--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/librechat-vs-typingmind/" data_url: "https://onaihq.com/compare/agents/librechat-vs-typingmind/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 TypingMind / TypingMind Teams > 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. 50 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. - TypingMind / TypingMind Teams source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/librechat-vs-typingmind/ - Machine-readable JSON: https://onaihq.com/compare/agents/librechat-vs-typingmind/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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams is a customer-key multi-provider chat interface, with dated additions and explicit model selection. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - providers — Which model providers are available? [supported]: Teams admin key setup lists OpenAI, Anthropic, Google, OpenRouter, DeepInfra, DeepSeek, Groq, Mistral, Moonshot, Perplexity, xAI and Z.ai, plus custom providers. Sources: typingmind:typingmind:set-up-api-keys. - current_models — Which current models are selectable on this plan? [partial]: The dated October changelog records Gemini 4 Argon and Muse Wonder on October 14 and Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1 on October 9. Actual availability depends on enabled endpoint and customer account; a complete Teams tenant model catalogue was not observed. Sources: typingmind:typingmind:release, typingmind:typingmind:set-up-api-keys. - user_choice — Can users pick the model per chat? [supported]: Users select an available model for a chat; Teams administrators choose which models are exposed. Sources: typingmind:typingmind:manage-ai-models, typingmind:typingmind:restrict-model-access. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [unknown]: Does the product route between models automatically, and is the chosen model shown? The first-party Teams documentation, pricing, legal pages and dated changelog retrieved on 2026-10-21 do not establish this detail; no account or bounded fixture was used. - multimodal_input — Which models accept images, audio or files? [partial]: Document upload, vision-capable model image input and transcription are documented as separate routes; the docs do not provide a complete per-model Teams image/audio/file matrix. Sources: typingmind:typingmind:chat-with-documents, typingmind:typingmind:voice. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:set-up-api-keys, typingmind:typingmind:release, typingmind:typingmind:manage-ai-models, typingmind:typingmind:restrict-model-access, typingmind:typingmind:chat-with-documents, typingmind:typingmind:voice ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated model additions are public; release lag and removal guarantees remain unestablished. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: What was the lag for each of the last three major releases, per provider? No matched first-party provider release dates for the last three releases, fixed deprecation-notice period or version-retention guarantee was retrieved. - changelog — Is there a dated public model changelog? [supported]: The public changelog dates model and Teams feature releases through October 14, 2026 in the retrieved page. Sources: typingmind:typingmind:release. - deprecation_notice — How much notice is given before a model is removed? [unknown]: How much notice is given before a model is removed? No matched first-party provider release dates for the last three releases, fixed deprecation-notice period or version-retention guarantee was retrieved. - version_pinning — Can an admin keep an older model version? [partial]: Customer custom-model endpoint configuration can name a provider model or deployment, but a contractual right to retain discontinued SaaS wrappers or provider versions is not established. Sources: typingmind:typingmind:manage-ai-models, typingmind:typingmind:azure-openai. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:release, typingmind:typingmind:manage-ai-models, typingmind:typingmind:azure-openai ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams uses customer provider keys; its Custom Admin documentation also describes Claude via the customer AWS Bedrock account. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS Starter/Growth/Professional custom-model setup; Bedrock Custom Admin route has no verified exact tier mapping. Separate Teams self-host licence for private endpoint configuration.; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Bedrock is documented for Custom Admin; no all-tier, all-Claude-model or self-host Bedrock entitlement is inferred. Provider-route feature parity was not tested. - own_api_keys — Can the customer use its own provider API keys? [supported]: Admins preset the organization’s provider keys. End users cannot supply separate personal keys in the Teams chat UI. Sources: typingmind:typingmind:set-up-api-keys. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [partial]: Teams documents Azure OpenAI custom-model setup. Its AWS Bedrock guide explicitly applies to TypingMind Custom Admin at custom.typingmind.com/manage and configures Claude via Bedrock using the customer AWS keys, region and approved model access. Exact Bedrock tier/current-model coverage and Vertex support remain unknown. Sources: typingmind:typingmind:r2-teams-custom-models, typingmind:typingmind:r3-custom-admin-bedrock, typingmind:typingmind:r2-plan-matrix. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [partial]: Teams Admin Panel supports Add Custom Model, naming Azure OpenAI, Hugging Face and Ollama. This does not establish an arbitrary-endpoint compatibility guarantee. Separately, commercial Teams self-host operators can enable otherwise-blocked private/localhost custom endpoints; connectivity and model feature parity were not tested. Sources: typingmind:typingmind:r2-teams-custom-models, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:get-started-with-self-host-installation-instruct. - byo_pricing — Does BYO change the licence price? [supported]: Teams subscription excludes API usage and requires customer keys; BYO is the standard paid model route, not an evidenced licence discount. Sources: typingmind:typingmind:pricing, typingmind:typingmind:set-up-api-keys. - byo_restrictions — Which features stop working with BYO? [partial]: Capabilities depend on the selected model and provider API supporting files, tool use and related features; there is no complete feature-by-provider parity matrix. Sources: typingmind:typingmind:manage-ai-models, typingmind:typingmind:toolbox. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:set-up-api-keys, typingmind:typingmind:r2-teams-custom-models, typingmind:typingmind:r3-custom-admin-bedrock, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:pricing, typingmind:typingmind:manage-ai-models, typingmind:typingmind:toolbox ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer model endpoints are supported; optional self-host knowledge uses documented OpenAI embeddings. Availability: generally-available Delivery: native Scope: surfaces=TypingMind personal browser app and PWA, TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Personal app local-model guides; Teams SaaS custom-model setup on Starter/Growth/Professional; separate annual commercial Teams self-host package; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=Personal browser/local network; US/EU Teams SaaS; customer-selected self-host placement and external API routes; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - self_hosted_chat — Can chat use a customer-hosted model? [partial]: Personal typingmind.com has Ollama and LM Studio guides. Teams-specific Admin Panel instructions independently name Ollama custom models, but do not establish the personal local-connection procedure for Teams SaaS. Commercial Teams self-host can explicitly enable private endpoints; no hosted-to-local connectivity fixture was run. Sources: typingmind:typingmind:r2-teams-custom-models, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:ollama, typingmind:typingmind:lmstudio, typingmind:typingmind:get-started-with-self-host-installation-instruct. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [partial]: The optional KB module in the separately quoted annual Teams self-host package requires an OpenAI embeddings key and PostgreSQL pgvector. A customer-hosted embedding substitution is unverified. This is separate from personal local chat models. Sources: typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:cloud-host-vs-self-host. - feature_parity — Which features fail with self-hosted models? [partial]: Toolbox needs a model capable of calling tools; other multimodal capabilities depend on the custom model. Complete parity and failure behaviour are undocumented. Sources: typingmind:typingmind:toolbox, typingmind:typingmind:manage-ai-models. - vendor_hosted_open_models — Does the vendor host open-weight models in EU/CH? [unknown]: Does the vendor host open-weight models in EU/CH? No vendor-hosted open-weight EU/CH model service, supported embedding substitution or full self-host-model parity matrix was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:r2-teams-custom-models, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:ollama, typingmind:typingmind:lmstudio, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:cloud-host-vs-self-host, typingmind:typingmind:toolbox, typingmind:typingmind:manage-ai-models ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Professional administrators govern model access and configurable consumption limits. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional for governance; customer-configured limits; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - model_allowlist_by_group — Can admins limit models per group? [supported]: Admins restrict model availability by user group; the limits guide still points availability controls to the legacy model-limits section. Sources: typingmind:typingmind:restrict-model-access, typingmind:typingmind:usage-limits. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [partial]: Admins configure the models available to agents and their knowledge access. No content-classification or connector-label-based model egress rule was established. Sources: typingmind:typingmind:roles-and-permissions, typingmind:typingmind:connect-knowledge-base-to-your-ai-agents. - default_model — Can admins set the default model? [unknown]: No Teams administrator control setting the default model for new chats was established. The October multi-model finalization default is a different feature; the plan matrix and model-management documents do not resolve this atom. - user_limits — What per-user message or token limits apply, and are they published? [supported]: Reusable limit groups configure message, character and token limits per time period, across users/groups, models, agents and plugins. Published examples are admin settings, not plan-wide quotas. Sources: typingmind:typingmind:usage-limits. - limit_behaviour — What happens when a limit is reached? [partial]: Users see a configurable limitation notice and can inspect details. Exact block, downgrade, overshoot and reset semantics at exhaustion were not established. Sources: typingmind:typingmind:usage-limits. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:restrict-model-access, typingmind:typingmind:usage-limits, typingmind:typingmind:roles-and-permissions, typingmind:typingmind:connect-knowledge-base-to-your-ai-agents ## 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Document text can be attached to chat; full-context training files and RAG are distinct. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - formats — Which formats are accepted? [supported]: The chat guide lists PDF, Markdown, CSV, XLSX, TXT, DOCX, JSON and HTML. Images require a suitable vision model. Sources: typingmind:typingmind:chat-with-documents. - limits — What size and count limits apply per file and chat? [partial]: Chat uploads are bounded by the selected model’s context, but a numeric per-chat file-count/size limit was not established. The separate KB documents 50MB uploads. Sources: typingmind:typingmind:chat-with-documents, typingmind:typingmind:how-knowledge-base-works-in-typingmind-team. - ocr — Are scanned PDFs read? [unknown]: Are scanned PDFs read? No scanned-PDF OCR accuracy, spreadsheet-preservation fixture or numerical ordinary-chat upload matrix was established. - spreadsheets — Are Excel tables read with structure intact? [partial]: XLSX and CSV are accepted; Toolbox executes local Python/JavaScript analysis. Preservation of merged cells, formula results and workbook structure was not tested. Sources: typingmind:typingmind:chat-with-documents, typingmind:typingmind:toolbox. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: Ordinary chat document text enters chat context and can later leave the model window; agent training files are injected into system context, while KB access retrieves relevant chunks. These are separate modes. Sources: typingmind:typingmind:chat-with-documents, typingmind:typingmind:training-files-vs-knowledge-base. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:chat-with-documents, typingmind:typingmind:how-knowledge-base-works-in-typingmind-team, typingmind:typingmind:toolbox, typingmind:typingmind:training-files-vs-knowledge-base ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Growth and above provide a tagged organization KB bound to agents; the technical guide still labels it Early Access. Availability: beta Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Growth/Professional: RAG and tagged agent KB; Professional additionally supplies group/resource visibility restrictions; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Current plan matrix sells RAG in Growth/Professional, while the technical KB guide (updated2025-11-10) still labels it Early Access. No dated GA transition or tenant rollout was verified; findings retain beta/Early Access qualification. - No source-user permission fixture was run. - persistent_collections — Can users keep document collections across chats? [supported]: The organization KB persists documents and connected data across conversations; this differs from temporary chat uploads and full-context agent training files. Sources: typingmind:typingmind:get-started-with-knowledge-base, typingmind:typingmind:training-files-vs-knowledge-base. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [partial]: Growth/Professional support tagged KB data bound to agents. Per-user/group agent restrictions require Professional governance; these restrictions do not establish per-document source ACL mirroring. Sources: typingmind:typingmind:connect-knowledge-base-to-your-ai-agents, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:r2-plan-matrix. - size_limits — What are the collection limits? [supported]: The KB guide states 50MB per upload and one million included training characters with extra capacity purchasable; indexed chunks are about 3,000 words and retrieval is up to five chunks. Sources: typingmind:typingmind:how-knowledge-base-works-in-typingmind-team. - assistant_binding — Can collections be bound to an assistant? [supported]: Knowledge Base Access in an agent selects tags identifying the accessible data. Sources: typingmind:typingmind:connect-knowledge-base-to-your-ai-agents. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:get-started-with-knowledge-base, typingmind:typingmind:training-files-vs-knowledge-base, typingmind:typingmind:connect-knowledge-base-to-your-ai-agents, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:how-knowledge-base-works-in-typingmind-team ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Named knowledge integrations and extensible tools exist; broad source mentions lack enterprise permission detail. Availability: beta Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Growth/Professional SaaS RAG; separate annual commercial Teams self-host licence with optional KB and customer-managed connector credentials; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Current plan matrix sells RAG in Growth/Professional, while the technical KB guide (updated2025-11-10) still labels it Early Access. No dated GA transition or tenant rollout was verified; findings retain beta/Early Access qualification. - A reachable self-host plugin endpoint is not a native file-share crawler. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: The training-files comparison mentions OneDrive as a possible KB source; no retrieved setup guide establishes SharePoint, Outlook or Teams ingestion, permissions or maintenance. Sources: typingmind:typingmind:training-files-vs-knowledge-base. - google_workspace — Which Google sources are connected? [partial]: Growth/Professional SaaS RAG names Google Drive. In the separate commercial Teams self-host package, external KB connectors require the operator’s OAuth configuration. Gmail and the full Workspace source set remain unverified. Sources: typingmind:typingmind:get-started-with-knowledge-base, typingmind:typingmind:setup-external-connectors-for-knowledge-base, typingmind:typingmind:r2-plan-matrix. - atlassian — Confluence and Jira? [unknown]: Confluence and Jira? No first-party Confluence/Jira connector setup, complete M365 connector matrix or maintained on-prem file-share connector was established. - other_systems — Which other business systems? [supported]: KB documentation names Notion and GitHub; admins select Notion pages/databases. Separate MCP/HTTP plugins can query other systems without proving a maintained KB connector. Sources: typingmind:typingmind:get-started-with-knowledge-base, typingmind:typingmind:connect-with-your-notion-pages, typingmind:typingmind:mcp. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Self-host operators can explicitly permit private custom-model/plugin/agent endpoints; custom database actions are described. A supported file-share crawler is not established. Sources: typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:overview. - connector_provider — Who builds and maintains each connector? [partial]: TypingMind documents built-in KB setup; external self-host sources need operator-managed OAuth credentials and Firecrawl for web scraping. MCP servers and custom plugins have separate maintainers. Sources: typingmind:typingmind:setup-external-connectors-for-knowledge-base, typingmind:typingmind:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:training-files-vs-knowledge-base, typingmind:typingmind:get-started-with-knowledge-base, typingmind:typingmind:setup-external-connectors-for-knowledge-base, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:connect-with-your-notion-pages, typingmind:typingmind:mcp, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:overview ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Documented access control is by tagged knowledge and agent/group visibility; per-user source ACL enforcement is unproven. Availability: beta Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Growth/Professional RAG data/tag selection; Professional adds group-based resource restrictions; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Current plan matrix sells RAG in Growth/Professional, while the technical KB guide (updated2025-11-10) still labels it Early Access. No dated GA transition or tenant rollout was verified; findings retain beta/Early Access qualification. - No two-user source-permission or revocation fixture. - source_permissions_respected — Are source permissions enforced per user? [unknown]: Are source permissions enforced per user? No two-user permission/revocation fixture, source ACL mirror, revocation SLA or Microsoft Purview-label enforcement documentation was retrieved. Do not equate agent access with source-user permissions. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: Growth/Professional bind data tags to agents; Professional adds agent availability by user/group. This application-side mechanism does not establish synchronized source-user ACLs. Sources: typingmind:typingmind:connect-knowledge-base-to-your-ai-agents, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:r2-plan-matrix. - revocation_delay — How quickly does a removed permission take effect? [unknown]: How quickly does a removed permission take effect? No two-user permission/revocation fixture, source ACL mirror, revocation SLA or Microsoft Purview-label enforcement documentation was retrieved. Do not equate agent access with source-user permissions. - admin_scope_controls — Can admins exclude sites, folders or labels? [supported]: Admins choose the Notion pages/databases to ingest and select knowledge tags for each agent. Sources: typingmind:typingmind:connect-with-your-notion-pages, typingmind:typingmind:connect-knowledge-base-to-your-ai-agents. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: Are Microsoft Purview or similar labels respected? No two-user permission/revocation fixture, source ACL mirror, revocation SLA or Microsoft Purview-label enforcement documentation was retrieved. Do not equate agent access with source-user permissions. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:connect-knowledge-base-to-your-ai-agents, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:connect-with-your-notion-pages ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial The KB indexes copies, refreshes connected content daily and uses selected SaaS or customer-hosted storage. Availability: beta Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Growth/Professional SaaS RAG; separately quoted annual Teams self-host licence and optional PostgreSQL KB; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Current plan matrix sells RAG in Growth/Professional, while the technical KB guide (updated2025-11-10) still labels it Early Access. No dated GA transition or tenant rollout was verified; findings retain beta/Early Access qualification. - No synchronization/deletion latency fixture. - live_or_indexed — Is content searched live or copied into an index? [supported]: RAG splits and embeds copied source text in a knowledge index; full-context training files and live custom tools are separate. Sources: typingmind:typingmind:training-files-vs-knowledge-base. - sync_interval — How often does an index refresh? [supported]: The KB guide describes daily connected-source refresh; Notion initial sync takes a few minutes. Neither is a permission-revocation guarantee. Sources: typingmind:typingmind:how-knowledge-base-works-in-typingmind-team, typingmind:typingmind:connect-with-your-notion-pages. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: How quickly does a deleted document disappear? Deleted-document propagation and exact SaaS index/backup location were not established. - index_location — Where is indexed content stored? [partial]: Opt-in EU SaaS uses Vercel/AWS EU resources; optional self-host KB uses the operator’s PostgreSQL pgvector database and blob configuration. Exact SaaS index, backup and telemetry placement is not itemized. Sources: typingmind:typingmind:eu-data-center, typingmind:typingmind:get-started-with-self-host-installation-instruct. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:training-files-vs-knowledge-base, typingmind:typingmind:how-knowledge-base-works-in-typingmind-team, typingmind:typingmind:connect-with-your-notion-pages, typingmind:typingmind:eu-data-center, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:cloud-host-vs-self-host ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Clickable source references are documented, but retrieval quality has no observed multilingual fixture. Availability: beta Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Growth/Professional SaaS RAG and reference display; model-followed instructions separate from retrieval guarantees; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Current plan matrix sells RAG in Growth/Professional, while the technical KB guide (updated2025-11-10) still labels it Early Access. No dated GA transition or tenant rollout was verified; findings retain beta/Early Access qualification. - No shared multilingual/citation-accuracy fixture. - citations — Are answers linked to specific sources? [supported]: Admins may enable reference display for knowledge responses so users can follow source links. Sources: typingmind:typingmind:get-started-with-knowledge-base. - citation_accuracy — Do the cited passages support the answer? [unknown]: Do the cited passages support the answer? No shared German/French/English question set, source-support check, cross-language retrieval test or measured answer count was run. - cross_language — Does a question in one language find documents in another? [unknown]: Does a question in one language find documents in another? No shared German/French/English question set, source-support check, cross-language retrieval test or measured answer count was run. - no_answer_behaviour — Does it say when the corpus has no answer? [partial]: Admins can instruct the model to refrain from answering when knowledge is insufficient; the system-prompt guide gives an example. This is prompt configuration, not a tested no-answer guarantee. Sources: typingmind:typingmind:system-prompts-on-admin-panel. - observed_accuracy — How many of the question set were answered correctly? [unknown]: How many of the question set were answered correctly? No shared German/French/English question set, source-support check, cross-language retrieval test or measured answer count was run. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:get-started-with-knowledge-base, typingmind:typingmind:system-prompts-on-admin-panel, typingmind:typingmind:r2-plan-matrix ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Persistent agent and global admin instructions are documented; named-tier cross-chat memory and its controls remain unknown. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS Starter/Growth/Professional instructions and shared agents; exact commercial entitlement for non-project memory and its controls unverified; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Persistent instructions are distinct from learned cross-chat memory. The Memory guide and release do not establish its named-tier entitlement. - custom_instructions — Can users set persistent instructions? [supported]: Persistent agent instructions and global admin instructions are documented; agents can include full-context training files. Sources: typingmind:typingmind:system-prompts-on-admin-panel, typingmind:typingmind:training-files-vs-knowledge-base. - cross_chat_memory — Does the product remember facts across chats? [unknown]: The October 14 Teams release and Memory guide describe cross-chat memory, but no named Starter/Growth/Professional entitlement for that capability was established. The Growth/Professional Projects gate does not establish non-project memory availability. - user_memory_controls — Can users view, edit and delete memories? [unknown]: The Memory guide describes saved-memory settings, but their named Teams tier entitlement and complete edit/delete behavior remain unverified. No personal-app control is inferred to be a Teams entitlement. - admin_memory_controls — Can admins turn memory off? [unknown]: The October 14 Teams release describes an admin Memory switch, but the current plan matrix does not map it to a named tier. Organization-wide memory-control entitlement remains unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:system-prompts-on-admin-panel, typingmind:typingmind:training-files-vs-knowledge-base, typingmind:typingmind:release, typingmind:typingmind:memory, typingmind:typingmind:r2-plan-matrix ## 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: supported Teams admins publish agents and prompts, with delegated creation permissions and group access. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Starter/Growth/Professional shared agents and prompts; Growth/Professional RAG; Professional delegated roles and resource visibility; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: All SaaS tiers include shared agents and configured models/plugins; tagged RAG knowledge requires Growth/Professional. Sources: typingmind:typingmind:build-a-shared-ai-agent-collection, typingmind:typingmind:training-files-vs-knowledge-base, typingmind:typingmind:r2-plan-matrix. - creator_permissions — Can admins limit who creates them? [supported]: Professional custom roles delegate AI Agent management separately from other Admin Panel permissions. Sources: typingmind:typingmind:roles-and-permissions, typingmind:typingmind:r2-plan-matrix. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: All tiers publish shared agent collections; Professional adds per-user/group resource restrictions. Sources: typingmind:typingmind:build-a-shared-ai-agent-collection, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:r2-plan-matrix. - catalogue — Is there an internal assistant directory? [supported]: The shared agent collection is displayed in the team chat UI. Sources: typingmind:typingmind:build-a-shared-ai-agent-collection. - prompt_library — Are shared prompt templates available? [supported]: All SaaS tiers provide a shared prompt library; Professional adds per-user prompt visibility controls. Sources: typingmind:typingmind:build-a-shared-prompt-library, typingmind:typingmind:r2-plan-matrix. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:build-a-shared-ai-agent-collection, typingmind:typingmind:training-files-vs-knowledge-base, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:roles-and-permissions, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:build-a-shared-prompt-library ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Built-in plugins and custom HTTP/JavaScript/MCP tools are available; authentication varies by connector. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, TypingMind personal browser app and PWA; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Starter/Growth/Professional plugins and remote MCP; Professional group restrictions; personal Private MCP Connector route separate; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=Remote server/provider regions depend on configuration; personal local MCP is not a verified Teams local route; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - builtin_tools — Which tools are built in? [supported]: Documented tools include Toolbox, web/deep research, image generation and voice services; optional third-party API keys may be required. Sources: typingmind:typingmind:toolbox, typingmind:typingmind:deep-research, typingmind:typingmind:image, typingmind:typingmind:voice. - custom_actions — Can admins add API actions? [supported]: Custom actions can be implemented as JavaScript, HTTP actions or MCP integrations. Sources: typingmind:typingmind:overview. - mcp_client — Can it use remote MCP servers, and with what admin control? [partial]: Teams pricing lists MCP integration and the MCP guide explicitly gives Team OAuth callbacks and per-user/per-chat sessions for remote HTTP MCP. The Private MCP Connector and local terminal-command procedure are explicitly personal-app routes; Teams local MCP support is unverified. Sources: typingmind:typingmind:mcp, typingmind:typingmind:pricing, typingmind:typingmind:r2-plan-matrix. - tool_auth — Do tools act as the user or as a shared account? [partial]: Teams remote MCP supports user OAuth and per-user sessions; separately configured plugins may use shared keys. The personal Private MCP Connector is not claimed for Teams. Sources: typingmind:typingmind:mcp, typingmind:typingmind:deep-research, typingmind:typingmind:r2-plan-matrix. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Professional admins restrict plugin visibility/usage by group. The MCP guide allows tools to be disabled individually; a mandatory per-action side-effect confirmation policy and Teams local connector are unverified. Sources: typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:mcp, typingmind:typingmind:r2-plan-matrix. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:toolbox, typingmind:typingmind:deep-research, typingmind:typingmind:image, typingmind:typingmind:voice, typingmind:typingmind:overview, typingmind:typingmind:mcp, typingmind:typingmind:pricing, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:restrict-plugin-access ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Deep Research is a configurable search/read/report plugin with separate provider accounts. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams plugin access on Starter/Growth/Professional; Professional for group availability/limits; add_ons=Customer SerpAPI and Firecrawl keys; model API charges; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - web_search — Is web search available? [supported]: The Deep Research plugin performs iterative web search and page reading. Sources: typingmind:typingmind:deep-research. - admin_toggle — Can admins disable it per organisation or group? [supported]: Professional admins restrict the research/search plugin to selected user groups through Plugin Access and Limits. Sources: typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix. - search_provider — Which search provider handles queries, and where? [partial]: This plugin requires SerpAPI for search and Firecrawl for page retrieval; processing countries for queries/content were not established. Sources: typingmind:typingmind:deep-research. - deep_research — Is multi-step research with a report available? [supported]: The plugin plans and iterates search/reading into a report, within its documented two-minute execution bound. Sources: typingmind:typingmind:deep-research. - web_citations — Are web sources cited? [partial]: The research plugin produces a sourced report, but link completeness and citation accuracy were not independently checked. Sources: typingmind:typingmind:deep-research. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:deep-research, typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial The documented automation layer uses agents and plugins rather than an established visual scheduling system. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, TypingMind Teams REST API; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams plugins/agents on Starter/Growth/Professional; Professional external REST API integration; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - workflow_builder — Is there a workflow or chain builder? [partial]: Docs describe composing AI interactions with JavaScript/HTTP/MCP plugins and business automation examples. A visual DAG/chain builder was not established. Sources: typingmind:typingmind:overview. - scheduled_tasks — Can prompts or assistants run on a schedule? [unknown]: Can prompts or assistants run on a schedule? No native recurring scheduler, durable workflow engine or supported event trigger setup was established. - event_triggers — Can external events start a workflow? [partial]: Professional external REST integration lets an external application call a Teams chat/agent API. This is a developer invocation route, not an established native managed trigger engine. Sources: typingmind:typingmind:api-integration-overview, typingmind:typingmind:r2-plan-matrix. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Team users use shared agents; technical builders configure JavaScript/HTTP plugins and credentials. Professional custom roles delegate administration, and its API supports developer integrations. Sources: typingmind:typingmind:overview, typingmind:typingmind:roles-and-permissions, typingmind:typingmind:r2-plan-matrix. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:overview, typingmind:typingmind:api-integration-overview, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:roles-and-permissions ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Multi-step tool workflows exist; universal side-effect confirmation and run controls remain unproven. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: The Deep Research plugin repeatedly searches/reads, and automation docs describe tool-driven multistep business actions. Sources: typingmind:typingmind:deep-research, typingmind:typingmind:overview. - visible_steps — Are steps and tool calls shown? [partial]: The research workflow is described as iterative search and page reading, but a complete visible execution trace for all agents/tools was not established. Sources: typingmind:typingmind:deep-research. - side_effect_confirmation — Must the user confirm actions with side effects? [unknown]: Must the user confirm actions with side effects? No bounded run verified visible traces, stop behaviour, rollback or mandatory side-effect confirmation for all custom tools. - stop_control — Can the user stop a running task? [unknown]: Can the user stop a running task? No bounded run verified visible traces, stop behaviour, rollback or mandatory side-effect confirmation for all custom tools. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:deep-research, typingmind:typingmind:overview ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial The Teams REST API creates chat/agent responses with governed api-users. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams REST API; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional API integration; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - chat_api — Is there an API for chat and assistants? [supported]: Teams REST endpoints produce model or agent responses, including configured plugins, KB and MCP capabilities. Sources: typingmind:typingmind:api-integration-overview. - knowledge_api — Can documents be loaded through an API? [unknown]: Can documents be loaded through an API? The retrieved API overview did not establish a supported knowledge-upload API or an MCP server exposing TypingMind itself. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: An API key creates an api-user subject to the same user restrictions and usage limits. Complete audit coverage, currency budgets and all API routes were not established. Sources: typingmind:typingmind:api-integration-overview. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: Does the product expose itself to other agents over MCP? The retrieved API overview did not establish a supported knowledge-upload API or an MCP server exposing TypingMind itself. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:api-integration-overview ## 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial The primary client is a browser app; installable PWAs are documented separately from native apps. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, TypingMind personal browser app and PWA; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS Starter/Growth/Professional browser chat; PWA installation findings only for personal typingmind.com (licence feature gates separate); add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - web — Is a full web client available? [supported]: Teams supplies a branded browser chat interface and separate Admin Panel. Sources: typingmind:typingmind:typingmind-vs-typingmind-team. - desktop_apps — Windows and macOS apps? [partial]: The personal typingmind.com app has browser-PWA installation instructions for Windows/macOS; this is not evidence of a Teams native desktop app or Teams PWA deployment entitlement. Sources: typingmind:typingmind:install, typingmind:typingmind:r2-personal-bulk-licence. - mobile_apps — iOS and Android apps with SSO? [partial]: Personal typingmind.com can be added to iOS/Android home screens as a browser PWA. Teams Professional SSO is a separate entitlement; no Teams installable mobile client or mobile SSO fixture was verified. Sources: typingmind:typingmind:install, typingmind:typingmind:r2-personal-bulk-licence, typingmind:typingmind:r2-plan-matrix. - browser_extension — Is there a browser extension or sidebar? [unknown]: Is there a browser extension or sidebar? No MDM packaging/configuration, supported browser sidebar/extension or mobile feature-parity matrix was established. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: Can IT deploy and configure clients through MDM? No MDM packaging/configuration, supported browser sidebar/extension or mobile feature-parity matrix was established. - client_feature_gaps — Which features are missing on mobile? [unknown]: Which features are missing on mobile? No MDM packaging/configuration, supported browser sidebar/extension or mobile feature-parity matrix was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:typingmind-vs-typingmind-team, typingmind:typingmind:install, typingmind:typingmind:r2-personal-bulk-licence, typingmind:typingmind:r2-plan-matrix ### 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. #### TypingMind / TypingMind Teams 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. #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configurable model instructions support writing workflows; dedicated translation fidelity is unestablished. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - document_translation — Can whole documents be translated with formatting kept? [unknown]: Can whole documents be translated with formatting kept? No whole-document formatting-preserving translation fixture, company glossary engine or Swiss language-quality test was retrieved. - translation_engine — Which engine translates? [partial]: Writing/translation prompts are handled by the customer-selected LLM; no separate translation engine or formatting-preserving document pipeline was established. Sources: typingmind:typingmind:manage-ai-models, typingmind:typingmind:system-prompts-on-admin-panel. - glossaries — Are company glossaries supported? [unknown]: Are company glossaries supported? No whole-document formatting-preserving translation fixture, company glossary engine or Swiss language-quality test was retrieved. - formality_and_variants — Can formality and regional variants (de-CH) be set? [partial]: Global and agent instructions can specify tone and language, but no dedicated de-CH/formality switch or quality guarantee was established. Sources: typingmind:typingmind:system-prompts-on-admin-panel. - writing_tools — Are dedicated rewrite and proofreading tools available? [partial]: Shared prompts and marketing-writing workflows support rewriting tasks; a dedicated proofreading interface and correction-quality fixture were not established. Sources: typingmind:typingmind:build-a-shared-prompt-library, typingmind:typingmind:ad-creative-generator. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:manage-ai-models, typingmind:typingmind:system-prompts-on-admin-panel, typingmind:typingmind:build-a-shared-prompt-library, typingmind:typingmind:ad-creative-generator ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial GPT Image generation and editing use customer API credentials and controllable plugins. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams plugin access on Starter/Growth/Professional; Professional for group-based image-plugin governance; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - image_generation — Can users generate images, with which models? [supported]: The GPT Image 2.5 plugin documents image generation through the customer’s OpenAI API. Sources: typingmind:typingmind:image. - image_editing — Can users edit uploaded images? [supported]: The October 2 changelog says GPT Image editing accepts any image in a chat, including attachments and artifact images. Sources: typingmind:typingmind:release, typingmind:typingmind:image. - admin_control — Can admins restrict image generation? [partial]: Professional admins restrict the image plugin by user group. Coverage of every provider-native image route remains unverified. Sources: typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix. - usage_terms — What usage rights apply to output? [partial]: The Terms say users own their content, subject to provider terms. No independent clearance of third-party rights or all model-provider output licences was performed. Sources: typingmind:typingmind:terms-of-service. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:image, typingmind:typingmind:release, typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:terms-of-service ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dictation, read-aloud and audio-summary workflows are documented; live meetings and Swiss German quality are unknown. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - dictation — Can users dictate prompts? [supported]: Dictation uses browser speech recognition or customer OpenAI Whisper, Groq or Azure transcription credentials; Teams admins configure keys. Sources: typingmind:typingmind:voice. - read_aloud — Can answers be read aloud? [supported]: Browser speech, ElevenLabs or OpenAI TTS reads answers aloud with playback/autoplay controls. Sources: typingmind:typingmind:tts. - voice_conversation — Is a live voice mode available? [unknown]: Is a live voice mode available? No full-duplex live voice mode, Swiss German audio fixture or native meeting-attendance integration was established. - meeting_summaries — Are meetings transcribed and summarised? [partial]: The meeting-summarizer workflow uses recorded audio transcription and LLM summaries; Whisper upload is capped at 25MB. No live meeting bot or diarization quality test was established. Sources: typingmind:typingmind:meeting-summarizer, typingmind:typingmind:voice. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Is Swiss German speech recognised? No full-duplex live voice mode, Swiss German audio fixture or native meeting-attendance integration was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:voice, typingmind:typingmind:tts, typingmind:typingmind:meeting-summarizer ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: supported Toolbox executes code locally and produces charts and Office documents; Growth includes Canvas. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Growth/Professional for Canvas; Toolbox on tool-capable models with separate API usage; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Toolbox runs Python/JavaScript in the browser, including tabular analysis libraries. Network is disabled by default; analysis is not a vendor EU code-execution guarantee. Sources: typingmind:typingmind:toolbox. - charts — Can it produce charts? [supported]: Toolbox supports chart generation with Plotly and Bokeh. Sources: typingmind:typingmind:toolbox. - office_file_output — Can it create Word, Excel or PowerPoint files? [supported]: Toolbox creates/edits documents, spreadsheets, presentations and PDFs, including Office formats. Sources: typingmind:typingmind:toolbox. - canvas_editing — Is there a document or canvas editor for iterating on output? [supported]: The Teams plan comparison lists Canvas and Artifacts for Growth and Professional. Sources: typingmind:typingmind:compare-typingmind-team-plans. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:toolbox, typingmind:typingmind:compare-typingmind-team-plans ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Shared agents and prompt libraries are documented, but collaborative project/chat boundaries are not established. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - share_chats — Can chats be shared inside the organisation? [unknown]: Can chats be shared inside the organisation? No Teams-specific shared-chat recipient ACL/redaction guarantee, simultaneous multi-person AI conversation or source-permission sharing fixture was established. - team_spaces — Are shared projects or workspaces available? [partial]: Teams share an agent catalogue and prompt library; project-scoped memory is documented. Shared project membership and cross-user workspace semantics were not established. Sources: typingmind:typingmind:build-a-shared-ai-agent-collection, typingmind:typingmind:build-a-shared-prompt-library, typingmind:typingmind:release. - group_chat — Can several people chat together with the AI? [unknown]: Can several people chat together with the AI? No Teams-specific shared-chat recipient ACL/redaction guarantee, simultaneous multi-person AI conversation or source-permission sharing fixture was established. - share_permission_boundary — Does sharing respect the recipient's access to sources? [unknown]: Does sharing respect the recipient's access to sources? No Teams-specific shared-chat recipient ACL/redaction guarantee, simultaneous multi-person AI conversation or source-permission sharing fixture was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:build-a-shared-ai-agent-collection, typingmind:typingmind:build-a-shared-prompt-library, typingmind:typingmind:release ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Multilingual capability is advertised without a verified DACH UI or accessibility matrix. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - ui_languages — Which UI languages are offered? [partial]: Teams plan documentation advertises a multilingual chat interface and a public translation collaboration project exists. A complete current language list was not established. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:translations. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: Are German, French and Italian UIs complete and natural? No complete German/French/Italian UI review, German Admin Panel guarantee, WCAG conformance statement or assistive-technology fixture was retrieved. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: Is there a WCAG conformance statement? No complete German/French/Italian UI review, German Admin Panel guarantee, WCAG conformance statement or assistive-technology fixture was retrieved. - admin_ui_languages — Is the admin interface available in German? [unknown]: Is the admin interface available in German? No complete German/French/Italian UI review, German Admin Panel guarantee, WCAG conformance statement or assistive-technology fixture was retrieved. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind: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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams Professional provides SAML SSO and OAuth/OIDC options. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional identity features; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - sso_protocols — Which SSO protocols and identity providers work? [supported]: SAML SSO accepts IdP metadata and multiple connections; OAuth/OIDC includes Microsoft, Google and custom provider configuration. Sources: typingmind:typingmind:sso, typingmind:typingmind:o-auth-2-0. - sso_plan — Which plan includes SSO? [supported]: The plan comparison places SSO/OAuth and Directory Sync in Professional. Sources: typingmind:typingmind:compare-typingmind-team-plans. - mfa — Can MFA be enforced? [partial]: The DPA security measures mention MFA and SSO; documented tenant-level enforcement settings and IdP MFA propagation were not verified. Sources: typingmind:typingmind:data-processing-agreement. - conditional_access — Do Entra conditional-access policies apply? [unknown]: Do Entra conditional-access policies apply? No Entra conditional-access test or verified-domain capture/mandatory login policy was established. - domain_capture — Can the company claim its email domain? [unknown]: Can the company claim its email domain? No Entra conditional-access test or verified-domain capture/mandatory login policy was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:sso, typingmind:typingmind:o-auth-2-0, typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:data-processing-agreement ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Professional supports SCIM, group sync and JIT; OAuth revocation alone does not remove a seat. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional Directory Sync; distinguish SCIM suspension from OAuth revocation; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - scim — Is SCIM provisioning supported? [supported]: SCIM v2 creates, updates and suspends users from a compatible IdP. Sources: typingmind:typingmind:scim. - group_sync — Are identity-provider groups synced? [supported]: Directory Sync assigns users to corresponding groups received from the identity provider. Sources: typingmind:typingmind:scim. - jit_provisioning — Are users created at first login? [supported]: OAuth login can create a user on first sign-in and consumes an available seat; creation fails without a free seat. Sources: typingmind:typingmind:o-auth-2-0. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: SCIM suspends users; separate OAuth docs warn that revoking IdP authorization alone does not remove an existing user, requiring admin removal. Shared asset ownership, deletion and session-revocation timing are not established. Sources: typingmind:typingmind:scim, typingmind:typingmind:o-auth-2-0. - seat_assignment — Can admins assign and reclaim seats? [partial]: Admins invite/manage users and JIT consumes purchased seats. Exact seat reclamation timing, licence proration and asset transfer were not established. Sources: typingmind:typingmind:invite-team-members, typingmind:typingmind:o-auth-2-0. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:scim, typingmind:typingmind:o-auth-2-0, typingmind:typingmind:invite-team-members ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Custom admin roles and user groups provide delegated management and feature availability controls. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional custom roles, resource groups and usage limits; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: Default Admin has highest permissions. Owners create custom roles for models, plugins, agents, reporting, billing, users, keys, KB and portal settings. Users may hold multiple roles; the former Content Moderator preset was removed. Sources: typingmind:typingmind:roles-and-permissions. - groups — Can permissions be set per group? [supported]: User groups govern resource visibility and limits. Admin roles are assigned to individual members; assigning roles to groups is still described as coming soon. Sources: typingmind:typingmind:roles-and-permissions, typingmind:typingmind:create-and-manage-user-groups. - feature_toggles — Which features can be switched on or off per group? [supported]: Professional provides model, agent and plugin group availability/usage controls through resource Access/Limit settings; the plan matrix separately lists per-user prompt visibility. CSS/themes are excluded from this permission finding. Sources: typingmind:typingmind:restrict-model-access, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix. - multi_entity — Can subsidiaries or departments be separated within one contract? [unknown]: Can subsidiaries or departments be separated within one contract? No multi-subsidiary legal/entity separation, independent subtenant keys or consolidated contract administration was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:roles-and-permissions, typingmind:typingmind:create-and-manage-user-groups, typingmind:typingmind:restrict-model-access, typingmind:typingmind:restrict-ai-agents-access, typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams analytics reports adoption and consumption, including identifiable user breakdowns. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional analytics; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - adoption_dashboard — Is there an adoption dashboard? [supported]: Dashboard counts active users, messages, conversations, characters and estimated tokens over a selected period. Sources: typingmind:typingmind:chatbot-analytics. - breakdowns — Can usage be broken down by group, model, feature and assistant? [supported]: Reporting filters by user, group, model and agent; a complete per-feature cost map was not established. Sources: typingmind:typingmind:chatbot-analytics. - export — Can usage data be exported? [partial]: Charts can be downloaded; a complete raw usage ledger export format was not established. Sources: typingmind:typingmind:chatbot-analytics. - privacy_modes — Can per-person reporting be limited or pseudonymised? [unknown]: Can per-person reporting be limited or pseudonymised? No pseudonymised reporting mode or enforceable per-person aggregation threshold was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:chatbot-analytics ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admins can inspect estimated consumption and set token/message limits; monetary budgets are unestablished. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional; API charges billed directly by customer providers; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Analytics shows estimated token and character usage per user/group/model/agent. Customer model bills remain external; reconciled currency cost is not established. Sources: typingmind:typingmind:chatbot-analytics. - budgets — Can budgets be set per user or group? [partial]: Admins configure reusable token/message/character limits for users/groups and resources, rather than an evidenced currency-denominated budget. Sources: typingmind:typingmind:usage-limits. - budget_enforcement — Does reaching a budget alert, block or downgrade? [partial]: Users are shown applicable limits, but hard monetary blocking, alerts, downgrade and in-flight overshoot semantics were not established. Sources: typingmind:typingmind:usage-limits. - chargeback — Can costs be exported per cost centre? [unknown]: Can costs be exported per cost centre? No cost-centre chargeback ledger or exact monetary budget-enforcement documentation was retrieved. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:chatbot-analytics, typingmind:typingmind:usage-limits ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional chat recording exposes prompts and answers to authorized admins with retention and JSON export. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional chat logs; logging must be enabled; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - admin_events — Are admin and security events logged? [unknown]: Are admin and security events logged? No first-party security/admin event catalogue, legal hold or eDiscovery workflow was established. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [supported]: Record all chats is opt-in and off by default; authorized Admin Panel roles can view saved user prompts and model responses. Sources: typingmind:typingmind:view-and-export-user-chat-logs, typingmind:typingmind:export-chat-logs, typingmind:typingmind:roles-and-permissions. - siem_export — Can logs stream to a SIEM or be exported? [partial]: An API exports recorded chats as JSON, last 100 matching conversations per request with date filtering. Native SIEM streaming and complete audit-event export were not established. Sources: typingmind:typingmind:export-chat-logs. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: Are eDiscovery and legal hold supported? No first-party security/admin event catalogue, legal hold or eDiscovery workflow was established. - log_retention — How long are logs kept? [partial]: Admins set chat retention and old records are permanently deleted. A default duration and separate admin/security log retention were not established. Sources: typingmind:typingmind:view-and-export-user-chat-logs. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:view-and-export-user-chat-logs, typingmind:typingmind:export-chat-logs, typingmind:typingmind:roles-and-permissions ### 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 #### TypingMind / TypingMind Teams Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### ADM-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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Global instructions can govern chat behaviour, but policy acceptance and violation reporting remain unknown. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS global instructions; Professional for group/resource plugin restrictions; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - org_instructions — Can admins set organisation-wide instructions? [supported]: Admins set hidden global system instructions, few-shot examples and post-message reminders across chats and agents. Sources: typingmind:typingmind:system-prompts-on-admin-panel. - usage_notice — Can users be required to accept a usage policy? [unknown]: Can users be required to accept a usage policy? No mandatory policy-acceptance record, enforcement-grade content filter or admin policy-hit report was established. - content_filters — Are content filters configurable? [partial]: Admins configure model-followed instructions; Professional separately restricts plugin availability by group. Neither establishes deterministic PII/content filtering or a policy-enforcement engine. Sources: typingmind:typingmind:system-prompts-on-admin-panel, typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix. - violation_reporting — Are policy hits visible to admins? [unknown]: Are policy hits visible to admins? No mandatory policy-acceptance record, enforcement-grade content filter or admin policy-hit report was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:system-prompts-on-admin-panel, typingmind:typingmind:restrict-plugin-access, typingmind:typingmind:r2-plan-matrix ## 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial EU SaaS storage is optional; inference, tools and support are separate residency questions. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - storage_region — Where are chats, files and indexes stored? [partial]: Teams offers US and opt-in EU instances. The EU guide names Vercel web hosting and AWS database resources; exact file/index/backup components are not fully enumerated. Sources: typingmind:typingmind:eu-data-center, typingmind:typingmind:privacy-policy. - inference_region — Where do model calls run, per provider? [supported]: The EU guide explicitly warns model calls may go outside the EU. Customers can choose an EU Azure endpoint or private/local model; this is not an all-provider EU inference promise. Sources: typingmind:typingmind:eu-data-center. - backups_logs_region — Where are backups, logs and telemetry? [unknown]: Where are backups, logs and telemetry? Backup, telemetry, support-access country matrix and contractual Swiss-only end-to-end processing were not established. - support_access_region — From where can vendor staff access data? [partial]: The DPA identifies the processor at a Da Nang, Vietnam address and requires need-to-know confidentiality; actual operational staff access countries and restrictions were not established. Sources: typingmind:typingmind:data-processing-agreement. - swiss_hosting — Is Swiss hosting available? [partial]: Customer self-host can run on operator-selected infrastructure, but no vendor-operated Swiss SaaS region or complete CH-only processing undertaking was established. Sources: typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct. - residency_plan — Which plan or option provides residency? [supported]: The EU instance is an account/instance choice for Teams SaaS. Self-host is a separate quoted annual commercial licence, not the personal licence. Sources: typingmind:typingmind:eu-data-center, typingmind:typingmind:selfhost. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:eu-data-center, typingmind:typingmind:privacy-policy, typingmind:typingmind:data-processing-agreement, typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams offers multitenant SaaS and a separate commercial self-host package; offline operation is not established. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Marketing language about data staying on customer infrastructure must be read with model, embedding, licence and update egress requirements. - multi_tenant_saas — Is a shared SaaS offered? [supported]: The privacy policy explicitly describes Teams as server-stored multitenant SaaS, unlike the default local-storage personal app. Sources: typingmind:typingmind:privacy-policy. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [partial]: Self-host permits one customer-operated instance with five included users. A separate vendor-operated dedicated SaaS service and its minimum were not established. Sources: typingmind:typingmind:selfhost. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: A quoted self-host licence runs the NodeJS service, MySQL, optional PostgreSQL KB and blob store in the customer’s cloud account. Sources: typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: The self-host package can run on customer infrastructure with Docker/NodeJS and required databases; five users and one instance are included under the annual quote. Sources: typingmind:typingmind:selfhost. - air_gapped — Can it run without internet access? [partial]: The self-host FAQ lists external model requests plus update and licence checks. Private models reduce model egress, while the optional KB guide still requires OpenAI embeddings. A supported air-gapped licence was not established. Sources: typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct. - mode_feature_gaps — Which features are missing outside SaaS? [supported]: Self-host releases lag cloud by approximately one to three weeks; optional KB needs additional infrastructure, external OAuth setup and OpenAI embeddings. SLA/dedicated support is a separate paid option. Sources: typingmind:typingmind:selfhost, typingmind:typingmind:setup-external-connectors-for-knowledge-base, typingmind:typingmind:get-started-with-self-host-installation-instruct. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:privacy-policy, typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:setup-external-connectors-for-knowledge-base ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial TypingMind asserts no vendor training; customer provider contracts control training and retention. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - vendor_training — Does the vendor train on customer content? [supported]: The published policy says TypingMind does not use conversations for AI training. This is a vendor policy assertion, not an independently verified contract-wide audit. Sources: typingmind:typingmind:data-usage-and-model-training-policy. - provider_training — Do model providers train on it under this product's contracts? [partial]: Teams uses customer provider keys and direct customer provider contracts. The policy summarizes provider-specific training defaults; this pass did not verify every provider contract or free/paid API variant. Sources: typingmind:typingmind:set-up-api-keys, typingmind:typingmind:data-usage-and-model-training-policy. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [partial]: The policy discusses provider-dependent abuse monitoring, retention and paid/unpaid distinctions; no uniform current retention duration applies to every customer-selected route. Sources: typingmind:typingmind:data-usage-and-model-training-policy. - zero_retention — Is zero data retention available, and on which plan? [partial]: A customer may select a provider/endpoint with suitable terms, but no TypingMind-wide ZDR entitlement, plan or complete exception matrix was established. Sources: typingmind:typingmind:data-usage-and-model-training-policy, typingmind:typingmind:eu-data-center. - human_review — Can provider staff review content? [partial]: TypingMind’s provider summary says OpenAI authorized employees may review API data for abuse/legal compliance. Its Gemini section distinguishes paid no-training from unpaid improvement use and says human reviewers may read/annotate/process inputs and outputs for quality improvement. These are qualified vendor summaries, not verified terms for every customer paid/unpaid endpoint, ZDR approval or actual account. Sources: typingmind:typingmind:data-usage-and-model-training-policy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:data-usage-and-model-training-policy, typingmind:typingmind:set-up-api-keys, typingmind:typingmind:eu-data-center ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admins control recorded chat retention; termination deletion/return is contractual without a fixed public completion window. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional for admin chat recording/retention; general service privacy/DPA rights separate from personal/local history; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - default_retention — What is retained and for how long by default? [partial]: Professional admin chat recording is off by default; that is separate from user-visible history and personal browser storage. The privacy policy separately mentions90-day unpaid-account inactivity deletion with warning; a paid Teams history lifetime is not specified. Sources: typingmind:typingmind:export-chat-logs, typingmind:typingmind:privacy-policy, typingmind:typingmind:r2-plan-matrix. - admin_retention — Can admins set retention periods? [supported]: Professional chat-log settings set recorded-chat retention, with permanent deletion of older records. No personal/local or backup deletion interval is inferred. Sources: typingmind:typingmind:view-and-export-user-chat-logs, typingmind:typingmind:r2-plan-matrix. - user_deletion — Can users delete their chats and files permanently? [partial]: The privacy policy provides data-erasure rights; immediate permanent deletion across Teams files, backups and logs by the user UI was not established. Sources: typingmind:typingmind:privacy-policy. - contract_end_deletion — What is deleted at contract end, and when? [partial]: The DPA permits customer-choice deletion or return and certification on request, subject to legal retention; a fixed completion deadline and self-serve export window are not specified. Sources: typingmind:typingmind:data-processing-agreement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:export-chat-logs, typingmind:typingmind:privacy-policy, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:view-and-export-user-chat-logs, typingmind:typingmind:data-processing-agreement ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial A public DPA lists processors and transfer measures; vendor legal jurisdiction differs from hosting region. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - subprocessor_list — Is a dated sub-processor list published? [partial]: DPA Appendix II publishes a subprocessor list; no standalone dated list revision was visible in the retrieved document. Sources: typingmind:typingmind:data-processing-agreement. - subprocessor_countries — Which countries do sub-processors operate in? [supported]: The list includes AWS US/Germany, Render US, Vercel US/EU, US services including Sentry/Axiom/Customer.io/Stripe/HelpScout/Mailgun and Paddle US/UK. EU storage does not remove these separate vendor paths. Sources: typingmind:typingmind:data-processing-agreement. - change_notification — Are customers notified of sub-processor changes? [supported]: DPA 7.8 says the processor will endeavor to give 30 days’ notice of additions/replacements, with 15 days for objections; preserve the qualified notice wording. Sources: typingmind:typingmind:data-processing-agreement. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: Terms identify Typing Technology Co Ltd with Singapore governing law; the DPA gives a Vietnam processor address. Parent ownership/jurisdiction and actual staff locations were not independently established. Sources: typingmind:typingmind:terms-of-service, typingmind:typingmind:data-processing-agreement. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [supported]: DPA 7.9 and its SCC appendix provide EU transfer safeguards, subject to actual processing configuration; a Swiss-specific addendum was not established. Sources: typingmind:typingmind:data-processing-agreement. - government_access_policy — Is there a published government-access or transparency policy? [partial]: The privacy policy allows disclosures for authorized legal requests; no separate transparency report or detailed government-request policy was retrieved. Sources: typingmind:typingmind:privacy-policy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:data-processing-agreement, typingmind:typingmind:terms-of-service, typingmind:typingmind:privacy-policy ### 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. #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial A public GDPR DPA and Singapore-law business terms are available; Swiss and sector-specific undertakings remain gaps. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - dpa — Is a DPA available, and is it negotiable? [partial]: A public fillable GDPR Article 28 DPA names the processor, security measures and SCCs. Whether bespoke negotiation is available was not established. Sources: typingmind:typingmind:data-processing-agreement. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [partial]: The DPA expressly addresses GDPR and SCCs; explicit revised Swiss FADP/revDSG coverage was not established. Sources: typingmind:typingmind:data-processing-agreement. - governing_law — Which law and court govern the contract? [supported]: The September 17, 2026 Terms use Singapore law, with SIAC English-language business arbitration; the DPA SCC appendix separately uses EU exporter-state law/forum where applicable. Sources: typingmind:typingmind:terms-of-service, typingmind:typingmind:data-processing-agreement. - ai_act_materials — Is EU AI Act documentation provided? [unknown]: Is EU AI Act documentation provided? No EU AI Act compliance package, FINMA outsourcing materials or dedicated professional-secrecy agreement was retrieved. - sector_materials — Are FINMA or other sector materials provided? [unknown]: Are FINMA or other sector materials provided? No EU AI Act compliance package, FINMA outsourcing materials or dedicated professional-secrecy agreement was retrieved. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:data-processing-agreement, typingmind:typingmind:terms-of-service ### 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. #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial The self-host page claims SOC 2 Type II. A report with auditor, period and covered-service scope was not retrieved, and other attestations remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Commercial self-hosted TypingMind Teams server; version=Public self-host page retrieved 2026-10-26; no certificate verified; plan=Commercial Teams self-host marketing assurance claim; no customer report or SaaS certificate scope inferred; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Vendor assertion only. No independently verified report, certificate scope or validity was accessed; trust.typingmind.com returned HTTP 403. - iso_27001 — ISO 27001 with scope and validity? [unknown]: ISO 27001 with scope and validity? Trust Center access returned HTTP 403. The retrieved DPA security appendix is not an ISO/SOC/C5 certificate. Issuer, service scope, validity/report period, report-access process and independent penetration-test summary were not retrieved. - soc2 — SOC 2 type, period and covered service? [partial]: The vendor advertises SOC 2 Type II on the Teams self-host page. Auditor, report period, covered entity/service and applicability to a customer-operated deployment are unverified. Sources: typingmind:typingmind:r4-soc2-selfhost-claim. - c5 — BSI C5 attestation? [unknown]: BSI C5 attestation? Trust Center access returned HTTP 403. The retrieved DPA security appendix is not an ISO/SOC/C5 certificate. Issuer, service scope, validity/report period, report-access process and independent penetration-test summary were not retrieved. - other_certifications — Which other certificates (27701, 42001, TISAX)? [unknown]: Which other certificates (27701, 42001, TISAX)? Trust Center access returned HTTP 403. The retrieved DPA security appendix is not an ISO/SOC/C5 certificate. Issuer, service scope, validity/report period, report-access process and independent penetration-test summary were not retrieved. - report_access — How can customers obtain reports? [unknown]: How can customers obtain reports? Trust Center access returned HTTP 403. The retrieved DPA security appendix is not an ISO/SOC/C5 certificate. Issuer, service scope, validity/report period, report-access process and independent penetration-test summary were not retrieved. - pentest — Are independent penetration test summaries available? [unknown]: Are independent penetration test summaries available? Trust Center access returned HTTP 403. The retrieved DPA security appendix is not an ISO/SOC/C5 certificate. Issuer, service scope, validity/report period, report-access process and independent penetration-test summary were not retrieved. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: typingmind:typingmind:r4-soc2-selfhost-claim ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Encryption and private self-host infrastructure are documented without a SaaS customer-key guarantee. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server, TypingMind personal browser app and PWA; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS US/EU storage; separately quoted annual Teams self-host network controls; personal local-key claims explicitly separate; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Teams OpenAI route: server requests using centrally configured admin keys. Personal direct-browser/local-key assertions are not inherited by Teams. - The generic policy versus Teams FAQ scope discrepancy remains visible pending policy clarification. - encryption_at_rest — Is data encrypted at rest? [partial]: The EU guide says stored information is encrypted; exact cipher, key ownership and component coverage were not established. Personal optional cloud encryption is a different surface. Sources: typingmind:typingmind:eu-data-center, typingmind:typingmind:privacy-policy. - customer_managed_keys — Can the customer manage or hold the keys? [unknown]: Can the customer manage or hold the keys? No Teams SaaS customer-managed/held encryption-key option or complete private-connectivity configuration was established. - private_networking — Is private connectivity or IP restriction available? [partial]: Self-host permits customer network placement; localhost/private custom endpoints require ALLOW_UNSAFE_USER_ENDPOINTS. SaaS private links, IP allowlisting and private model routing were not established. Sources: typingmind:typingmind:get-started-with-self-host-installation-instruct. - tenant_isolation — How are customers separated in shared SaaS? [partial]: The privacy policy calls Teams multitenant; logical isolation implementation and independent tenant-boundary testing were not established. Sources: typingmind:typingmind:privacy-policy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:eu-data-center, typingmind:typingmind:privacy-policy, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:r2-teams-server-route ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial General GDPR confidentiality and configurable admin/model access are documented; a specific §203 or Art321 undertaking is unverified. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS Professional chat governance and separately quoted self-host licence; ordinary public DPA; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US/EU SaaS or customer self-host placement; customer provider contracts separate; os=not specified. Limitations: - DPA confidentiality, direct provider contracts and self-host placement alone do not establish professional-secrecy suitability. - No legal suitability or compliance conclusion. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: DPA7.4(c) limits personnel access and requires confidentiality/statutory duties. No signed/signon §203 StGB or Art321 StGB professional-secrecy undertaking was retrieved; ordinary GDPR confidentiality is not treated as that agreement. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: DPA7.8(d)-(e) requires substantially equivalent data-protection obligations and allows a redacted subprocessor agreement on request. A dedicated professional-secrecy undertaking flowing to subprocessors was not established. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: No specific professional-secrecy package/add-on or SaaS/self-host plan entitlement was established. Customer-operated infrastructure and the commercial self-host licence do not by themselves prove that undertaking. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: SaaS authorized personnel may access data only as needed under the DPA; customer admins with chat-log permission may inspect recorded prompts/answers when logging is enabled. Selected customer API providers process content; self-host placement changes operator access but model/embedding/blob routes remain relevant. A complete plaintext support/subprocessor/provider human-access matrix was not retrieved. Sources: typingmind:typingmind:dpa-confidentiality, typingmind:typingmind:view-and-export-user-chat-logs, typingmind:typingmind:roles-and-permissions, typingmind:typingmind:set-up-api-keys, typingmind:typingmind:get-started-with-self-host-installation-instruct. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public DPA, security appendix, processor list and self-host data-flow guides were retrieved. Targeted first-party search did not establish a professional-secrecy contract template, DE/CH-specific data-flow addendum or professional-body guidance. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:dpa-confidentiality, typingmind:typingmind:view-and-export-user-chat-logs, typingmind:typingmind:roles-and-permissions, typingmind:typingmind:set-up-api-keys, typingmind:typingmind:get-started-with-self-host-installation-instruct ## 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams subscriptions, personal one-time licences and self-host annual quotes are separate cost structures. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server, TypingMind personal browser app and PWA; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams SaaS Starter/Growth/Professional/quoted Business; separate annual Teams self-host quote; personal Standard/Extended/Premium one-time licences and separate bulk pack; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - pricing_unit — What is the pricing unit? [supported]: Teams SaaS uses recurring instance/seats billing; commercial Teams self-host is an annual quoted licence per instance. Personal one-time licences, including the separate shareable bulk pack, do not establish a Teams administration entitlement. Sources: typingmind:typingmind:pricing, typingmind:typingmind:cloud-host-vs-self-host, typingmind:typingmind:r2-personal-bulk-licence. - list_prices — What are list prices per plan, with date and currency? [supported]: As retrieved October 21, annual-selected landing cards display USD83/166/249 per month Starter/Growth/Professional (Professional crossed-out USD499). The documentation’s monthly table lists USD99/199/299 plus USD8/additional user/month. Business starts USD18,700/year by quote; conditional “as low as USD4/user/month” is not a universal rate. Sources: typingmind:typingmind:pricing, typingmind:typingmind:compare-typingmind-team-plans. - included_usage — What usage is included? [supported]: All SaaS tiers include five users and unlimited configured models/agents/plugins/prompts, excluding provider API usage. One million KB training characters belongs to the Growth/Professional RAG guide, still labeled Early Access; no Starter KB allowance is inferred. Sources: typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:how-knowledge-base-works-in-typingmind-team. - add_ons — Which features cost extra? [supported]: Additional seats, KB character capacity, model APIs and third-party plugin services are separate; self-host SLA/dedicated support is an add-on. Sources: typingmind:typingmind:pricing, typingmind:typingmind:selfhost, typingmind:typingmind:deep-research. - overage — What do usage beyond limits and premium models cost? [partial]: Model usage is billed by the customer’s chosen provider. No unified TypingMind premium-model tariff applies; extra KB capacity and Business/self-host scope require current checkout or quote. Sources: typingmind:typingmind:pricing, typingmind:typingmind:set-up-api-keys. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:pricing, typingmind:typingmind:cloud-host-vs-self-host, typingmind:typingmind:r2-personal-bulk-licence, typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:how-knowledge-base-works-in-typingmind-team, typingmind:typingmind:selfhost, typingmind:typingmind:deep-research, typingmind:typingmind:set-up-api-keys ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial A conditional Professional monthly licence-plus-BYOK floor is calculable; Business and self-host totals remain unknown. