui:hardening ## Daily work ### WORK-01: Clients and access points Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. - browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. - web — Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local. - desktop_apps — Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps — iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights. - browser_extension — Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps — Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The web/PWA client is complemented by a separate native Desktop distribution for macOS, Windows and Linux. Desktop is explicitly Early Alpha; SSO/MDM and cross-client parity were not tested. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server, Open WebUI Desktop native distribution (Early Alpha); version=Web/PWA documentation retrieved 2026-10-21; Desktop v0.0.20 / 601137c5dec2967cfe173a6bf071fbbb460852be (released 2026-05-06, labelled Early Alpha); plan=Customer-operated web/PWA plus the separately packaged Open WebUI Desktop distribution; production Quick Start recommends Docker or Python; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=Windows, macOS, Linux, iOS (PWA), Android (PWA). Limitations: - Beta availability reflects the Early Alpha desktop distribution; the browser/PWA route is separate. - Native mobile clients, corporate SSO, MDM/Intune deployment and client parity were not tested. - web — Is a full web client available? [supported]: The deployed server supplies the full browser client; Quick Start also links the separate desktop distribution. Sources: open-webui:open-webui:desktop-quickstart-r2. - desktop_apps — Windows and macOS apps? [partial]: Open WebUI Desktop v0.0.20 provides native macOS (Apple Silicon/Intel), Windows (x64/ARM64) and Linux installers. It can run locally without Docker or connect to an existing server. It is labelled Early Alpha; first launch requires internet. Enterprise SSO and managed rollout were not tested. Sources: open-webui:open-webui:desktop-readme-r2, open-webui:open-webui:desktop-release-r2, open-webui:open-webui:desktop-quickstart-r2. - mobile_apps — iOS and Android apps with SSO? [partial]: Android browsers and iOS Safari can install the PWA. Native mobile app-store clients and mobile company-SSO/MDM behavior were not verified. Sources: open-webui:open-webui:pwa-r2. - browser_extension — Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? No first-party managed MDM/Intune deployment policy or Office/browser sidebar extension was established in the client guide. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? No first-party managed MDM/Intune deployment policy or Office/browser sidebar extension was established in the client guide. - client_feature_gaps — Which features are missing on mobile? [partial]: PWA notifications need the app to remain open. Desktop is Early Alpha and Quick Start recommends Docker/Python for production; no desktop/mobile feature-parity or enterprise SSO matrix was verified. Sources: open-webui:open-webui:pwa-r2, open-webui:open-webui:desktop-readme-r2, open-webui:open-webui:desktop-quickstart-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:desktop-quickstart-r2, open-webui:open-webui:desktop-readme-r2, open-webui:open-webui:desktop-release-r2, open-webui:open-webui:pwa-r2 ### WORK-02: Office suite and Teams integration Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02. #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### Open WebUI 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. #### 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. #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial AI editing is documented in Notes. Dedicated layout-preserving translation and glossary behavior remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - document_translation: Can whole documents be translated with formatting kept? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - translation_engine: Notes sends rewrite requests to the selected model. A dedicated translation service or whole-document translation workflow was not established. - glossaries: Are company glossaries supported? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - formality_and_variants: Can formality and regional variants (de-CH) be set? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - document_translation — Can whole documents be translated with formatting kept? [unknown]: document_translation: Can whole documents be translated with formatting kept? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - translation_engine — Which engine translates? [partial]: Notes sends rewrite requests to the selected model. A dedicated translation service or whole-document translation workflow was not established. Sources: open-webui:open-webui:notes. - glossaries — Are company glossaries supported? [unknown]: glossaries: Are company glossaries supported? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - 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 DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - writing_tools — Are dedicated rewrite and proofreading tools available? [supported]: The Notes editor supports AI rewriting and improving selected text. Sources: open-webui:open-webui:notes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:notes ### WORK-04: Image generation and editing Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured Agent image tools generate and edit images; model service rights/costs remain separate. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. - usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. - image_generation — Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images. - image_editing — Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images. - admin_control — Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured image engines generate and edit uploaded images, subject to feature permissions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - usage_terms: What usage rights apply to output? Output rights and actual per-image costs depend on the chosen image service and were not established as a single Open WebUI entitlement. - image_generation — Can users generate images, with which models? [supported]: OpenAI, Gemini, ComfyUI and AUTOMATIC1111 are documented engine routes; exact models are operator-configured. Sources: open-webui:open-webui:images. - image_editing — Can users edit uploaded images? [supported]: The usage guide documents uploaded-image edits and multi-image compositing with an enabled editing engine. Sources: open-webui:open-webui:image-usage. - admin_control — Can admins restrict image generation? [supported]: Global image configuration, feature permission and model capability govern availability. Sources: open-webui:open-webui:image-usage. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Output rights and actual per-image costs depend on the chosen image service and were not established as a single Open WebUI entitlement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:images, open-webui:open-webui:image-usage ### WORK-05: Voice and meetings Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified. Limitations: - Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified. - Audio location depends on the chosen engine. No meeting or Swiss German fixture was run. - dictation — Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech. - read_aloud — Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech. - voice_conversation — Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2 #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dictation, read-aloud and voice conversation use configured audio services. Swiss German recognition and a meeting workflow were not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - meeting_summaries: Are meetings transcribed and summarised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. - swiss_german_speech: Is Swiss German speech recognised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. - dictation — Can users dictate prompts? [supported]: Audio configuration supports speech-to-text for prompts. Sources: open-webui:open-webui:env. - read_aloud — Can answers be read aloud? [supported]: Standard voice reads replies using the configured TTS engine, including browser options. Sources: open-webui:open-webui:voice. - voice_conversation — Is a live voice mode available? [supported]: Standard STT/TTS voice mode and separately configured realtime API calls are documented. Sources: open-webui:open-webui:voice. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: meeting_summaries: Are meetings transcribed and summarised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: swiss_german_speech: Is Swiss German speech recognised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:env, open-webui:open-webui:voice ### WORK-06: Data analysis and document output Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. - office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. - canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code. - charts — Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Open Terminal runs analysis code and creates artifacts; Notes provides document editing. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Separately operated Open Terminal and document libraries; Enterprise Terminals optional; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - office_file_output: The runtime can process Office files and create downloadable files through code and installed packages. Editable DOCX/XLSX/PPTX output was not verified with the shared fixture. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Open Terminal documents spreadsheet/CSV inspection and code-based data analysis on the separately deployed runtime. Sources: open-webui:open-webui:terminal. - charts — Can it produce charts? [supported]: Its data-analysis workflow includes generated charts and report artifacts. Sources: open-webui:open-webui:terminal. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: The runtime can process Office files and create downloadable files through code and installed packages. Editable DOCX/XLSX/PPTX output was not verified with the shared fixture. Sources: open-webui:open-webui:terminal. - canvas_editing — Is there a document or canvas editor for iterating on output? [supported]: Notes offers a rich text and Markdown editor with AI rewrites. Sources: open-webui:open-webui:notes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:terminal, open-webui:open-webui:notes ### WORK-07: Sharing and team spaces Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. - share_chats — Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share. - team_spaces — Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects. - group_chat — Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Chats, shared resources and multi-person channels are documented. Recipient source-access boundaries were not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - team_spaces: Groups organize shared models/knowledge and channels organize collaboration. This is not evidence of separate legal-entity tenancy. - share_permission_boundary: Does sharing respect the recipient's access to sources? No colleague-in-another-group chat-sharing fixture was run; transcript sharing may reveal already included content independently of original source access. - share_chats — Can chats be shared inside the organisation? [supported]: Chat sharing is a configurable permission and users can manage shared chats. Sources: open-webui:open-webui:permissions, open-webui:open-webui:export. - team_spaces — Are shared projects or workspaces available? [partial]: Groups organize shared models/knowledge and channels organize collaboration. This is not evidence of separate legal-entity tenancy. Sources: open-webui:open-webui:groups, open-webui:open-webui:channels. - group_chat — Can several people chat together with the AI? [supported]: Channels support multiple members and AI participation. Sources: open-webui:open-webui:channels. - share_permission_boundary — Does sharing respect the recipient's access to sources? [unknown]: share_permission_boundary: Does sharing respect the recipient's access to sources? No colleague-in-another-group chat-sharing fixture was run; transcript sharing may reveal already included content independently of original source access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:permissions, open-webui:open-webui:export, open-webui:open-webui:groups, open-webui:open-webui:channels ### WORK-08: Interface languages and accessibility Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial English, German, French and Italian UI resources are registered in the pinned client; quality and accessibility conformance were not evaluated. