Skip to content

Agent-readable comparison

Gemini Enterprise vs LibreChat

Published by onAI. onAI also sells one of the products compared here. Findings about other products link to public sources so you can check them; statements about onAI are marked as stated by onAI.

This comparison has 44 criteria with sourced findings for both products, including 44 that a second agent cross-checked for both. 51 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation: they are scoped, fresh and cite public resolved sources. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. "Stated by onAI" marks the publisher's own statements about its product (evidence type vendor-statement), which cite no third-party source. Humans approve the rubric, templates and generator; they do not review every finding. No winner is declared. A missing sourced finding is not evidence that a capability is absent.

Same facts as Markdown and JSON. 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.

Gemini Enterprise

Agent cross-checked Support: partial

In the Standard/Plus Enterprise app, Google models and opt-in, separately billed Claude models are documented; this finding excludes the universal-agent rollout.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus app model picker; excludes Starter, Workspace Gemini and the universal-agent early-access experience; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us and eu; partner models excluded from in-country regions; os=not specified.

Limitations

  • Gemini 3.1 Pro is limited availability; paid partner models are disabled by default.
  • October 15 Enterprise release notes explicitly announce Claude GA for this app. The marketing universal-agent experience describes third-party choice as early access; its entitlement is outside this claim. The listed Google models include limited-availability Gemini 3.1 Pro, so no single GA state is asserted for the whole model list.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-features, gemini-enterprise:gemini-enterprise:g-locations, gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-releases.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr.

MOD-02 Model freshness

Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models.

Gemini Enterprise

Agent cross-checked Support: partial

A dated product changelog establishes model arrivals and regional removals; a comparable three-release lag dataset was not obtained.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: release_lag_days, version_pinning.
  • release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: Unknown. Enterprise arrival dates exist, but provider GA dates for three recent major releases per offered provider were not assembled; no median is calculated.
  • changelog Is there a dated public model changelog? [supported]: The public release log dates model changes, including Claude app availability on 2026-10-15. Sources: gemini-enterprise:gemini-enterprise:g-releases.
  • deprecation_notice How much notice is given before a model is removed? [partial]: Notes include an announced 14-day Flash removal that was postponed, and a 2026-10-20 regional Pro removal; no uniform guaranteed notice was established. Sources: gemini-enterprise:gemini-enterprise:g-releases.
  • version_pinning Can an admin keep an older model version? [unknown]: Unknown. The model-toggle and release guides do not promise retention of a particular older model revision.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-releases.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom.

MOD-03 Bring-your-own keys and provider contracts

Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract.

Gemini Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

LibreChat

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.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code.

MOD-04 Local and self-hosted models

Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work.

Gemini Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code.

MOD-05 Model control and usage limits

Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use.

Gemini Enterprise

Agent cross-checked Support: partial

App model toggles, shared pools and optional single-user quota limits are documented; group model/data allowlists remain unverified.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: model_allowlist_by_group, data_bound_models, default_model.
  • model_allowlist_by_group Can admins limit models per group? [unknown]: Unknown. Model toggles are app-level in the retrieved guide; a two-group restriction test and direct group-level model policy were not verified.
  • data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: Unknown. No source-to-model routing restriction was established in the model and connector guides.
  • default_model Can admins set the default model? [unknown]: Unknown. Auto is documented as the user-facing default, but an administrator-set default model was not established.
  • user_limits What per-user message or token limits apply, and are they published? [supported]: Standard/Plus retain shared edition/project/location pools of 160/200 assistant queries per seat/day. Since October 22, admins can also configure a single-user quota multiplier for an edition/location. AI developer tools are excluded from that multiplier. Sources: gemini-enterprise:gemini-enterprise:g-quotas, gemini-enterprise:gemini-enterprise:r4-single-user-quotas, gemini-enterprise:gemini-enterprise:r4-single-user-enforcement.
  • limit_behaviour What happens when a limit is reached? [supported]: A single-user limit can stop the exhausted feature for that user while other features/users continue within the pool; overage configuration changes exhaustion behavior. A depleted shared pool needs paid overages, and project spend caps retain delayed enforcement. Sources: gemini-enterprise:gemini-enterprise:r4-single-user-enforcement, gemini-enterprise:gemini-enterprise:g-budget.