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Conditional documented Professional monthly list route; not a large-scale quote; add_ons=Model usage proxy; other add-ons unknown; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Known price floor plus explicitly unpriced parts; no complete year-one TCO or negotiated price claim. - cost_200 — Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21: 12 months ex VAT, 60% light100/30% regular400/10% power1500 messages per user/month, hence330; 3000 input+600 output tokens/message. Conditional undiscounted Teams Professional monthly route USD299 + USD8*(N−5) monthly, not the annual promotion or a Business quote. Direct-provider BYOK proxy gpt-6-luna, reasoning effort none, Standard short context USD0.10 input/USD0.50 output per million; no cache => USD2.376/user/year. ECB2026-10-20 EUR1=USD1.1215=CHF0.9237; USD/EUR divide1.1215, EUR/CHF multiply0.9237. For200 users: licence USD22,308 + model proxy USD475.20 = from USD22,783.20 / EUR20,314.94 / CHF18,764.91 + unknown components. Not a 200-seat quote. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:pricing, typingmind:typingmind:openai-price, typingmind:typingmind:openai-model, typingmind:typingmind:fx. - cost_1000 — Year-one cost at 1,000 users? [partial]: Same assumptions:1000 users licence USD99,108 + model USD2,376 = from USD101,484 / EUR90,489.52 / CHF83,585.17 + unknown components. Scale entitlement and negotiated Business alternative unverified. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:pricing, typingmind:typingmind:openai-price, typingmind:typingmind:openai-model, typingmind:typingmind:fx. - cost_5000 — Year-one cost at 5,000 users? [partial]: Same assumptions:5000 users licence USD483,108 + model USD11,880 = from USD494,988 / EUR441,362.46 / CHF407,686.51 + unknown components. Scale entitlement and Business alternative unverified. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:pricing, typingmind:typingmind:openai-price, typingmind:typingmind:openai-model, typingmind:typingmind:fx. - variable_share — Which part depends on usage? [supported]: The disclosed model proxy contributes USD2.376/user/year. Actual provider model mix, tools, images, audio, embeddings, cached/context tokens and regional API uplifts change usage. This proxy is a comparison assumption, not a vendor default or invoice. Sources: typingmind:typingmind:set-up-api-keys, typingmind:typingmind:openai-price, typingmind:typingmind:openai-model. - unknown_parts — Which costs could not be priced? [supported]: Unknown: large-scale SaaS entitlement/Business quote, current checkout promotion terms, extra KB capacity, connectors/search/plugin bills, embeddings, support/implementation and optional regional processing uplift. Self-host annual commercial licence/support quote plus MySQL, optional PostgreSQL/blob/network infrastructure and operator effort are unpriced; no zero-licence OSS assumption applies. Sources: typingmind:typingmind:pricing, typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:deep-research. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:pricing, typingmind:typingmind:openai-price, typingmind:typingmind:openai-model, typingmind:typingmind:fx, typingmind:typingmind:set-up-api-keys, typingmind:typingmind:selfhost, typingmind:typingmind:get-started-with-self-host-installation-instruct, typingmind:typingmind:deep-research ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Teams SaaS has a self-serve trial; self-host evaluation is a separate sales-gated route. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=TypingMind Teams SaaS; Starter, Growth and Professional prerequisites stated per answer; Business quote not obtained; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=multi-tenant-saas; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - free_tier — Is there a free tier for business use? [partial]: The cloud offer advertises a time-limited trial rather than a documented permanent free business tier. Personal free-use rights do not supply Teams governance. Sources: typingmind:typingmind:pricing, typingmind:typingmind:typingmind-vs-typingmind-team. - self_serve_trial — Is a self-serve business trial available? [supported]: The cloud-vs-self-host comparison offers a 14-day self-serve cloud trial with no upfront payment. Sources: typingmind:typingmind:cloud-host-vs-self-host. - trial_scope — Do trials include SSO, connectors and admin features? [partial]: The trial provides cloud evaluation; exact trial entitlements for SSO, SCIM, connectors and API quotas were not independently established. Sources: typingmind:typingmind:cloud-host-vs-self-host. - sales_gate — Does meaningful evaluation require sales contact? [supported]: Cloud starts self-serve; Business and annual self-host require a quote, and self-host has no free trial. Sources: typingmind:typingmind:pricing, typingmind:typingmind:selfhost, typingmind:typingmind:cloud-host-vs-self-host. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:pricing, typingmind:typingmind:typingmind-vs-typingmind-team, typingmind:typingmind:cloud-host-vs-self-host, typingmind:typingmind:selfhost ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cloud supports monthly/annual subscriptions; self-host is annual and commercial. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Starter/Growth/Professional monthly or annual SaaS; quoted Business and separate annual commercial Teams self-host; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - minimum_commitment — What seat or spend minimum applies? [supported]: Cloud plan cards and self-host licence include five users. Business advertises a USD18,700/year starting quote; no all-scenario minimum was established. Sources: typingmind:typingmind:pricing, typingmind:typingmind:selfhost. - contract_length — What contract lengths are offered? [supported]: Cloud-host vs Self-host explicitly describes monthly SaaS and annual quoted self-host subscriptions; the current SaaS landing also offers annual billing. Teams Terms specify renewal of the agreed term. Sources: typingmind:typingmind:cloud-host-vs-self-host, typingmind:typingmind:pricing, typingmind:typingmind:terms-of-service. - cancellation — How can the contract be cancelled or reduced? [partial]: Cloud billing settings manage subscriptions; Terms make fixed-term Teams/self-host fees generally nonrefundable. Exact mid-term seat-reduction proration and notice deadline were not established. Sources: typingmind:typingmind:manage-your-subscription, typingmind:typingmind:terms-of-service. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [unknown]: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR invoicing from a European entity, tax handling and bespoke contract negotiation were not established. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [supported]: Partial: public small-plan SaaS seat pricing with separate API bills, quote-only Business and self-host, and unpriced optional support/knowledge services. Sources: typingmind:typingmind:pricing, typingmind:typingmind:selfhost. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:pricing, typingmind:typingmind:selfhost, typingmind:typingmind:cloud-host-vs-self-host, typingmind:typingmind:terms-of-service, typingmind:typingmind:manage-your-subscription ### VEN-05: Source licence Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. - licence_type — Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial TypingMind is commercial proprietary software; self-host access is not an open-source licence. Availability: generally-available Delivery: native Scope: surfaces=TypingMind personal browser app and PWA, TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Commercial personal licence, separate bulk pack, Teams SaaS Starter/Growth/Professional and separate commercial Teams self-host licence; personal user/device allowance unverified; add_ons=Customer-paid model APIs; optional knowledge-base capacity and third-party plugin services; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - The personal user/device allowance is unknown. No five-user or one-user allowance is published as a reconciled finding; Teams and annual self-host seat rights remain separate. - licence_type — Which licence applies to each component? [supported]: The personal app and Teams operate under commercial Terms/EULA. Self-host provides compiled/minified code in a private repository with no analysis, modification, resale, sharing or redistribution rights; white-box review is by arrangement. Sources: typingmind:typingmind:end-user-license-agreement, typingmind:typingmind:terms-of-service, typingmind:typingmind:selfhost. - branding_restrictions — Do licence terms restrict branding or user counts? [partial]: Teams SaaS provides custom branding; the separate commercial Teams self-host licence includes one instance with five seats. Personal user/device allowance remains unknown because the generic five-device-or-user comparison conflicts with the one-user Terms. The separate bulk pack does not establish the default personal allowance. Sources: typingmind:typingmind:custom-branding, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:selfhost, typingmind:typingmind:terms-of-service, typingmind:typingmind:r2-personal-bulk-licence. - enterprise_features_closed — Are enterprise features in a separate closed edition? [supported]: Teams administration is part of the commercial service; SSO/SCIM, analytics, roles, logs and API are in Professional rather than an open-source core edition. Sources: typingmind:typingmind:compare-typingmind-team-plans. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:end-user-license-agreement, typingmind:typingmind:terms-of-service, typingmind:typingmind:selfhost, typingmind:typingmind:custom-branding, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:r2-personal-bulk-licence, typingmind:typingmind:compare-typingmind-team-plans ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Recorded Teams chats have a JSON API export; generic app exports do not prove full organizational portability. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams REST API, TypingMind Teams SaaS chat and Admin Panel, TypingMind personal browser app and PWA; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Professional recorded-chat API/export; separate personal app JSON backups (feature licence gate not mapped); add_ons=Professional chat recording enabled before export; authorized API key; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - chat_export — Can admins export all chats? [partial]: Professional includes chat logs/data export and API integration. Authorized admins export recorded conversation JSON via the API, last100 matching conversations/request plus date filters; complete tenant history and pagination were not tested. Sources: typingmind:typingmind:export-chat-logs, typingmind:typingmind:r2-plan-matrix. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: The personal-app backup guide exports user agents, prompts/plugins/model settings as JSON. That is not evidence of bulk centrally managed Teams asset export; its personal feature gate is not mapped here. Sources: typingmind:typingmind:export-import-data. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: Can knowledge bases and their sources be exported? A bulk reusable organization KB/source export and complete centrally managed agent/prompt export were not established. - export_format — Are formats documented and machine-readable? [supported]: Professional recorded-chat API responses are JSON; the separate personal backup/import also uses JSON. Formats do not establish complete organization portability. Sources: typingmind:typingmind:export-chat-logs, typingmind:typingmind:export-import-data, typingmind:typingmind:r2-plan-matrix. - post_termination_window — How long can data be retrieved after termination? [partial]: The DPA allows deletion/return at termination but does not publish a fixed retrieval grace period. Terms allow content deletion after termination. Sources: typingmind:typingmind:data-processing-agreement, typingmind:typingmind:terms-of-service. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:export-chat-logs, typingmind:typingmind:r2-plan-matrix, typingmind:typingmind:export-import-data, typingmind:typingmind:data-processing-agreement, typingmind:typingmind:terms-of-service ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Email support is documented; self-host SLA is optional and public incident data was inaccessible. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Starter/Growth/Professional public email support/material; separate quoted annual Teams self-host Enterprise Support add-on; add_ons=Commercial Teams self-host Enterprise Support (SLA/SLO/dedicated queue), separately quoted; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Self-host support package is distinct from SaaS support/onboarding; no public numerical uptime/credit or adoption-service tariff established. - support_channels — Which support channels are available on each plan? [supported]: Cloud plan comparison lists email support. Self-host dedicated support/SLA is a separate option; exact Business response targets were not established. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:selfhost. - support_languages — Is support available in German, French or Italian? [unknown]: Is support available in German, French or Italian? No German/French/Italian support commitment, DACH/Swiss support entity or public credit-bearing SLA terms were retrieved. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: Is there a DACH or Swiss entity, team or partner? No German/French/Italian support commitment, DACH/Swiss support entity or public credit-bearing SLA terms were retrieved. - uptime_sla — Is there an uptime SLA with credits? [partial]: Self-host marketing offers a paid SLA/SLO/dedicated-support add-on; a public uptime percentage, credit schedule or standard SaaS SLA was not retrieved. Sources: typingmind:typingmind:selfhost. - status_page — Is there a public status page with history? [partial]: A public status site loads but returned an error fetching status data in this pass, so history and measured availability are unknown. Sources: typingmind:typingmind:status. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:compare-typingmind-team-plans, typingmind:typingmind:selfhost, typingmind:typingmind:status, typingmind:typingmind:pricing, typingmind:typingmind:cloud-host-vs-self-host ### 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 #### TypingMind / TypingMind Teams Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public setup guides and role examples exist; managed adoption services are not fully specified. Availability: generally-available Delivery: native Scope: surfaces=TypingMind Teams SaaS chat and Admin Panel, Commercial self-hosted TypingMind Teams server; version=Public documentation and changelog retrieved 2026-10-21; no deployed tenant observed; plan=Teams Starter/Growth/Professional public email support/material; separate quoted annual Teams self-host Enterprise Support add-on; add_ons=Commercial Teams self-host Enterprise Support (SLA/SLO/dedicated queue), separately quoted; deployment_mode=not specified; region=US or opt-in EU SaaS storage; inference and tools depend on customer-selected providers; os=not specified. Limitations: - Self-host support package is distinct from SaaS support/onboarding; no public numerical uptime/credit or adoption-service tariff established. - onboarding_service — Is guided onboarding included? [unknown]: Is guided onboarding included? No included guided-onboarding scope, multilingual training commitment or champion/adoption programme was established. - user_training — Is end-user training offered, in which languages? [partial]: Public documentation teaches setup, use, agents and workflows. A contracted live user-training service and languages were not established. Sources: typingmind:typingmind:typingmind-vs-typingmind-team, typingmind:typingmind:overview. - use_case_library — Are role-based use cases and templates provided? [supported]: The documentation provides marketing ad creation, meeting-summary and business automation examples and role/permission examples. Sources: typingmind:typingmind:ad-creative-generator, typingmind:typingmind:meeting-summarizer, typingmind:typingmind:overview, typingmind:typingmind:roles-and-permissions. - adoption_programme — Is there a champion or adoption programme? [unknown]: Is there a champion or adoption programme? No included guided-onboarding scope, multilingual training commitment or champion/adoption programme was established. - service_cost — Which services cost extra? [partial]: Self-host dedicated support/SLA is an optional extra; onboarding/training/adoption-program prices were not established. Sources: typingmind:typingmind:selfhost. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: typingmind:typingmind:typingmind-vs-typingmind-team, typingmind:typingmind:overview, typingmind:typingmind:ad-creative-generator, typingmind:typingmind:meeting-summarizer, typingmind:typingmind:roles-and-permissions, typingmind:typingmind:selfhost, typingmind:typingmind:pricing, typingmind:typingmind:cloud-host-vs-self-host ## 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 ### typingmind:typingmind:set-up-api-keys Set up API Keys. Teams admins preset customer provider keys; end users cannot enter their own key in the chat interface. - URL: https://docs.typingmind.com/typingmind-team/getting-started/set-up-api-keys.md - Locator: Set up API Keys - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:manage-ai-models Manage AI Models. The app has a per-chat model selector and configurable model endpoints; provider examples are not a complete current catalogue. - URL: https://docs.typingmind.com/manage-and-connect-ai-models/manage-ai-models.md - Locator: Manage AI Models - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:release TypingMind changelog. Dated releases include Teams memory administration, new models, browser-local code and office outputs, and GPT Image editing. - URL: https://feedback.typingmind.com/changelog/ - Locator: 2026-10-14 Memory for Teams and new models; 2026-10-13 Toolbox; 2026-10-02 image editing - Evidence kind: documented - Source date: 2026-10-14 - Retrieved: 2026-10-21 ### typingmind:typingmind:restrict-model-access Restrict Model access. Teams admins restrict available models by user group. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/restrict-model-access.md - Locator: Restrict Model access - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:chat-with-documents Chat with documents. Uploads accept PDF, Markdown, CSV, XLSX, TXT, DOCX, JSON and HTML, with document text added as chat context. - URL: https://docs.typingmind.com/upload-and-chat-with-files/chat-with-documents.md - Locator: Chat with documents - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:voice Voice input. Browser speech recognition or customer OpenAI, Groq and Azure transcription keys enable dictation; uploaded Whisper recordings have a 25MB limit. - URL: https://docs.typingmind.com/voice-input - Locator: Transcription models and Teams configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:azure-openai Azure OpenAI. A customer Azure OpenAI endpoint and deployment can be configured. - URL: https://docs.typingmind.com/manage-and-connect-ai-models/azure-openai.md - Locator: Azure OpenAI - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:firstchat Your first chat. LibreChat ships without a model key; the public demo is for evaluation rather than private or durable data. - URL: https://www.librechat.ai/docs/quick_start/first_chat - Locator: Software you host yourself; endpoint credentials; public demo - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:code Code Interpreter API. A separate code execution service supports multiple languages and downloadable generated files; stateful/attached modes are experimental. - URL: https://www.librechat.ai/docs/features/code_interpreter - Locator: Setup; self-hosted service; workspace permissions; generated files - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:license LibreChat v0.8.8 MIT licence. The pinned repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/LICENSE - Locator: LICENSE, permission grant and notice requirement - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:pricing TypingMind Teams pricing. Annual selected prices display USD83/166/249 per month for Starter/Growth/Professional, five users, USD8 extra seats; Business starts USD18,700/year. - URL: https://custom.typingmind.com/pricing - Locator: Annual selector, plan cards, Add-ons and Business card - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:get-started-with-self-host-installation-instruct Self-host installation instructions. A NodeJS service needs MySQL 8, optional PostgreSQL 16 pgvector KB, OpenAI embeddings and S3-compatible blobs; private endpoints are blocked by default. - URL: https://docs.typingmind.com/typingmind-team/self-host-guides/get-started-with-self-host-installation-instruct.md - Locator: Self-host installation instructions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:toolbox Toolbox. A free built-in plugin executes Python and JavaScript locally in the browser with network disabled by default and creates Office/PDF files and charts. - URL: https://docs.typingmind.com/plugins/toolbox - Locator: Local execution, network control and file capabilities - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:r2-teams-custom-models Teams API Keys Setup. Teams-specific instructions name Azure OpenAI, Hugging Face and Ollama custom-model setup in the Admin Panel; this is distinct from personal local-server guides. - URL: https://docs.typingmind.com/typingmind-team/getting-started/set-up-api-keys.md - Locator: Use with other models; Add Custom Model in Admin Panel - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:r2-plan-matrix Compare Teams Plans. All SaaS tiers list custom models and shared resources; Growth adds RAG/projects; Professional adds roles, restrictions, logs and external API integration. - URL: https://docs.typingmind.com/typingmind-team/getting-started/compare-typingmind-team-plans.md - Locator: Full Feature Comparison - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:r3-custom-admin-bedrock AWS Bedrock Anthropic. The Custom Admin route configures Claude via Bedrock with customer AWS access/secret keys, region and approved model access; current model and commercial tier coverage are not enumerated. - URL: https://docs.typingmind.com/manage-and-connect-ai-models/aws-bedrock-anthropic - Locator: Custom Admin restriction and steps 2-4, including custom.typingmind.com/manage - 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 ### typingmind:typingmind:ollama Ollama. A customer Ollama model endpoint can be added; network accessibility must be configured. - URL: https://docs.typingmind.com/manage-and-connect-ai-models/ollama.md - Locator: Ollama - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:lmstudio LM Studio. Customer local LM Studio can supply an OpenAI-compatible model endpoint. - URL: https://docs.typingmind.com/manage-and-connect-ai-models/lmstudio.md - Locator: LM Studio - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:cloud-host-vs-self-host Cloud host vs self host. SaaS has a self-serve 14-day trial; self-host has no free trial and carries a quoted annual licence and update/support conditions. - URL: https://docs.typingmind.com/typingmind-team/getting-started/cloud-host-vs-self-host.md - Locator: Cloud host vs self host - 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 ### typingmind:typingmind:usage-limits Usage limits. Reusable limit groups cover messages, characters and tokens by period, applicable globally or to users, groups, models, agents and plugins. - URL: https://docs.typingmind.com/typingmind-team/user-management/usage-limits.md - Locator: Usage limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:connect-knowledge-base-to-your-ai-agents Connect Knowledge Base to your AI Agents. Tagged knowledge is assigned to agents through Knowledge Base Access. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/connect-knowledge-base-to-your-ai-agents.md - Locator: Connect Knowledge Base to your AI Agents - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:roles-and-permissions Roles and Permissions. Owners delegate granular Admin Panel permissions through custom roles; group-role assignment is described as coming soon. - URL: https://docs.typingmind.com/typingmind-team/user-management/roles-and-permissions.md - Locator: Roles and Permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:rag RAG API. A separate RAG API indexes uploaded content in PostgreSQL/PGVector for retrieval. - URL: https://www.librechat.ai/docs/features/rag_api - Locator: Architecture; document indexing; embeddings; semantic search - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:text Upload files as text. Text upload injects extracted file content rather than relying only on vector retrieval. - URL: https://www.librechat.ai/docs/features/upload_as_text - Locator: Full text extraction and context - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:filecfg File configuration. File limits and formats are configurable by endpoint and file processing route. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/file_config - Locator: File limits; MIME patterns; provider routes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:r4-spreadsheet-parser LibreChat spreadsheet text parser. The built-in parser accepts XLSX/XLS/ODS and serializes each sheet as its name followed by CSV values. It does not establish preserved workbook layout, recalculated formulas or fixture accuracy. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/files/documents/crud.ts - Locator: getParserForMimeType; excelSheetToText, lines 109-129 - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/files/documents/crud.ts ### librechat:librechat:r4-text-current LibreChat current Upload as Text guide. The development guide lists XLSX/XLS/ODS parsing up to 15 MB and token-bounded text injection, not a formatted spreadsheet editor. - URL: https://www.librechat.ai/docs/features/upload_as_text - Locator: Built-in parser; supported documents; truncation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### typingmind:typingmind:how-knowledge-base-works-in-typingmind-team How Knowledge Base works in TypingMind Team. The early-access KB uses RAG, about 3,000-word chunks and up to five retrieved chunks, 50MB uploads and daily source refresh. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/how-knowledge-base-works-in-typingmind-team.md - Locator: Early Access; indexing; limits and refresh - Evidence kind: documented - Source date: 2025-11-10 - Retrieved: 2026-10-21 ### typingmind:typingmind:training-files-vs-knowledge-base Training Files vs Knowledge Base. Agent training-file text is injected into system context; the separate KB retrieves chunks and advertises multiple source integrations. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/training-files-vs-knowledge-base.md - Locator: Training Files vs Knowledge Base - 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 ### typingmind:typingmind:get-started-with-knowledge-base Get started with Knowledge Base. Admins add documents or connected sources, tag data, bind tags to agents and optionally show clickable references. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/get-started-with-knowledge-base.md - Locator: Get started with Knowledge Base - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:restrict-ai-agents-access Restrict AI Agents access. Agent access and usage can be limited for groups. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/restrict-ai-agents-access.md - Locator: Restrict AI Agents access - 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 ### typingmind:typingmind:connect-with-your-notion-pages Connect with Notion pages. Admins select Notion pages/databases for an instance, with initial sync taking a few minutes. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/connect-with-your-notion-pages.md - Locator: Connect with Notion pages - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:setup-external-connectors-for-knowledge-base Self-host external knowledge connectors. Optional self-host KB external connectors need separate OAuth configuration and Firecrawl for web scraping. - URL: https://docs.typingmind.com/typingmind-team/self-host-guides/setup-external-connectors-for-knowledge-base.md - Locator: Self-host external knowledge connectors - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:overview LLM Automated Workflows overview. JavaScript, HTTP and MCP plugins can perform multi-step business actions; example flows are not evidence of a scheduler. - URL: https://docs.typingmind.com/llm-automated-workflows/overview.md - Locator: LLM Automated Workflows overview - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:mcp MCP in TypingMind. The client connects remote HTTP or local-command MCP servers, supports OAuth and individual tool controls, and separates Teams sessions per user/chat. - URL: https://docs.typingmind.com/model-context-protocol-(mcp)-in-typingmind - Locator: Remote and local connectors; Teams sessions; tool control - 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 ### typingmind:typingmind:eu-data-center EU data center. EU instances use Vercel and AWS EU storage but model API calls may leave the EU. - URL: https://docs.typingmind.com/typingmind-team/account-management/eu-data-center.md - Locator: EU data center - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:system-prompts-on-admin-panel System Prompts on Admin Panel. Global system instructions, few-shot examples and post-message reminders apply across chats and agents. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/system-prompts-on-admin-panel.md - Locator: System Prompts on Admin Panel - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:memory User memory. Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats. - URL: https://www.librechat.ai/docs/features/memory - Locator: Key/value store; controls; disabled by default - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:memory Memory. Users can enable memory globally or for an agent/project and inspect saved memories. - URL: https://docs.typingmind.com/memory.md - Locator: Memory - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:build-a-shared-ai-agent-collection Build a Shared AI Agent collection. Admins create an agent collection exposed in the team chat interface and control group access. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/build-a-shared-ai-agent-collection.md - Locator: Build a Shared AI Agent collection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:build-a-shared-prompt-library Build a Shared Prompt Library. Admins can publish reusable prompts to the team interface. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/build-a-shared-prompt-library.md - Locator: Build a Shared Prompt Library - 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 ### typingmind:typingmind:restrict-plugin-access Restrict Plugin access. Plugins can be made available or unavailable to specified user groups. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/restrict-plugin-access.md - Locator: Restrict Plugin access - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:deep-research Deep Research plugin. A multi-step search/read/report plugin requires customer SerpAPI and Firecrawl keys and has a two-minute execution limit. - URL: https://docs.typingmind.com/plugins/deep-research - Locator: Requirements and operation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:image GPT Image 2.5 plugin. The plugin generates and edits images using the customer OpenAI API route. - URL: https://docs.typingmind.com/plugins/gpt-image-2-5 - Locator: Image generation, editing and API key - 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 ### 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 ### typingmind:typingmind:api-integration-overview API integration overview. REST chat/agent API uses API-key-associated api-users subject to user restrictions and usage limits. - URL: https://docs.typingmind.com/typingmind-team/integrations/api-integration-overview.md - Locator: API integration overview - 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 ### typingmind:typingmind:typingmind-vs-typingmind-team TypingMind vs TypingMind Team. The personal app and Teams with an Admin Panel, managed users and centrally preset keys are separate offerings. - URL: https://docs.typingmind.com/quickstart/typingmind-vs-typingmind-team.md - Locator: TypingMind vs TypingMind Team - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:install Install TypingMind app. Installation uses browser PWA technology; browser storage remains separate and this does not establish native app-store clients. - URL: https://docs.typingmind.com/install-typingmind-app - Locator: PWA installation on Windows, Mac, iOS and Android - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:r2-personal-bulk-licence TypingMind personal licence checkout. Personal licences normally cover five devices for one user; a separate shareable Bulk License is offered, without establishing a Teams Admin Panel entitlement. - URL: https://checkout.typingmind.com/buy - Locator: How many devices/users? and Team/Bulk License FAQ; self-host FAQ - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:ad-creative-generator Ad creative generator workflow. Public examples include marketing automation built with AI and plugins. - URL: https://docs.typingmind.com/llm-automated-workflows/ad-creative-generator.md - Locator: Ad creative generator workflow - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:terms-of-service Terms of Service. Typing Technology Co Ltd contracts under Singapore law and business SIAC arbitration; Teams renews and self-host code has restricted licence rights. - URL: https://docs.typingmind.com/security-and-compliance/terms-of-service.md - Locator: Sections 1, 4-6, 13 and 16 - Evidence kind: documented - Source date: 2026-09-17 - 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 ### typingmind:typingmind:tts Text to speech. Answers can be read aloud using browser speech, ElevenLabs or OpenAI TTS. - URL: https://docs.typingmind.com/use-text-to-speech - Locator: Browser, ElevenLabs and OpenAI options - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:meeting-summarizer Meeting summarizer workflow. The guide offers an audio-transcription and summarisation workflow, not a demonstrated meeting bot. - URL: https://docs.typingmind.com/llm-automated-workflows/meeting-summarizer.md - Locator: Meeting summarizer workflow - 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 ### typingmind:typingmind:compare-typingmind-team-plans Compare TypingMind Team plans. The comparison lists monthly USD99/199/299, five users plus USD8 additional users, Growth knowledge and Professional identity/governance. - URL: https://docs.typingmind.com/typingmind-team/getting-started/compare-typingmind-team-plans.md - Locator: Compare TypingMind Team plans - 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 ### 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 ### typingmind:typingmind:translations Translation collaboration. A translation project exists, but the retrieved page does not establish completeness of German, French, Italian or Admin Panel translations. - URL: https://docs.typingmind.com/app-translation/translation-collaboration - Locator: Multilingual app translation project - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:auth Authentication system. Local/LDAP accounts can be required to use TOTP; federated MFA belongs to the identity provider and account creation/deletion scripts are documented. - URL: https://www.librechat.ai/docs/configuration/authentication - Locator: Required two-factor authentication; Registration; User scripts - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:openid OAuth2 and OIDC. LibreChat documents OAuth2/OIDC providers including Microsoft Entra, Google, Keycloak and Auth0. - URL: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC - Locator: Supported providers; setup - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:saml SAML authentication. SAML is a documented authentication option for the self-hosted application. - URL: https://www.librechat.ai/docs/configuration/authentication/SAML - Locator: Overview and requirements - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:entra Azure Entra authentication. Entra OIDC supports group-based admission and Graph integration using configured scopes and token reuse. - URL: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC/azure - Locator: Group claims; token reuse; Microsoft Graph integration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:sso Single Sign-On (SSO). SAML identity-provider metadata, entity ID and reply URL are configured in Teams. - URL: https://docs.typingmind.com/typingmind-team/user-management/single-sign-on-(sso) - Locator: SAML configuration and multiple connections - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:o-auth-2-0 OAuth 2.0. OAuth/OIDC supports built-in Microsoft and Google logins and JIT seats; revoking IdP authorization alone does not remove the user. - URL: https://docs.typingmind.com/typingmind-team/user-management/o-auth-2-0.md - Locator: OAuth 2.0 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:data-processing-agreement Data Processing Agreement. The public GDPR processor form includes confidentiality, subprocessor flow-down, SCC transfers and customer-choice deletion or return. - URL: https://docs.typingmind.com/security-and-compliance/data-processing-agreement.md - Locator: Clauses 7.4, 7.8-7.10 and Appendices I-IV - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:scim Directory Sync (SCIM v2). SCIM sync creates and suspends users, updates profiles and assigns corresponding groups from the IdP. - URL: https://docs.typingmind.com/typingmind-team/user-management/directory-sync-(scim-v2) - Locator: Create, update, suspend users and groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:invite-team-members Invite team members. Teams admins invite members to the instance and manage seats. - URL: https://docs.typingmind.com/typingmind-team/user-management/invite-team-members.md - Locator: Invite team members - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:create-and-manage-user-groups Create and manage user groups. Groups control access and are usable for limits and analytics. - URL: https://docs.typingmind.com/typingmind-team/user-management/create-and-manage-user-groups.md - Locator: Create and manage user groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:tokens Token usage. Usage and estimated costs use recorded tokens and configured provider rates; transactions are distinct from balance enforcement. - URL: https://www.librechat.ai/docs/configuration/token_usage - Locator: Context cost; transactions; per-endpoint token rates - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:chatbot-analytics Chatbot analytics. Reporting covers active users, messages, conversations, estimated tokens and characters, with model/agent/group/user breakdowns and chart downloads. - URL: https://docs.typingmind.com/typingmind-team/analytics/chatbot-analytics.md - Locator: Chatbot analytics - 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 ### typingmind:typingmind:view-and-export-user-chat-logs View and export user chat logs. Opt-in Record all chats exposes user prompts and responses to authorized admins and configurable retention permanently deletes old records. - URL: https://docs.typingmind.com/typingmind-team/analytics/view-and-export-user-chat-logs.md - Locator: View and export user chat logs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:export-chat-logs Export chat logs. Chat logging is off by default; the API exports JSON conversation content and dates, limited to the last 100 matching conversations per request. - URL: https://docs.typingmind.com/typingmind-team/integrations/export-chat-logs.md - Locator: Export chat logs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:r4-content-filter LibreChat development content-filter configuration. Opt-in base-YAML policies inspect selected message/file content; block and audit differ from limited Agent text redaction. This is development documentation, not a hosted DLP assurance. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/message_filter - Locator: Source-Aware Filters; Pattern Configuration; Redaction; File Fields - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:r4-pii-runtime LibreChat content-inspection runtime. Source-aware configured inspection executes in the LibreChat API. Missing policy disables that scope; configured actions and fields bound inspection. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/runtime.ts - Locator: createConfiguredContentInspector; source rule configuration - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/runtime.ts ### librechat:librechat:r4-patterns LibreChat pattern detector. Default starter patterns detect credential-shaped tokens/headers. Operator custom patterns use bounded regular expressions; a generic comprehensive PII classifier is not established. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/detectors/pattern.ts - Locator: STARTER_PATTERNS; configured RE2JS rules - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/detectors/pattern.ts ### librechat:librechat:r4-private-submission LibreChat private text submission. The private text ingress permits configured redaction only on eligible fresh interactive Agent text. Original content is encrypted; edit/resume/file paths do not gain blanket redaction. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/private/submission.ts - Locator: createPrivateTextIngress; fresh Agent text and clientRequestId checks - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/private/submission.ts ### librechat:librechat:r4-filter-middleware LibreChat API content-filter middleware. The server middleware applies configured inspection and rejects blocked/uninspectable requests with HTTP 400. No deployment or detection fixture was run. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/middleware/messageFilterPii.ts - Locator: createMessageFilterPii; contentFilterBlockResponse; uninspectable response - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/middleware/messageFilterPii.ts ### librechat:librechat:r4-config-1318 LibreChat config v1.3.18 changelog. Dated development config changes add limited Agent text redaction and ephemeral retention mode. These are not a promise of universal redaction or a vendor zero-retention contract. - URL: https://www.librechat.ai/changelog/config_v1.3.18 - Locator: October 22, 2026; opt-in PII redaction; retention mode - Evidence kind: documented - Source date: 2026-10-22 - Retrieved: 2026-10-26 ### librechat:librechat:interface Interface configuration. Administrators configure UI feature permissions and usage terms in the self-hosted deployment. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/interface - Locator: Feature permissions; custom welcome and terms - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:remote Remote hosting. The application can be deployed on customer-selected remote servers with operator-managed security. - URL: https://www.librechat.ai/docs/remote - Locator: Hosting options; security considerations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:selfhost TypingMind Teams Self Host. Commercial self-host requires an annual quote, includes five users, uses compiled/minified code, checks licence/updates externally and can use customer model endpoints. - URL: https://custom.typingmind.com/self-host - Locator: Technical requirements, licensing, network, updates and pricing FAQ - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:privacy-policy Privacy policy. The policy distinguishes personal local storage from Teams multitenant server storage, and lists inactive unpaid account deletion. - URL: https://docs.typingmind.com/security-and-compliance/privacy-policy.md - Locator: Storage scope, API keys and section on account deletion - Evidence kind: documented - Source date: 2026-09-19 - 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 ### typingmind:typingmind:data-usage-and-model-training-policy Data Usage and Model Training Policy. The vendor says it does not train on conversations; customers contract directly with model providers and their retention/training terms vary. - URL: https://docs.typingmind.com/security-and-compliance/data-usage-and-model-training-policy.md - Locator: TypingMind role and provider API comparison - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:settings Personal settings. Users configure interface language, audio and personal data controls. - URL: https://www.librechat.ai/docs/features/settings - Locator: Language; speech; data controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:owner ClickHouse acquisition of LibreChat. ClickHouse announced the acquisition of LibreChat and that Danny Avila and the team joined ClickHouse. - URL: https://clickhouse.com/blog/clickhouse-acquires-librechat - Locator: Announcement, November 4, 2025 - Evidence kind: documented - Source date: 2025-11-04 - Retrieved: 2026-10-21 ### typingmind:typingmind:r4-soc2-selfhost-claim TypingMind Teams self-host. The self-host marketing page claims SOC 2 Type II; no auditor, reporting period, covered legal entity or report was retrieved. This is a vendor claim rather than verified attestation. - URL: https://custom.typingmind.com/self-host - Locator: Maximum security, SOC 2 Type II badge; updates and licence checks - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-26 ### typingmind:typingmind:r2-teams-server-route TypingMind Teams pricing FAQ. The Teams-specific FAQ says users do not see the key and OpenAI requests are sent from the Teams server. - URL: https://custom.typingmind.com/pricing - Locator: Do my users see my OpenAI API key? - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:siteprivacy LibreChat website privacy policy. Website, demo and self-hosted software are distinct privacy scopes; website terms do not establish a customer deployment DPA. - URL: https://www.librechat.ai/privacy - Locator: Scope and exclusions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:secrecy-message-pin LibreChat v0.8.8 message storage schema. The pinned Mongoose schema declares message text as a String and content as mixed fields; this source does not establish operator exclusion from live content. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/packages/data-schemas/src/schema/message.ts - Locator: packages/data-schemas/src/schema/message.ts, text at lines 55-58 and content at lines 139-143 - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: packages/data-schemas/src/schema/message.ts ### librechat:librechat:secrecy-demo-policy LibreChat Demo privacy policy. The Demo policy describes model-provider transmission and contractual processor instruction/security duties for the Demo; it does not cover a customer self-hosted deployment. - URL: https://www.librechat.ai/demo/privacy - Locator: Scope; section 4 Third-Party AI Model Providers; section 6 Data Sharing and Sub-Processors - Evidence kind: documented - Source date: 2026-03-12 - Retrieved: 2026-10-21 ### typingmind:typingmind:dpa-confidentiality TypingMind DPA confidentiality. Staff have need-to-know confidentiality duties and subprocessor contracts carry substantially the same data-protection obligations; a specific professional-secrecy agreement is not established. - URL: https://docs.typingmind.com/security-and-compliance/data-processing-agreement.md - Locator: 7.4(c),7.8(d)-(e); AppendixII andIII - 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 ### typingmind:typingmind:openai-price OpenAI API pricing. gpt-6-luna Standard input is USD0.10 and output USD0.50 per million tokens, excluding cache and optional regional uplifts. - 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 ### typingmind:typingmind:openai-model GPT-6 Luna model documentation. Reasoning effort none is the lowest option; the shared cost proxy does not use reasoning tokens. - URL: https://developers.openai.com/api/docs/models/gpt-6-luna - Locator: Reasoning effort and API support - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:fx ECB reference exchange rates. EUR1 equals USD1.1215 and CHF0.9237. - URL: https://www.ecb.europa.eu/stats/eurofxref/eurofxref-hist.xml - Locator: Cube time=2026-10-20 - Evidence kind: documented - Source date: 2026-10-20 - Retrieved: 2026-10-21 ### typingmind:typingmind:manage-your-subscription Manage your subscription. Cloud customers manage the recurring subscription through billing settings. - URL: https://docs.typingmind.com/typingmind-team/account-management/manage-your-subscription.md - Locator: Manage your subscription - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:end-user-license-agreement End User License Agreement. The software is commercially licensed with restrictions on redistribution and modification. - URL: https://docs.typingmind.com/security-and-compliance/end-user-license-agreement.md - Locator: End User License Agreement - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:custom-branding Custom branding. Teams supports instance logo, theme and branded presentation within its commercial licence. - URL: https://docs.typingmind.com/typingmind-team/branding-and-customizations/custom-branding.md - Locator: Custom branding - 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 ### typingmind:typingmind:export-import-data Export and import data. User app settings export/import chats, prompts, plugins, folders, agents and model settings as JSON. - URL: https://docs.typingmind.com/cloud-sync-and-backup/export-import-data.md - Locator: Export and import data - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### typingmind:typingmind:status TypingMind status. The status site loaded a status shell but reported an error fetching data; incident history and measured uptime were not retrieved. - URL: https://status.typingmind.ai - Locator: Public status shell - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21