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - ui_languages — Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages — Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial English, German, French and Italian locales are present in the pinned client. Completeness, naturalness and WCAG conformance are unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New extension/locale findings inspected at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16; earlier accepted documented facts retained; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - accessibility_statement: Is there a WCAG conformance statement? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - admin_ui_languages: Is the admin interface available in German? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - ui_languages — Which UI languages are offered? [supported]: The locale registry includes en-US/en-GB, de-DE, fr-FR and it-IT among other languages. Sources: open-webui:open-webui: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? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - admin_ui_languages — Is the admin interface available in German? [partial]: The pinned German locale includes Admin Panel, user-management and settings labels. Full admin-screen translation coverage and naturalness were not observed; the public roadmap still lists full internationalization as planned. Sources: open-webui:open-webui:r4-german-admin-translations. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:i18n-pin, open-webui:open-webui:r4-german-admin-translations ## Administration and governance ### ADM-01: Single sign-on and authentication Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. - domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth. - sso_plan — Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth. - mfa — Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth. - conditional_access — Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial OAuth/OIDC, trusted-header and directory authentication are documented; standard self-hosting includes configuration access. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - conditional_access: The privacy guide recommends enforcing MFA, conditional access and device posture at the identity provider. No Entra sign-in fixture was run. - domain_capture: Can the company claim its email domain? Email-domain filtering settings do not establish enterprise domain ownership capture; this was not verified. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OAuth/OIDC includes Microsoft, Google and generic providers; trusted-header proxies and LDAP are documented. Direct SAML was not established. Sources: open-webui:open-webui:sso, open-webui:open-webui:roles. - sso_plan — Which plan includes SSO? [supported]: The public self-hosted authentication configuration is available under standard use, with no separately listed SSO charge. Sources: open-webui:open-webui:sso, open-webui:open-webui:enterprise. - mfa — Can MFA be enforced? [supported]: Admins can enable built-in authenticator-based MFA and choose whether OAuth may bypass it. Sources: open-webui:open-webui:mfa. - conditional_access — Do Entra conditional-access policies apply? [partial]: The privacy guide recommends enforcing MFA, conditional access and device posture at the identity provider. No Entra sign-in fixture was run. Sources: open-webui:open-webui:privacy. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Email-domain filtering settings do not establish enterprise domain ownership capture; this was not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:sso, open-webui:open-webui:roles, open-webui:open-webui:enterprise, open-webui:open-webui:mfa, open-webui:open-webui:privacy ### ADM-02: User provisioning and lifecycle Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. - seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. - scim — Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - group_sync — Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra. - jit_provisioning — Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth. - seat_assignment — Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial SCIM and login-time identity groups are documented; content ownership after removing a user needs further verification. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=SCIM bearer-token authentication rechecked at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16 and current guide on 2026-10-26; other accepted identity facts retain their own cited versions; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - deprovisioning: SCIM active=false maps ordinary users to pending and disconnects live sessions. Asset transfer and retained shared content were not fixture-tested. - seat_assignment: Administrators control user accounts and roles. Standard use has no paid per-seat licence assignment mechanism to price; Enterprise entitlements were not reviewed. - No user-selectable token-scope control was established from the current SCIM guide or pinned authentication path. - scim — Is SCIM provisioning supported? [supported]: SCIM 2.0 provisions/deactivates users and manages groups when enabled through SCIM_ENABLED and authenticated with the configured SCIM_TOKEN bearer token. The documented configuration does not expose user-selectable token scopes. Sources: open-webui:open-webui:r7-scim-bearer-doc, open-webui:open-webui:r7-scim-bearer-code. - group_sync — Are identity-provider groups synced? [supported]: OAuth group management syncs claims at sign-in; SCIM also manages memberships. Sources: open-webui:open-webui:sso, open-webui:open-webui:scim. - jit_provisioning — Are users created at first login? [supported]: OAuth account creation and optional JIT group creation can be enabled. Sources: open-webui:open-webui:sso. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: SCIM active=false maps ordinary users to pending and disconnects live sessions. Asset transfer and retained shared content were not fixture-tested. Sources: open-webui:open-webui:scim. - seat_assignment — Can admins assign and reclaim seats? [partial]: Administrators control user accounts and roles. Standard use has no paid per-seat licence assignment mechanism to price; Enterprise entitlements were not reviewed. Sources: open-webui:open-webui:roles, open-webui:open-webui:enterprise. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:scim, open-webui:open-webui:sso, open-webui:open-webui:roles, open-webui:open-webui:enterprise, open-webui:open-webui:r7-scim-bearer-doc, open-webui:open-webui:r7-scim-bearer-code ### ADM-03: Roles, groups and feature permissions Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Separate admin management UI is preview; the core authorization model is documented as available. - No two-group disabled-feature fixture was run. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access. - groups — Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin. - feature_toggles — Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Roles and additive groups provide feature and resource permissions; separate instances remain the documented stronger trust boundary. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - admin_roles: Admin, User and Pending are system roles. Admin access can be reduced by product flags, but a least-privilege delegated-admin role matrix was not established. - multi_entity: Groups can organize departments; the privacy guide recommends separate instances/databases/operators for distinct trust boundaries. A multi-entity commercial contract was not reviewed. - admin_roles — Which admin roles exist, and can admin rights be delegated? [partial]: Admin, User and Pending are system roles. Admin access can be reduced by product flags, but a least-privilege delegated-admin role matrix was not established. Sources: open-webui:open-webui:roles. - groups — Can permissions be set per group? [supported]: User/group resource grants and additive feature permissions are documented. Sources: open-webui:open-webui:groups. - feature_toggles — Which features can be switched on or off per group? [supported]: Permissions cover web search, images, files, model creation, tools, knowledge, memories and other features. Sources: open-webui:open-webui:permissions. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Groups can organize departments; the privacy guide recommends separate instances/databases/operators for distinct trust boundaries. A multi-entity commercial contract was not reviewed. Sources: open-webui:open-webui:groups, open-webui:open-webui:privacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:roles, open-webui:open-webui:groups, open-webui:open-webui:permissions, open-webui:open-webui:privacy ### ADM-04: Usage and adoption analytics Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. - export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. - adoption_dashboard — Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens. - export — Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admin analytics provides user/model/group activity and token reports, with API export. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - breakdowns: User, model and group views are documented. Complete feature/assistant breakdowns were not established. - privacy_modes: Admins can disable analytics and product-level chat access. Pseudonymized reporting was not established; the default user table identifies users. - adoption_dashboard — Is there an adoption dashboard? [supported]: The dashboard reports messages, chats, token usage and user activity by date range. Sources: open-webui:open-webui:analytics. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: User, model and group views are documented. Complete feature/assistant breakdowns were not established. Sources: open-webui:open-webui:analytics. - export — Can usage data be exported? [supported]: Analytics API endpoints can be exported into JSON or external BI tooling. Sources: open-webui:open-webui:analytics. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Admins can disable analytics and product-level chat access. Pseudonymized reporting was not established; the default user table identifies users. Sources: open-webui:open-webui:analytics, open-webui:open-webui:privacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:analytics, open-webui:open-webui:privacy ### ADM-05: Spend controls and cost allocation Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. - budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. - chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights. - budgets — Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance. - budget_enforcement — Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Token usage supports cost estimation; enforced monetary budgets and cost-centre exports remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - cost_visibility: Analytics exposes provider-reported input/output tokens by user/model/group; billed currency requires multiplying by external provider prices. - budgets: Can budgets be set per user or group? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - budget_enforcement: Does reaching a budget alert, block or downgrade? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - chargeback: Can costs be exported per cost centre? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Analytics exposes provider-reported input/output tokens by user/model/group; billed currency requires multiplying by external provider prices. Sources: open-webui:open-webui:analytics. - budgets — Can budgets be set per user or group? [unknown]: budgets: Can budgets be set per user or group? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - budget_enforcement — Does reaching a budget alert, block or downgrade? [unknown]: budget_enforcement: Does reaching a budget alert, block or downgrade? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:analytics ### ADM-06: Audit logs and compliance export Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. - content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. - siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. - ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. - admin_events — Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin. - siem_export — Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention — How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional request logging can capture metadata or content and stream to operator log infrastructure. It is not a verified immutable compliance archive. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal-hold contract or immutable retention/integrity model was verified. - log_retention: File rotation is configurable and operators own log storage and retention. No universal retention period or tamper-evident archive was established. - admin_events — Are admin and security events logged? [supported]: Configured request logging can include authentication and administrative API paths. Sources: open-webui:open-webui:hardening. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [supported]: REQUEST and REQUEST_RESPONSE levels add bodies, subject to path exclusions and a body-size cap; metadata-only capture is also available. Sources: open-webui:open-webui:hardening. - siem_export — Can logs stream to a SIEM or be exported? [supported]: File or stdout output can feed an operator-managed log collector. Sources: open-webui:open-webui:hardening. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal-hold contract or immutable retention/integrity model was verified. - log_retention — How long are logs kept? [partial]: File rotation is configurable and operators own log storage and retention. No universal retention period or tamper-evident archive was established. Sources: open-webui:open-webui:hardening, open-webui:open-webui:security. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:hardening, open-webui:open-webui:security ### ADM-07: Data loss prevention and personal data Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown. Availability: source-only Delivery: native Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Development-source finding; no running instance or AHV/IBAN fixture. - Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class. - Redaction applies only to eligible fresh Agent text; encrypted originals remain stored. - A dedicated external DLP integration remains unverified. - pii_detection — Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - custom_patterns — Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration. - filter_location — Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318 #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Custom request filters provide an extension point for PII policies; a configured detection/redaction product and Swiss fixture result were not established. Availability: generally-available Delivery: manual-workaround Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - pii_detection: Is personal data detected in prompts and files? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - pii_action: An installed custom Python filter can modify or reject requests before model processing. No built-in AHV/IBAN policy is claimed. - custom_patterns: Custom filter code can implement customer rules; ready-made managed pattern libraries were not verified. - dlp_integration: Does it integrate with an existing DLP product? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - pii_detection — Is personal data detected in prompts and files? [unknown]: pii_detection: Is personal data detected in prompts and files? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: An installed custom Python filter can modify or reject requests before model processing. No built-in AHV/IBAN policy is claimed. Sources: open-webui:open-webui:filter. - custom_patterns — Can admins add custom patterns or terms? [partial]: Custom filter code can implement customer rules; ready-made managed pattern libraries were not verified. Sources: open-webui:open-webui:filter. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: dlp_integration: Does it integrate with an existing DLP product? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - filter_location — Where does filtering run? [supported]: Python filters execute in the customer-operated backend unless their implementation calls an external service. Sources: open-webui:open-webui:filter. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:filter ### ADM-08: AI policy and guardrails Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. - content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. - violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. - org_instructions — Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - usage_notice — Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface. - content_filters — Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod. - violation_reporting — Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model defaults, prompts, banners and custom filters can express policy. Recorded acceptance and violation reporting remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - org_instructions: Admins can configure model/default system prompts; sources explicitly warn that instructions do not guarantee model behavior. - usage_notice: Banners can display policy text, but a required recorded acknowledgement was not established. - content_filters: Operators can install custom request/response filters. Actual policy enforcement depends on that code and configuration. - violation_reporting: Are policy hits visible to admins? The models, banner and filter guides did not establish an organization-wide violation dashboard or mandatory acceptable-use acknowledgement. - org_instructions — Can admins set organisation-wide instructions? [partial]: Admins can configure model/default system prompts; sources explicitly warn that instructions do not guarantee model behavior. Sources: open-webui:open-webui:models, open-webui:open-webui:env. - usage_notice — Can users be required to accept a usage policy? [partial]: Banners can display policy text, but a required recorded acknowledgement was not established. Sources: open-webui:open-webui:banners. - content_filters — Are content filters configurable? [partial]: Operators can install custom request/response filters. Actual policy enforcement depends on that code and configuration. Sources: open-webui:open-webui:filter. - violation_reporting — Are policy hits visible to admins? [unknown]: violation_reporting: Are policy hits visible to admins? The models, banner and filter guides did not establish an organization-wide violation dashboard or mandatory acceptable-use acknowledgement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:env, open-webui:open-webui:banners, open-webui:open-webui:filter ## Data protection and sovereignty ### DATA-01: Hosting location and data residency Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. - support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. - storage_region — Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote. - inference_region — Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex. - backups_logs_region — Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin. - support_access_region — From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting — Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license. - residency_plan — Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The operator chooses data locations; external services can receive prompts or documents independently of where Open WebUI is hosted. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - backups_logs_region: The operator controls backups and logging locations. A concrete installation and its telemetry/egress were not audited. - support_access_region: Operators and support recipients with host/database access can read data; there is no reviewed geographic enterprise support-access commitment. - swiss_hosting: An organization can deploy the self-hosted stack on Swiss infrastructure. This is not a bundled vendor-managed Swiss service or guaranteed Swiss inference. - storage_region — Where are chats, files and indexes stored? [supported]: Chats, files and indexes reside in configured customer storage/database locations. No vendor-chosen region applies to this self-hosted instance. Sources: open-webui:open-webui:privacy. - inference_region — Where do model calls run, per provider? [supported]: The selected provider endpoint runs inference; local, private or external endpoints must be scoped separately. Sources: open-webui:open-webui:provider, open-webui:open-webui:privacy. - backups_logs_region — Where are backups, logs and telemetry? [partial]: The operator controls backups and logging locations. A concrete installation and its telemetry/egress were not audited. Sources: open-webui:open-webui:privacy. - support_access_region — From where can vendor staff access data? [partial]: Operators and support recipients with host/database access can read data; there is no reviewed geographic enterprise support-access commitment. Sources: open-webui:open-webui:privacy. - swiss_hosting — Is Swiss hosting available? [partial]: An organization can deploy the self-hosted stack on Swiss infrastructure. This is not a bundled vendor-managed Swiss service or guaranteed Swiss inference. Sources: open-webui:open-webui:privacy, open-webui:open-webui:quickstart. - residency_plan — Which plan or option provides residency? [supported]: Self-hosting gives the operator infrastructure placement control under standard use; provider contracts and optional enterprise services are separate. Sources: open-webui:open-webui:privacy, open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:provider, open-webui:open-webui:quickstart, open-webui:open-webui:enterprise ### DATA-02: Deployment options Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The project documents local and customer-cloud installs. A free public demo is separate from a production managed service. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. - dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. - mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. - multi_tenant_saas — Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin. - air_gapped — Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg. - mode_feature_gaps — Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-operated cloud and on-premise installs are documented, with offline operation requiring all dependencies to be local. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - multi_tenant_saas: Is a shared SaaS offered? A vendor-operated shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - multi_tenant_saas — Is a shared SaaS offered? [unknown]: multi_tenant_saas: Is a shared SaaS offered? A vendor-operated shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - 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 shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Docker/Python installs can run in customer infrastructure; no standard-use seat minimum is stated. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:enterprise. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: The complete application can run on customer servers with local inference/extraction services. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:offline. - air_gapped — Can it run without internet access? [supported]: The offline guide describes preparing cached models/assets and local services before disconnecting. Sources: open-webui:open-webui:offline. - mode_feature_gaps — Which features are missing outside SaaS? [supported]: External model APIs, internet search, remote extraction and other online tools require network access; they are not made local by self-hosting the UI. Sources: open-webui:open-webui:offline. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:enterprise, open-webui:open-webui:offline ### DATA-03: Training use and provider retention Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. - provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - vendor_training — Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat. - provider_training — Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosting controls the application data path; training and retention obligations depend on the chosen external model contract. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - vendor_training: The self-hosted data path runs on customer infrastructure; this is architecture evidence, not a reviewed contractual no-training promise covering support or optional services. - provider_training: Do model providers train on it under this product's contracts? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - zero_retention: Is zero data retention available, and on which plan? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - human_review: Can provider staff review content? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - vendor_training — Does the vendor train on customer content? [partial]: The self-hosted data path runs on customer infrastructure; this is architecture evidence, not a reviewed contractual no-training promise covering support or optional services. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline. - 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 executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - 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 executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline ### DATA-04: Retention and deletion Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. - contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. - default_retention — What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention. - admin_retention — Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention. - user_deletion — Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings. - contract_end_deletion — What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can remove chats/files subject to permissions, and temporary-chat enforcement can avoid saving new conversations. Complete purge and contract-end schedules remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - default_retention: Normal history persists in the operator’s database; temporary chats reduce saved history. A uniform default duration across chats, files, indexes, logs and backups was not established. - admin_retention: Operators control database and backup retention; enforced temporary-chat permissions stop saving new chats. A general time-based retention scheduler was not established. - user_deletion: Permissions allow chat deletion and file management removes files and related embeddings. Backup purge and irreversible-deletion timing were not verified. - contract_end_deletion: What is deleted at contract end, and when? No enterprise termination deletion deadline or deletion confirmation was reviewed. - default_retention — What is retained and for how long by default? [partial]: Normal history persists in the operator’s database; temporary chats reduce saved history. A uniform default duration across chats, files, indexes, logs and backups was not established. Sources: open-webui:open-webui:privacy, open-webui:open-webui:quickstart. - admin_retention — Can admins set retention periods? [partial]: Operators control database and backup retention; enforced temporary-chat permissions stop saving new chats. A general time-based retention scheduler was not established. Sources: open-webui:open-webui:privacy. - user_deletion — Can users delete their chats and files permanently? [partial]: Permissions allow chat deletion and file management removes files and related embeddings. Backup purge and irreversible-deletion timing were not verified. Sources: open-webui:open-webui:permissions, open-webui:open-webui:rag. - contract_end_deletion — What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No enterprise termination deletion deadline or deletion confirmation was reviewed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:quickstart, open-webui:open-webui:permissions, open-webui:open-webui:rag ### DATA-05: Sub-processors and foreign-law exposure Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. - transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_list — Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification — Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy — Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner #### Open WebUI 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-06: Contracts and regulatory coverage Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict. #### LibreChat Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### Open WebUI 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. #### 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. #### Open WebUI 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). #### 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 #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Encryption and private networking are operator responsibilities; product flags do not remove host-operator access. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - encryption_at_rest: The privacy guide recommends encrypted PostgreSQL volumes/backups or encrypted SQLite filesystems. SQLCipher is explicitly unsupported since v0.9.0. It is not automatic application-level encryption of all content. - customer_managed_keys: The customer can operate infrastructure encryption keys. A product HYOK/key-escrow protocol was not established. - tenant_isolation: How are customers separated in shared SaaS? Shared vendor SaaS tenant isolation was not established for the scoped customer-operated product. - encryption_at_rest — Is data encrypted at rest? [partial]: The privacy guide recommends encrypted PostgreSQL volumes/backups or encrypted SQLite filesystems. SQLCipher is explicitly unsupported since v0.9.0. It is not automatic application-level encryption of all content. Sources: open-webui:open-webui:privacy. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: The customer can operate infrastructure encryption keys. A product HYOK/key-escrow protocol was not established. Sources: open-webui:open-webui:privacy. - private_networking — Is private connectivity or IP restriction available? [supported]: The application and local services can run inside customer networks and disconnected environments; TLS/reverse-proxy setup remains operator work. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline. - tenant_isolation — How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? Shared vendor SaaS tenant isolation was not established for the scoped customer-operated product. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline ### DATA-09: Professional secrecy Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified. - Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The self-hosted content-access boundary is documented. A vendor secrecy undertaking under § 203 StGB or Art. 321 StGB, its staff/sub-processor coverage and any plan-specific offering remain unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; standard self-hosted server and separately described Enterprise support; plan=Standard branded self-hosted use; Enterprise licensing/support checked separately, with no professional-secrecy contract or add-on verified; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application/model infrastructure; no DE/CH secrecy-contract variant or vendor/support access jurisdiction verified; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: A concrete deployment, support-access grant, sub-processor permissions and model-provider staff access were not audited. - 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]: The public Enterprise, support, security and law-firm pages did not establish a signed or signable professional-secrecy undertaking binding Open WebUI staff. No § 203 StGB / Art. 321 StGB agreement was obtained; informational security guidance is not recorded as one. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:secrecy-support. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No professional-secrecy undertaking or annex identifying covered sub-processors and their secrecy obligations was found in the reviewed public materials. Customer-selected hosting, model and support arrangements need their own document review. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: Enterprise licensing and advisory support are documented, but their public descriptions did not establish a professional-secrecy package, paid add-on, eligible plan or contractual scope. No sales contact was made. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:secrecy-support. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: For self-hosted AI chats, Open WebUI documents the running application, live-query database administrators, host/backup operators and configured external model providers as part of the content-access boundary. Admin UI restrictions and at-rest encryption do not exclude those operators. The law-firm page says self-hosted data is not sent to Open WebUI as a managed service; vendor support grants, sub-processor staff permissions and provider human access were not verified for a concrete deployment. Sources: open-webui:open-webui:secrecy-access, open-webui:open-webui:secrecy-legal. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: The law-firm page provides general deployment/privacy guidance and links US ABA materials. No product-scoped DE/CH secrecy contract template, staff/sub-processor annex or professional-body confirmation was located in the reviewed public pages or targeted searches. Sources: open-webui:open-webui:secrecy-legal. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:secrecy-support, open-webui:open-webui:secrecy-access, open-webui:open-webui:secrecy-legal ## Commercials and vendor ### VEN-01: Pricing model and list prices Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. - overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. - pricing_unit — What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat. - list_prices — What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat. - included_usage — What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat. - add_ons — Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images. - overage — What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Branding-intact standard use is free; Enterprise and external infrastructure/model services cost separately. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - list_prices: Standard internal use is listed as Free on 2026-10-21. No numeric Enterprise tariff was published in the reviewed offer. - add_ons: Branding changes outside licence exceptions and enterprise-exclusive offerings such as Terminals require Enterprise rights; service rates were not established. - overage: External providers charge under their own accounts; no universal Open WebUI inference overage tariff applies to standard self-hosting. - pricing_unit — What is the pricing unit? [supported]: Standard software use has no per-seat fee with original branding intact. Enterprise rights/support are separately licensed. Sources: open-webui:open-webui:enterprise. - list_prices — What are list prices per plan, with date and currency? [partial]: Standard internal use is listed as Free on 2026-10-21. No numeric Enterprise tariff was published in the reviewed offer. Sources: open-webui:open-webui:enterprise. - included_usage — What usage is included? [supported]: A software licence does not supply model inference or hosting; customers configure those services. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:provider. - add_ons — Which features cost extra? [partial]: Branding changes outside licence exceptions and enterprise-exclusive offerings such as Terminals require Enterprise rights; service rates were not established. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:terms. - overage — What do usage beyond limits and premium models cost? [partial]: External providers charge under their own accounts; no universal Open WebUI inference overage tariff applies to standard self-hosting. Sources: open-webui:open-webui:provider, open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:provider, open-webui:open-webui:terms ### VEN-02: Scenario cost Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified. Limitations: - ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise. - The budget is a floor because named infrastructure and service costs are unpriced. - cost_200 — Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_1000 — Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_5000 — Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - variable_share — Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort. - unknown_parts — Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort #### Open WebUI 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 code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; 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: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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: open-webui:open-webui:cost-model, open-webui:open-webui: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. Open WebUI Enterprise, branding rights outside standard exceptions and Terminals production licences are quote-only. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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. #### 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 #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Standard self-installation permits evaluation without sales contact; Enterprise rights and services have a separate sales path. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - self_serve_trial: Docker/Python self-installation is available without a licence payment or trial clock; it is an install path rather than a vendor-operated business trial. - sales_gate: Standard self-install evaluation is possible without sales. Enterprise licensing is offered to registered entities via the sales path. - free_tier — Is there a free tier for business use? [supported]: The current enterprise page permits free standard use with branding intact, including organizations. Sources: open-webui:open-webui:enterprise. - self_serve_trial — Is a self-serve business trial available? [partial]: Docker/Python self-installation is available without a licence payment or trial clock; it is an install path rather than a vendor-operated business trial. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:enterprise. - trial_scope — Do trials include SSO, connectors and admin features? [supported]: Self-hosted authentication, administration and knowledge features can be configured for evaluation with the customer’s own infrastructure and credentials. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:sso, open-webui:open-webui:knowledge. - sales_gate — Does meaningful evaluation require sales contact? [partial]: Standard self-install evaluation is possible without sales. Enterprise licensing is offered to registered entities via the sales path. Sources: open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:quickstart, open-webui:open-webui:sso, open-webui:open-webui:knowledge ### VEN-04: Contract terms and pricing transparency Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. - minimum_commitment — What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license. - contract_length — What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license. - cancellation — How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Standard-use licence terms are public; Enterprise pricing and negotiated contract details remain quote-only. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - minimum_commitment: No paid standard-use seat commitment is listed. The 50-user rolling window is a branding exception, not a cap on branded deployment size; Enterprise is available to registered entities. - contract_length: What contract lengths are offered? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - cancellation: How can the contract be cancelled or reduced? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - minimum_commitment — What seat or spend minimum applies? [partial]: No paid standard-use seat commitment is listed. The 50-user rolling window is a branding exception, not a cap on branded deployment size; Enterprise is available to registered entities. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:enterprise. - contract_length — What contract lengths are offered? [unknown]: contract_length: What contract lengths are offered? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - cancellation — How can the contract be cancelled or reduced? [unknown]: cancellation: How can the contract be cancelled or reduced? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - 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? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [supported]: Standard-use licence is disclosed; Enterprise price and service terms are quote-only in the reviewed public offer. Sources: open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:enterprise ### VEN-05: Source licence Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. - licence_type — Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The core server at v0.12.3 uses a licence with branding restrictions. The separate Desktop v0.0.20 repository distributes GNU AGPL v3. Terminals and proprietary Enterprise component terms remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, Open WebUI Desktop native distribution (Early Alpha); version=Core v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; Desktop v0.0.20 / 601137c5dec2967cfe173a6bf071fbbb460852be; plan=Pinned core server and Desktop component licences only; no executed Enterprise agreement or pinned Terminals licence verified; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - The claim follows pinned component licence texts and excludes unverified Enterprise/Terminals feature-licensing assertions. - No executed branding exception or proprietary Enterprise agreement was reviewed. - licence_type — Which licence applies to each component? [partial]: Core v0.12.3 is distributed under the Open WebUI License with branding conditions, so its source availability has restrictions. The separate Desktop v0.0.20 LICENSE is GNU AGPL version 3. Other component licences were not established by these two texts. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:desktop-license-r2. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: Core LICENSE clause 4 restricts branding changes, with exceptions for no more than 50 natural-person users in a rolling 30 days, specific prior written permission, or an executed Enterprise licence expressly permitting changes. It does not impose a 50-user cap on branded use. This answer follows that pinned text, not the FAQ contribution qualifier. Sources: open-webui:open-webui:license-pin. - enterprise_features_closed — Are enterprise features in a separate closed edition? [unknown]: The core text mentions an Enterprise branding-permission exception but does not establish a separate closed edition or Terminals production terms. No relevant pinned Terminals component licence or executed Enterprise contract was reviewed; those details remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:desktop-license-r2 ### VEN-06: Data export and exit Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. - assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. - knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - chat_export — Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - export_format — Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin. - post_termination_window — How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial User chats, admin chat records and model definitions have machine-readable export paths. Knowledge ZIP export converts source files to text. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - assistant_export: Models have JSON export/import and sync APIs. Full portability of all bound tools, skills, external secrets and shared prompts was not tested. - knowledge_export: Admins can export a knowledge base as ZIP containing .txt conversions. Original binary fidelity and full index/configuration restoration were not established. - post_termination_window: How long can data be retrieved after termination? No admin export fixture or Enterprise post-termination retrieval period was tested/reviewed; customer-owned backups remain the operator’s responsibility. - chat_export — Can admins export all chats? [supported]: Users export their history as JSON. The pinned admin all/db route returns database chat records if ENABLE_ADMIN_EXPORT is enabled. Sources: open-webui:open-webui:export, open-webui:open-webui:chats-pin. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: Models have JSON export/import and sync APIs. Full portability of all bound tools, skills, external secrets and shared prompts was not tested. Sources: open-webui:open-webui:api. - knowledge_export — Can knowledge bases and their sources be exported? [partial]: Admins can export a knowledge base as ZIP containing .txt conversions. Original binary fidelity and full index/configuration restoration were not established. Sources: open-webui:open-webui:knowledge. - export_format — Are formats documented and machine-readable? [supported]: Chat/model JSON schemas and APIs and knowledge text ZIP output are documented. Sources: open-webui:open-webui:export, open-webui:open-webui:api, open-webui:open-webui:knowledge. - 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 export fixture or Enterprise post-termination retrieval period was tested/reviewed; customer-owned backups remain the operator’s responsibility. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:export, open-webui:open-webui:chats-pin, open-webui:open-webui:api, open-webui:open-webui:knowledge ### VEN-07: Support and service levels Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public project/community channels are available; a binding business support SLA was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. - support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - support_channels — Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat. - support_languages — Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla — Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page — Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise support advertises dedicated channels, account management and engineering office hours; public response/credit terms were not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - support_languages: Is support available in German, French or Italian? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - regional_presence: Is there a DACH or Swiss entity, team or partner? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - uptime_sla: The support page refers to negotiated SLAs, but publishes no reviewed uptime percentage, response commitment or service-credit schedule. - status_page: Is there a public status page with history? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - support_channels — Which support channels are available on each plan? [supported]: Enterprise customers can obtain dedicated support channels and an account manager; community development/support uses public GitHub and community channels. Sources: open-webui:open-webui:support, open-webui:open-webui:roadmap. - support_languages — Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap 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? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - uptime_sla — Is there an uptime SLA with credits? [partial]: The support page refers to negotiated SLAs, but publishes no reviewed uptime percentage, response commitment or service-credit schedule. Sources: open-webui:open-webui:support. - status_page — Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:support, open-webui:open-webui:roadmap ### VEN-08: Onboarding, training and adoption Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. - adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - onboarding_service — Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training — Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library — Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost — Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise guidance includes onboarding and engineering advice. Paid hands-on implementation and training terms need separate scoping. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - onboarding_service: Enterprise account management advertises onboarding guidance, with package inclusion and cost unspecified. - user_training: Is end-user training offered, in which languages? No vendor training languages/curriculum, champion programme or priced change-management package was established. - use_case_library: Documentation provides assistant examples and Open Terminal use cases. A full workforce training/adoption curriculum was not established. - adoption_programme: Is there a champion or adoption programme? No vendor training languages/curriculum, champion programme or priced change-management package was established. - service_cost: Enterprise support is separately arranged; the team describes guidance rather than implementation services and recommends a systems integrator or internal team for hands-on work. Public rates were not established. - onboarding_service — Is guided onboarding included? [partial]: Enterprise account management advertises onboarding guidance, with package inclusion and cost unspecified. Sources: open-webui:open-webui:support. - user_training — Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No vendor training languages/curriculum, champion programme or priced change-management package was established. - use_case_library — Are role-based use cases and templates provided? [partial]: Documentation provides assistant examples and Open Terminal use cases. A full workforce training/adoption curriculum was not established. Sources: open-webui:open-webui:models, open-webui:open-webui:terminal. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No vendor training languages/curriculum, champion programme or priced change-management package was established. - service_cost — Which services cost extra? [partial]: Enterprise support is separately arranged; the team describes guidance rather than implementation services and recommends a systems integrator or internal team for hands-on work. Public rates were not established. Sources: open-webui:open-webui:support. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:support, open-webui:open-webui:models, open-webui:open-webui:terminal ## Sources ### librechat:librechat:custom Custom endpoints. Operators configure compatible endpoints and customer-held keys, including local and hosted services. - URL: https://www.librechat.ai/docs/quick_start/custom_endpoints - Locator: Endpoint setup; API key; base URL; model list - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:azure Azure OpenAI configuration. Azure OpenAI uses customer deployment groups, instance names and credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/azure - Locator: Deployment groups; API credentials - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:bedrock AWS Bedrock object structure. Bedrock routes use customer AWS configuration and region selection. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/aws_bedrock - Locator: Region; credentials; model selection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:vertex Anthropic Vertex AI configuration. Claude can run through customer Google Vertex AI credentials and regions. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/anthropic_vertex - Locator: Project and region configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:modelspec Model specifications. Administrators can enforce configured model presets and defaults; available endpoints still depend on customer credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/model_specs - Locator: enforce; preset; modelSelect; addedEndpoints - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:agents Agents. Agents combine instructions, models, files, tools, skills and sharing permissions, with visible execution and configurable approval. - URL: https://www.librechat.ai/docs/features/agents - Locator: Builder; Capabilities; Version history; Sharing; Activity; tool approval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:ocr OCR for documents. OCR can augment text extraction, or files can be sent to compatible provider APIs; format and model limitations remain. - URL: https://www.librechat.ai/docs/features/ocr - Locator: File Context; Upload as Text; Optional OCR; Limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:releases LibreChat v0.8.8 release. The stable release documents agent controls, current model updates and explicitly experimental schedules/workspaces and beta Agents API. - URL: https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8 - Locator: Highlights, 2026-10-01 - Evidence kind: documented - Source date: 2026-10-01 - Retrieved: 2026-10-21 ### open-webui:open-webui:provider Connect local and cloud models. Administrators connect model endpoints; the selected endpoint determines inference location, including for attached context. - URL: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/ - Locator: How it works; Cloud Providers; Local Servers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:compat OpenAI-compatible providers. The guide documents compatible cloud gateways and local inference servers, with provider-specific capability differences. - URL: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible/ - Locator: Provider configuration and provider examples - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:rag Retrieval augmented generation. Document retrieval uses configured embeddings and chunks or full context, with citations and a Google Drive file picker. - URL: https://docs.openwebui.com/features/chat-conversations/rag/ - Locator: Embedding support; Citations; Google Drive integration; per-file retrieval mode - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:extraction Document extraction. Configurable extraction engines can process scanned documents; browser-only temporary extraction has format limitations. - URL: https://docs.openwebui.com/features/chat-conversations/rag/document-extraction/ - Locator: Available extraction methods; temporary chat limitation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:openai OpenAI and Azure OpenAI connections. Customers configure their own OpenAI keys or Azure endpoint, deployment IDs and API version. - URL: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai/ - Locator: Azure OpenAI tab; Advanced Configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:releases Open WebUI release notes. Dated releases document shipped changes, including v0.12.3 Drive scope reduction and encrypted private-channel chats. - URL: https://github.com/open-webui/open-webui/releases/tag/v0.12.3 - Locator: v0.12.3, 2026-10-16; v0.12.2; v0.12.1 - Evidence kind: documented - Source date: 2026-10-16 - 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 ### open-webui:open-webui:models Models workspace. Model presets combine instructions, model, knowledge, tools and skills, with access grants and saved versions. - URL: https://docs.openwebui.com/features/workspace/models/ - Locator: Presets; Access; Builtin Tools; System prompts - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:enterprise Open WebUI for enterprise. Branding-intact internal use is free; enterprise branding rights, support and exclusive offerings require a separate licence. - URL: https://docs.openwebui.com/enterprise/ - Locator: Licence requirements; Deployment; Support - 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 ### open-webui:open-webui:memory Memory and personalization. Users manage persistent memories; administrators can disable the feature or restrict groups, including server-side use. - URL: https://docs.openwebui.com/features/chat-conversations/memory/ - Locator: Manual management; Administrative controls; Privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:offline Run Open WebUI offline. Disconnected operation requires prepared local models, embeddings and extraction; internet APIs and tools remain external dependencies. - URL: https://docs.openwebui.com/tutorials/maintenance/offline-mode/ - Locator: Local prerequisites; disabled online functionality; verification - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:access Granular access control. Roles, groups and resource ACLs govern features and sharing, with Entra groups synchronized at sign-in. - URL: https://www.librechat.ai/docs/features/access_control - Locator: Feature permissions; Resource ACLs; System grants; Groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:admin LibreChat Admin Panel. A separate browser management panel is available for testing and uses the underlying LibreChat admin APIs. - URL: https://www.librechat.ai/docs/features/admin_panel - Locator: Status Preview; separate service; admin APIs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:balance Balance configuration. Optional token-credit balances initialize and refill user credits; tracking is disabled by default. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/balance - Locator: enabled; startBalance; refill configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mod Automated moderation. Moderation scores abusive login/registration/message activity and may ban users; it is not a documented content DLP classifier. - URL: https://www.librechat.ai/docs/features/mod_system - Locator: Violation scoring and limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:balance-pin LibreChat balance admission implementation. The pinned middleware reserves user credits and throws a TOKEN_BALANCE error when the reservation cannot be admitted. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/packages/api/src/middleware/checkBalance.ts - Locator: packages/api/src/middleware/checkBalance.ts, checkBalance - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: packages/api/src/middleware/checkBalance.ts ### open-webui:open-webui:knowledge Knowledge bases and document chat. Persistent knowledge bases support scoped access, model attachment, incremental directory sync and admin text-file ZIP export. - URL: https://docs.openwebui.com/features/workspace/knowledge/ - Locator: Retrieval modes; Sharing; Syncing; Export; API - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:groups Groups. User and group grants control resources; permissions accumulate across groups rather than deny access. - URL: https://docs.openwebui.com/features/authentication-access/rbac/groups/ - Locator: Additive permissions; Resource Access; Nested Groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:privacy Chat data privacy and encryption. The deployer controls storage, encryption, logs, backups and provider connections; product admin restrictions do not prevent host-operator access. - URL: https://docs.openwebui.com/security/chat-data-privacy-and-encryption/ - Locator: Controls by concern; encryption; operators; model providers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:r4-filter-implementation Open WebUI v0.12.4 filter implementation. The backend dispatches installed filter handlers with user context and propagates inlet failures. It does not itself provide a configured recurring quota or managed PII policy. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/utils/filter.py - Locator: process_filter_function; process_filter_functions; inlet exception propagation - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/utils/filter.py ### open-webui:open-webui:r4-rate-limit-example Open WebUI filter functions. The official optional Python example counts requests per user and raises at its configurable per-minute threshold. This sample uses in-process state and is not an enabled product-wide quota or monetary budget. - URL: https://docs.openwebui.com/features/extensibility/plugin/functions/filter/ - Locator: Example: Rate Limiting for All Requests - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### 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 ### open-webui:open-webui:env Environment variable configuration. Administrators configure document limits, accepted extensions, audio engines and instance settings. - URL: https://docs.openwebui.com/reference/env-configuration/ - Locator: RAG_FILE_MAX_SIZE; RAG_FILE_MAX_COUNT; RAG_ALLOWED_FILE_EXTENSIONS; audio; system prompt - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:projects Projects. Projects persist files and instructions across a user’s chats but cannot be shared or transferred. - URL: https://www.librechat.ai/docs/features/projects - Locator: Availability; personal scope; files and instructions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:sharepoint SharePoint and OneDrive integration. The Microsoft file picker uses Entra token reuse and delegated on-behalf-of downloads to attach files. - URL: https://www.librechat.ai/docs/configuration/sharepoint - Locator: Prerequisites; delegated permissions; admin consent - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mcp MCP. MCP servers can be configured through YAML or the permission-gated UI, including per-user OAuth. - URL: https://www.librechat.ai/docs/features/mcp - Locator: YAML/UI setup; authentication; ownership and selection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mcpcfg MCP server configuration. Configuration includes stdio, SSE and Streamable HTTP transports and server-specific credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/mcp_servers - Locator: Transport examples; headers; OAuth - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:onedrive OneDrive and SharePoint. Users attach Microsoft files through a delegated file picker; the guide requires tenant app registration and admin consent. - URL: https://docs.openwebui.com/tutorials/integrations/onedrive-sharepoint/ - Locator: Work/school app registration; delegated API permissions; admin consent - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:sync Knowledge base sync, oikb. The separate official CLI and daemon copies sources into Open WebUI knowledge bases and propagates changes during sync. - URL: https://docs.openwebui.com/ecosystem/knowledge-base-sync/ - Locator: Overview; connectors; scheduling; incremental sync - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:mcp Model Context Protocol. Native remote MCP is administrator-configured Streamable HTTP with shared credentials or user OAuth modes. - URL: https://docs.openwebui.com/features/extensibility/mcp/ - Locator: Streamable HTTP; Why admins only; Authentication modes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:sync-connectors-r2 oikb connector credentials and deployment boundary. The separate official oikb program lists Teams and Gmail with source credentials; it writes into knowledge bases using an Open WebUI user API key. - URL: https://docs.openwebui.com/ecosystem/knowledge-base-sync/ - Locator: Install; Sources and connectors: SharePoint, Microsoft Teams, Google Drive, Gmail; Access is your access - 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 ### 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 ### open-webui:open-webui:permissions Permissions. Feature and resource permissions cover models, knowledge, prompts, tools, search, images, files and memories. - URL: https://docs.openwebui.com/features/authentication-access/rbac/permissions/ - Locator: Workspace and feature permission tables - 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 ### open-webui:open-webui:tools Tools. Tools may run through Python, OpenAPI or MCP, and an optional approval mode stops calls until the user allows or denies them. - URL: https://docs.openwebui.com/features/extensibility/plugin/tools/ - Locator: Native tools and OpenAPI; Tool call approval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:approvals-r2 Open WebUI experimental tool permissions. Tool Permissions is experimental and disabled by default; interactive approvals can wait, but automations and channel replies always use full access. - URL: https://docs.openwebui.com/features/extensibility/plugin/tools/ - Locator: Tool Approval: ENABLE_TOOL_PERMISSIONS, Full access, Ask for approval, Stop, saved/temporary chats and exceptions - 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 ### open-webui:open-webui:web Web search. Search uses an administrator-configured provider and can add external sources to a conversation. - URL: https://docs.openwebui.com/features/chat-conversations/web-search/ - Locator: Enabling and using web search; providers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:agent-search Agentic web search and URL fetching. Tool-capable models can repeatedly search and fetch pages, with results and citations in the conversation. - URL: https://docs.openwebui.com/features/chat-conversations/web-search/agentic-search/ - Locator: Native function calling; search and fetch tools - 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 ### open-webui:open-webui:automation Automations. Recurring prompts run on the customer server through the normal chat pipeline and remain private to their owner. - URL: https://docs.openwebui.com/features/chat-conversations/chat-features/automations/ - Locator: Schedules; Access Control; Runtime behavior - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:r4-event-dispatch Open WebUI v0.12.4 event dispatch. Configured Event functions receive published system events and can run developer-written handlers. Event payload field sanitization is not a general prompt/file PII detection service. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/events.py - Locator: build_event; dispatch_event_functions; EventFunctionSink - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/events.py ### open-webui:open-webui:r4-incoming-channel-webhook Open WebUI v0.12.4 channel webhooks. A token-validated incoming webhook creates a channel message and publishes MESSAGE_CREATED with source channel_webhook. A configured Event handler can respond to this external input; no no-code workflow engine is implied. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/routers/channels.py - Locator: post_webhook_message, lines 2283-2361 - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/routers/channels.py ### open-webui:open-webui:terminal Open Terminal. The separately deployed Open Terminal gives agents file, shell and code tools, including analysis and chart creation. - URL: https://docs.openwebui.com/features/open-terminal/ - Locator: Agent loop; Data analysis; Document processing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:api API endpoints. Authenticated APIs expose chat, tool use, file ingestion, knowledge attachment and model configuration export. - URL: https://docs.openwebui.com/reference/api-endpoints/ - Locator: Authentication; chat completions; tools; files; models export - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:hardening Hardening Open WebUI. Optional request logging has configurable bodies, path exclusions, file rotation and stdout output; deployment operators own log handling. - URL: https://docs.openwebui.com/getting-started/advanced-topics/hardening/ - Locator: Audit logging; output; path filtering; reverse proxy - 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 ### open-webui:open-webui:desktop-quickstart-r2 Open WebUI Desktop installation route. Quick Start links the native desktop distribution as a route without Docker/manual setup and recommends Docker or Python for production. - URL: https://docs.openwebui.com/getting-started/quick-start/ - Locator: Desktop App section and production-install note - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-readme-r2 Open WebUI Desktop v0.0.20 documentation. The pinned Desktop README labels the app Early Alpha, lists macOS/Windows/Linux installers and describes local execution or a connection to an existing server. - URL: https://raw.githubusercontent.com/open-webui/desktop/601137c5dec2967cfe173a6bf071fbbb460852be/README.md - Locator: Early Alpha; Download table; How It Works; System Requirements - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-release-r2 Open WebUI