Checked ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: gemini-enterprise:gemini-enterprise:g-quotas, gemini-enterprise:gemini-enterprise:g-budget, gemini-enterprise:gemini-enterprise:r4-single-user-quotas, gemini-enterprise:gemini-enterprise:r4-single-user-enforcement.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin.

Company knowledge

KNOW-01 Files in chat

Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures.

Gemini Enterprise

Agent cross-checked Support: partial

The assistant accepts common documents and multimodal files; spreadsheet processing can run code, subject to byte and context limits.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: ocr.
  • formats Which formats are accepted? [supported]: PDF, DOCX, XLSX, CSV, PPTX, TXT, Markdown, JSON, common code files, PNG/JPEG, MP4 and MP3 are listed. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • limits What size and count limits apply per file and chat? [partial]: Examples: PDF/PPTX 100 MB, XLSX 50 MB decompressed, CSV 7 MB, DOCX 3 MB, images 30 MB, audio/video 200 MB; combined chat context is 800,000 tokens. File-count limit was not established. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • ocr Are scanned PDFs read? [unknown]: Unknown. The upload guide lists PDF support, but a scanned-PDF fixture was not run and chat OCR completeness was not established.
  • spreadsheets Are Excel tables read with structure intact? [partial]: The guide describes conversion of each worksheet into a table and code-based analysis for large sheets; formula/layout fidelity was not tested. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [partial]: Direct attachments consume combined context; indexed data stores use retrieval instead. The exact visible coverage of each uploaded long file was not tested. Sources: gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-connect-overview.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-connect-overview.

LibreChat

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 ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current.

KNOW-02 Knowledge bases and shared collections

Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope.

Gemini Enterprise

Agent cross-checked Support: supported

Projects retain shared knowledge and custom agents accept attached knowledge, with separate limits.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-projects, gemini-enterprise:gemini-enterprise:g-features, gemini-enterprise:gemini-enterprise:g-editions, gemini-enterprise:gemini-enterprise:g-agents.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr.

KNOW-03 Enterprise connectors

Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02).

Gemini Enterprise

Agent cross-checked Support: supported

Google lists enterprise connectors by individual launch stage; a source connector is distinct from an Office add-in.

Availability: unknown · Delivery: official-integration
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-connectors, gemini-enterprise:gemini-enterprise:g-selfhosted-data, gemini-enterprise:gemini-enterprise:g-connect-overview.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp.

KNOW-04 Permission-aware retrieval

Judgment rule: Using two test users, verify that a restricted document in the fixture tenant is never cited or summarised for the user without access, including after a permission change. Record whether permissions are enforced at query time by the source system, mirrored into an index, or not enforced. Record the propagation delay of a revocation.

Gemini Enterprise

Agent cross-checked Support: partial

The docs describe permission-aware retrieval and source-label inspection; enforcement after revocation has not been observed.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: revocation_delay, admin_scope_controls.
  • source_permissions_respected Are source permissions enforced per user? [partial]: Docs promise per-user access; projects preserve linked-source ACLs. No two-user restricted-document test was run. Sources: gemini-enterprise:gemini-enterprise:g-projects, gemini-enterprise:gemini-enterprise:g-connect-overview.
  • enforcement_point Does the source system, a mirrored index or nothing enforce them? [supported]: Ingested stores synchronize identity/ACL data; federated stores query sources. Exact enforcement differs by connector. Sources: gemini-enterprise:gemini-enterprise:g-connect-overview.
  • revocation_delay How quickly does a removed permission take effect? [unknown]: Unknown. Identity sync schedules are configurable, but no end-to-end permission-revocation propagation test was run.
  • admin_scope_controls Can admins exclude sites, folders or labels? [unknown]: Unknown. Connector configuration varies; a complete verified site/folder exclusion matrix was not obtained.
  • sensitivity_labels Are Microsoft Purview or similar labels respected? [supported]: Sensitive Data Protection can inspect Microsoft sensitivity and Workspace metadata labels; encrypted Microsoft files cannot be decrypted for inspection. Sources: gemini-enterprise:gemini-enterprise:g-dlp.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-projects, gemini-enterprise:gemini-enterprise:g-connect-overview, gemini-enterprise:gemini-enterprise:g-dlp.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:sharepoint, librechat:librechat:agents.

KNOW-05 Freshness and sync model

Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01.

Gemini Enterprise

Agent cross-checked Support: partial

Both federated and copied-index connectors exist; deletion and ACL freshness must be scoped to the connector and sync mode.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The partial atomic answers state their documentation or verification limits.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-connect-overview, gemini-enterprise:gemini-enterprise:g-locations.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin.

KNOW-06 Grounding and retrieval quality

Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking.

Gemini Enterprise

Agent cross-checked Support: partial

Source panels and citation chips are documented; retrieval quality remains unmeasured.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: citation_accuracy, cross_language, no_answer_behaviour, observed_accuracy.
  • citations Are answers linked to specific sources? [supported]: Answers expose a Sources panel and inline citations with supporting-result highlighting. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • citation_accuracy Do the cited passages support the answer? [unknown]: Unknown. No shared DE/FR/EN corpus question set or two-user fixture was run; documentation is not evidence of this observed retrieval outcome.
  • cross_language Does a question in one language find documents in another? [unknown]: Unknown. No shared DE/FR/EN corpus question set or two-user fixture was run; documentation is not evidence of this observed retrieval outcome.
  • no_answer_behaviour Does it say when the corpus has no answer? [unknown]: Unknown. No shared DE/FR/EN corpus question set or two-user fixture was run; documentation is not evidence of this observed retrieval outcome.
  • observed_accuracy How many of the question set were answered correctly? [unknown]: Unknown. No shared DE/FR/EN corpus question set or two-user fixture was run; documentation is not evidence of this observed retrieval outcome.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-chat.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access.

KNOW-07 Memory and personal context

Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide.

Gemini Enterprise

Agent cross-checked Support: partial

Users control saved memories and personal profiles; administrators can disable app-wide memory.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The partial atomic answers state their documentation or verification limits.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-personalization.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access.

Assistants and agents

AGT-01 Custom assistants

Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here.

Gemini Enterprise

Agent cross-checked Support: partial

Custom chat agents have instructions, knowledge and tools; app controls govern creation and sharing.

Availability: beta · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The edition comparison labels no-code agent tools preview; individual features have separate release stages.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-agents, gemini-enterprise:gemini-enterprise:g-features, gemini-enterprise:gemini-enterprise:g-workflow, gemini-enterprise:gemini-enterprise:g-start.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access.

AGT-02 Tools, actions and MCP

Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary.

Gemini Enterprise

Agent cross-checked Support: partial

Connector actions and remote MCP integrations are documented, with user or service-agent authentication by route.

Availability: beta · Delivery: official-integration
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The partial atomic answers state their documentation or verification limits.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-start, gemini-enterprise:gemini-enterprise:g-features, gemini-enterprise:gemini-enterprise:g-mcp, gemini-enterprise:gemini-enterprise:g-connectors, gemini-enterprise:gemini-enterprise:g-actions.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code.

AGT-03 Web search and deep research

Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off.

Gemini Enterprise

Agent cross-checked Support: partial

Web grounding and Deep Research are documented; Google Search and Enterprise web grounding have different residency treatment.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The partial atomic answers state their documentation or verification limits.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-configure, gemini-enterprise:gemini-enterprise:g-locations, gemini-enterprise:gemini-enterprise:g-research, gemini-enterprise:gemini-enterprise:g-chat.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access.

AGT-04 Workflows and automation

Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow.

Gemini Enterprise

Agent cross-checked Support: partial

Workflow Builder supports no-code/low-code chains; scheduled chat agents have a recurring credential-renewal requirement.

Availability: beta · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: event_triggers.
  • workflow_builder Is there a workflow or chain builder? [supported]: Business users build chat agents and multi-step workflows using natural language and a visual editor. Sources: gemini-enterprise:gemini-enterprise:g-workflow.
  • scheduled_tasks Can prompts or assistants run on a schedule? [supported]: Non-workflow chat agents can run recurring personal tasks in multi-regions; schedules need manual credential refresh every 14 days. Sources: gemini-enterprise:gemini-enterprise:g-schedule.
  • event_triggers Can external events start a workflow? [unknown]: Unknown. Workflow documentation mentions triggers, but a verified matrix of external event types, required plans and authenticated execution boundaries was not obtained.
  • builder_audience Is building aimed at business users, IT or developers? [supported]: The documented builder supports business users through no-code interaction and more technical low-code workflow work. Sources: gemini-enterprise:gemini-enterprise:g-workflow.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-workflow, gemini-enterprise:gemini-enterprise:g-schedule.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api.