Desktop v0.0.20 release assets. The 2026-05-06 release includes macOS and Windows x64/ARM64 installers plus Linux packages; its notes describe a Linux blank-webview fix. - URL: https://api.github.com/repos/open-webui/desktop/releases/tags/v0.0.20 - Locator: published_at; assets[].name; release body - Evidence kind: documented - Source date: 2026-05-06 - Retrieved: 2026-10-21 ### open-webui:open-webui:pwa-r2 Open WebUI browser PWA installation. The web interface can also be installed as a desktop/mobile browser PWA; PWA notifications require it to stay open. - URL: https://docs.openwebui.com/getting-started/open-webui-as-app/ - Locator: Desktop browser installation; Android; iOS; notification limitation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:notes Notes. Notes provide rich text and Markdown editing with AI rewrites and full-content attachment to chats. - URL: https://docs.openwebui.com/features/notes/ - Locator: Rich editor; AI editing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:images Image generation. Image providers include OpenAI, Gemini, ComfyUI and AUTOMATIC1111. - URL: https://docs.openwebui.com/features/chat-conversations/image-generation-and-editing/ - Locator: Provider list - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:image-usage Generate and edit images in chat. Image generation and editing require configured providers, feature permissions and model capability toggles. - URL: https://docs.openwebui.com/features/chat-conversations/image-generation-and-editing/usage/ - Locator: Availability conditions; Editing; Compositing - 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 ### open-webui:open-webui:voice Voice mode. Voice mode combines configured STT and TTS or a separately configured OpenAI-compatible realtime service. - URL: https://docs.openwebui.com/features/chat-conversations/chat-features/voice-mode/ - Locator: Standard mode; Realtime calls; Audio 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 ### open-webui:open-webui:channels Channels. Channels support multi-person collaboration and AI participation, with channel access controls. - URL: https://docs.openwebui.com/features/channels/ - Locator: Shared channels and direct messages - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:export Import and export. Users export their conversation history in documented JSON and can import compatible records. - URL: https://docs.openwebui.com/features/chat-conversations/data-controls/import-export/ - Locator: Exporting all chats; JSON schema - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### open-webui:open-webui:i18n-pin Open WebUI locale registration. The pinned client registers English, German, French and Italian interface locales; this does not establish translation quality. - URL: https://raw.githubusercontent.com/open-webui/open-webui/91ea4e3421d1d8069f13d4a463fcb5986d94ea60/src/lib/i18n/locales/languages.json - Locator: src/lib/i18n/locales/languages.json, en-US, de-DE, fr-FR, it-IT entries - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 91ea4e3421d1d8069f13d4a463fcb5986d94ea60 - Path: src/lib/i18n/locales/languages.json ### open-webui:open-webui:r4-german-admin-translations Open WebUI v0.12.4 German translations. The distributed German translation file includes administrator and user-management labels. This establishes partial German admin localization, not completeness, naturalness or accessibility conformance. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/src/lib/i18n/locales/de-DE/translation.json - Locator: Admin Panel, Admin, Add User, Change User Role and settings entries - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: src/lib/i18n/locales/de-DE/translation.json ### 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 ### open-webui:open-webui:roles Roles. Admins can manage the system and normally bypass resource grants; environment controls can restrict product-level chat access. - URL: https://docs.openwebui.com/features/authentication-access/rbac/roles/ - Locator: Admin; User; Pending; privacy controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:sso SSO, OAuth, OIDC and trusted header. OAuth/OIDC providers and trusted authentication proxies support account creation and login-time group synchronization. - URL: https://docs.openwebui.com/features/authentication-access/auth/sso/ - Locator: Provider setup; OAuth group management; account creation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:mfa Two-factor sign-in. Built-in authenticator-based sign-in can be required, with explicit configuration for OAuth bypass. - URL: https://docs.openwebui.com/features/authentication-access/mfa/ - Locator: Administrative configuration; OAuth bypass - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:scim SCIM 2.0 support. SCIM provisions users and groups; deactivation maps ordinary accounts to pending and ends live connections. - URL: https://docs.openwebui.com/features/authentication-access/auth/scim/ - Locator: Overview; User Operations; Deprovisioning; Group Operations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:r7-scim-bearer-doc Open WebUI SCIM bearer authentication recheck. The guide configures SCIM through environment variables, including SCIM_ENABLED and SCIM_TOKEN bearer authentication. It documents no user-selectable token-scope control; account visibility rules are distinct from token scopes. - URL: https://docs.openwebui.com/features/authentication-access/auth/scim/ - Locator: Configuration; Environment Variables; SCIM API Configuration; Security Considerations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### open-webui:open-webui:r7-scim-bearer-code Open WebUI v0.12.4 SCIM authentication. The pinned authentication function checks Bearer header format, whether SCIM is enabled, and a constant-time comparison with the configured SCIM_TOKEN. The inspected authentication path exposes no per-token selectable scopes. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/routers/scim.py - Locator: get_scim_auth, lines 251-297 - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/routers/scim.py ### 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 ### open-webui:open-webui:analytics Analytics. Admin analytics reports messages and provider-reported tokens by users, models and groups and exposes an export API. - URL: https://docs.openwebui.com/features/administration/analytics/ - Locator: User and model tables; Group filters; Export; Privacy - 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 ### open-webui:open-webui:security Enterprise security. The page describes deployment controls and states that compliance responsibility remains with the deploying organization. - URL: https://docs.openwebui.com/enterprise/security/ - Locator: Regulatory frameworks; data governance - 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 ### open-webui:open-webui:filter Filter functions. Administrators can install custom Python filters in the model request path; behavior depends on the installed filter. - URL: https://docs.openwebui.com/features/extensibility/plugin/functions/filter/ - Locator: Filter lifecycle and extension examples - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### open-webui:open-webui:banners Customizable banners. Admins can display instance banners; a banner is not evidence of a mandatory recorded policy acknowledgement. - URL: https://docs.openwebui.com/features/administration/banners/ - Locator: Configuration and dismissible banners - 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 ### open-webui:open-webui:quickstart Quick start. The software is self-installable with Docker or Python and keeps state in customer-controlled storage. - URL: https://docs.openwebui.com/getting-started/quick-start/ - Locator: Docker; pip; data volume - 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 ### 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 ### 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 ### open-webui:open-webui:secrecy-access Open WebUI chat data access boundary. The privacy guide identifies application, infrastructure operators and configured model providers as content-access trust boundaries; admin UI controls do not remove infrastructure access. - URL: https://docs.openwebui.com/security/chat-data-privacy-and-encryption/ - Locator: Who Can Read Chat Data?; What Encryption Protects; informational-content disclaimer - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:secrecy-legal Open WebUI for law firms. The law-firm page describes customer-operated storage/routing and links technical guidance and US ABA materials; it is general product guidance. - URL: https://www.openwebui.com/legal - Locator: Materials for risk, KM, security, and legal ops review; FAQ: confidential matter information and uploaded files - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:secrecy-support Open WebUI enterprise support. Enterprise support describes advisory engineering access, dedicated channels and SLAs, with contractual commitments dependent on applicable terms. - URL: https://docs.openwebui.com/enterprise/support/ - Locator: Support Capabilities; Consulting Topics; For Procurement & Legal; informational-content disclaimer - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:terms Terminals orchestrator. The separate per-user terminal orchestration layer requires an Open WebUI Enterprise licence for production. - URL: https://docs.openwebui.com/features/open-terminal/terminals/ - Locator: Prerequisites; Licensing - 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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui:license-pin Open WebUI v0.12.3 licence. The pinned licence preserves notices and restricts branding changes, with exceptions for up to 50 rolling-30-day users, prior written permission or enterprise permission. - URL: https://raw.githubusercontent.com/open-webui/open-webui/91ea4e3421d1d8069f13d4a463fcb5986d94ea60/LICENSE - Locator: LICENSE, clauses 1-4; prior-licence reservation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-license-r2 Open WebUI Desktop v0.0.20 licence. The separately packaged Desktop repository distributes GNU AGPL version 3 licence text at its v0.0.20 revision. - URL: https://raw.githubusercontent.com/open-webui/desktop/601137c5dec2967cfe173a6bf071fbbb460852be/LICENSE - Locator: LICENSE heading and GNU Affero General Public License version 3 text - 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 ### open-webui:open-webui:chats-pin Open WebUI admin chat export implementation. The admin-only all/db route returns chat records when ENABLE_ADMIN_EXPORT is enabled. - URL: https://raw.githubusercontent.com/open-webui/open-webui/91ea4e3421d1d8069f13d4a463fcb5986d94ea60/backend/open_webui/routers/chats.py - Locator: backend/open_webui/routers/chats.py, get_all_user_chats_in_db, lines 1113-1117 - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 91ea4e3421d1d8069f13d4a463fcb5986d94ea60 - Path: backend/open_webui/routers/chats.py ### open-webui:open-webui:support Support and SLAs. Enterprise support advertises account management and engineering guidance, while hands-on implementation remains with the customer or integrator. - URL: https://docs.openwebui.com/enterprise/support/ - Locator: Account manager; Office hours; Consulting; guidance scope - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:roadmap Open WebUI roadmap. Budget controls, broader localization and accessibility appear on an undated roadmap and are not treated as shipped guarantees. - URL: https://docs.openwebui.com/roadmap/ - Locator: In progress; Planned - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21