AGT-05 Agentic task execution

Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof.

Gemini Enterprise

Agent cross-checked Support: partial

The assistant documents multi-step tool execution and visible activity; autonomous-action safety boundaries are only partly established.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: stop_control.
  • agent_mode Is there an agent mode for multi-step tasks? [partial]: Agents plan/search across tools and connectors; no shared multi-step fixture task was executed. Sources: gemini-enterprise:gemini-enterprise:g-workflow, gemini-enterprise:gemini-enterprise:g-research.
  • visible_steps Are steps and tool calls shown? [supported]: Chat shows a plan explanation and expandable tool execution activity; this is not disclosure of raw model chain-of-thought. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • side_effect_confirmation Must the user confirm actions with side effects? [partial]: Scheduled chat agents restrict other-person actions and document paused-run approval. A consistent rule for all interactive mutations was not verified. Sources: gemini-enterprise:gemini-enterprise:g-schedule.
  • stop_control Can the user stop a running task? [unknown]: Unknown. A documented universal stop/cancel control for running agents was not established from the app and workflow guides.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-workflow, gemini-enterprise:gemini-enterprise:g-research, gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-schedule.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases.

AGT-06 Programmable access

Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP.

Gemini Enterprise

Agent cross-checked Support: partial

Discovery Engine documents programmatic assistant and knowledge operations; parity with all UI governance remains open.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise Discovery Engine API; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: mcp_server.
  • chat_api Is there an API for chat and assistants? [supported]: The public REST reference lists assistants, agent operations and conversational/search resources; methods span API versions. Sources: gemini-enterprise:gemini-enterprise:g-api.
  • knowledge_api Can documents be loaded through an API? [supported]: Data-store document resources support programmatic knowledge operations. Sources: gemini-enterprise:gemini-enterprise:g-api.
  • api_governance Do audit, budgets and model rules apply to API use? [partial]: Google identity/IAM and method-specific audit logging apply; complete parity for every seat quota, model policy and budget route was not tested. Sources: gemini-enterprise:gemini-enterprise:g-api-auth, gemini-enterprise:gemini-enterprise:g-audit.
  • mcp_server Does the product expose itself to other agents over MCP? [unknown]: Unknown. A custom-MCP client integration is documented; a supported MCP server exposing the entire Enterprise product was not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-api, gemini-enterprise:gemini-enterprise:g-api-auth, gemini-enterprise:gemini-enterprise:g-audit.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access.

Daily work

WORK-01 Clients and access points

Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website.

Gemini Enterprise

Agent cross-checked Support: partial

Web and managed mobile access are documented; desktop-app availability is entangled with the wider early-access rollout.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace, Gemini Enterprise mobile app; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: desktop_apps, browser_extension.
  • web Is a full web client available? [supported]: The Enterprise web app is a documented access path. Sources: gemini-enterprise:gemini-enterprise:g-start.
  • desktop_apps Windows and macOS apps? [unknown]: Unknown. The wider marketing page describes desktop early access, but a released Standard/Plus desktop application and its precise entitlement were not established.
  • mobile_apps iOS and Android apps with SSO? [supported]: The mobile setup supports iOS/Android MDM configuration with Google and third-party identities. Sources: gemini-enterprise:gemini-enterprise:g-mobile.
  • browser_extension Is there a browser extension or sidebar? [unknown]: Unknown. Chrome address-bar integration appears in historical release notes, but current extension package, licence and feature parity were not reverified.
  • managed_deployment Can IT deploy and configure clients through MDM? [supported]: Admins can distribute/configure mobile access using MDM configuration keys, QR codes or links. Sources: gemini-enterprise:gemini-enterprise:g-mobile.
  • client_feature_gaps Which features are missing on mobile? [partial]: Canvas is explicitly unavailable on mobile; a complete web/mobile parity matrix was not obtained. Sources: gemini-enterprise:gemini-enterprise:g-canvas.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-start, gemini-enterprise:gemini-enterprise:g-mobile, gemini-enterprise:gemini-enterprise:g-canvas.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights.

WORK-02 Office suite and Teams integration

Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02.

Gemini Enterprise

Agent cross-checked Support: partial

Gemini Enterprise agent access in a Workspace side panel and a custom Gmail/Chat add-on route are documented. Exact native editor coverage and Office clients remain unverified.

Availability: unknown · Delivery: official-integration
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace, Gemini Enterprise Discovery Engine API, Gemini Enterprise agents in Workspace side panel or customer-built Workspace add-on; version=Public Workspace admin guide and official Gemini Enterprise integration codelab retrieved 2026-10-26; plan=Gemini Enterprise Standard/Plus and separately eligible Google Workspace accounts for the documented custom integration; native per-editor entitlement matrix unverified; add_ons=Separate Google Workspace account/subscription, Customer-built Apps Script add-on and Cloud project/API permissions where using the codelab route; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The official sample demonstrates Gmail/Chat and calls Docs/Sheets/Slides extension targets; no per-editor deployment or entitlement fixture was run.
  • Side-panel agent availability is documented, but a full shipped native editor feature matrix and Word/Excel/PowerPoint/Outlook/Teams assistant clients remain unverified.
  • The custom add-on requires deployment, authentication/permissions and production hardening; connector actions alone do not establish an embedded editor.
  • word_excel_powerpoint Does it work inside Word, Excel and PowerPoint? [unknown]: Unresolved on 2026-10-26. Searched https://cloud.google.com/gemini-enterprise/faq , https://docs.cloud.google.com/gemini/enterprise/docs/connectors/ms-teams , https://knowledge.workspace.google.com/admin/generative-ai/gemini-enterprise/turn-gemini-enterprise-on-or-off-for-users and https://codelabs.developers.google.com/ge-gws-agents . The documented Microsoft routes are connector search/actions, while the demonstrated embedded UI is a customer-built Google Workspace add-on. No first-party native Office/Outlook/Teams assistant client and its in-editor data/consent contract were established.
  • outlook Does it work inside Outlook? [unknown]: Unresolved on 2026-10-26. Searched https://cloud.google.com/gemini-enterprise/faq , https://docs.cloud.google.com/gemini/enterprise/docs/connectors/ms-teams , https://knowledge.workspace.google.com/admin/generative-ai/gemini-enterprise/turn-gemini-enterprise-on-or-off-for-users and https://codelabs.developers.google.com/ge-gws-agents . The documented Microsoft routes are connector search/actions, while the demonstrated embedded UI is a customer-built Google Workspace add-on. No first-party native Office/Outlook/Teams assistant client and its in-editor data/consent contract were established.
  • teams Is there a Teams app or bot? [unknown]: Unresolved on 2026-10-26. Searched https://cloud.google.com/gemini-enterprise/faq , https://docs.cloud.google.com/gemini/enterprise/docs/connectors/ms-teams , https://knowledge.workspace.google.com/admin/generative-ai/gemini-enterprise/turn-gemini-enterprise-on-or-off-for-users and https://codelabs.developers.google.com/ge-gws-agents . The documented Microsoft routes are connector search/actions, while the demonstrated embedded UI is a customer-built Google Workspace add-on. No first-party native Office/Outlook/Teams assistant client and its in-editor data/consent contract were established.
  • google_workspace_apps Does it work inside Docs, Sheets or Gmail? [partial]: Google’s admin guide explicitly permits Gemini Enterprise agents in a side panel for enabled licensed users. An official codelab demonstrates a custom Apps Script/StreamAssist add-on in Gmail and Chat with current-message context; Docs/Sheets/Slides are stated extension targets. A shipped native editing contract for each editor was not established, and the distinct Gemini-in-Workspace product is not inherited. Sources: gemini-enterprise:gemini-enterprise:r5-workspace-agent-access, gemini-enterprise:gemini-enterprise:r5-workspace-custom-addon, gemini-enterprise:gemini-enterprise:r5-offer-boundaries.
  • licence_prerequisites Which licences or consents are needed? [partial]: Gemini Enterprise licences are separate from Google Workspace subscriptions. The custom integration tutorial requires enabled Enterprise Standard/Plus, a billed Cloud project, Workspace Business/Enterprise with Chat and smart features, and authorized APIs/scopes. Workspace admins separately control service access and Workspace-data access; these prerequisites do not license an embedded Office client. Sources: gemini-enterprise:gemini-enterprise:r5-workspace-agent-access, gemini-enterprise:gemini-enterprise:r5-workspace-custom-addon.

Checked ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: gemini-enterprise:gemini-enterprise:r5-workspace-agent-access, gemini-enterprise:gemini-enterprise:r5-workspace-custom-addon, gemini-enterprise:gemini-enterprise:r5-offer-boundaries.

LibreChat

No public information found 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.

Gemini Enterprise

Agent cross-checked Support: partial

Canvas provides tone/length adjustments and instructed rewriting. Layout-preserving document translation, a dedicated engine and a corporate glossary in the Enterprise app remain unverified.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Canvas editing and DOCX/PDF export do not establish preserved source-document layout during translation.
  • Cloud Translation Advanced documents formatted-document translation and glossaries as a separate API; no included Enterprise-app feature or engine relationship was verified.
  • No shared DE-to-FR/IT translation, terminology or Swiss-language fixture was run.
  • document_translation Can whole documents be translated with formatting kept? [unknown]: Unresolved on 2026-10-26. Re-read https://docs.cloud.google.com/gemini/enterprise/docs/assistant-canvas , https://cloud.google.com/gemini-enterprise/faq and https://docs.cloud.google.com/translate/docs/advanced/translate-documents , with targeted Enterprise-doc searches for translation/glossary. Canvas documents generation/editing/export, not a source-layout-preserving translation or maintained company glossary. Cloud Translation Advanced is a separate API with project/authentication prerequisites; no built-in or included Enterprise-app mapping was established. No shared translation/glossary fixture was run.
  • translation_engine Which engine translates? [unknown]: Unresolved on 2026-10-26. Re-read https://docs.cloud.google.com/gemini/enterprise/docs/assistant-canvas , https://cloud.google.com/gemini-enterprise/faq and https://docs.cloud.google.com/translate/docs/advanced/translate-documents , with targeted Enterprise-doc searches for translation/glossary. Canvas documents generation/editing/export, not a source-layout-preserving translation or maintained company glossary. Cloud Translation Advanced is a separate API with project/authentication prerequisites; no built-in or included Enterprise-app mapping was established. No shared translation/glossary fixture was run.
  • glossaries Are company glossaries supported? [unknown]: Unresolved on 2026-10-26. Re-read https://docs.cloud.google.com/gemini/enterprise/docs/assistant-canvas , https://cloud.google.com/gemini-enterprise/faq and https://docs.cloud.google.com/translate/docs/advanced/translate-documents , with targeted Enterprise-doc searches for translation/glossary. Canvas documents generation/editing/export, not a source-layout-preserving translation or maintained company glossary. Cloud Translation Advanced is a separate API with project/authentication prerequisites; no built-in or included Enterprise-app mapping was established. No shared translation/glossary fixture was run.
  • formality_and_variants Can formality and regional variants (de-CH) be set? [partial]: Canvas provides a Change tone slider and selected-text instructions, so tone can be adjusted. A documented de-CH variant preset, deterministic terminology control or Swiss-language quality result was not established. Sources: gemini-enterprise:gemini-enterprise:r5-canvas-tone.
  • writing_tools Are dedicated rewrite and proofreading tools available? [supported]: Canvas supports direct edits, selected-text rewriting and tone/length adjustments with exported editable documents. Sources: gemini-enterprise:gemini-enterprise:g-canvas.

Checked ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: gemini-enterprise:gemini-enterprise:g-canvas, gemini-enterprise:gemini-enterprise:r5-canvas-tone, gemini-enterprise:gemini-enterprise:r5-translation-separate-api.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

WORK-04 Image generation and editing

Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images.

Gemini Enterprise

Agent cross-checked Support: partial

Admins can enable image models; location and paid-usage conditions vary.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: image_editing.
  • image_generation Can users generate images, with which models? [supported]: Listed image options are Gemini 2.5 Flash image, Gemini 3 Pro image and Gemini 3.1 Flash image; Nano Banana Pro is global-only. Sources: gemini-enterprise:gemini-enterprise:g-features, gemini-enterprise:gemini-enterprise:g-locations.
  • image_editing Can users edit uploaded images? [unknown]: Unknown. General image generation is documented; precise uploaded-image editing/inpainting controls and per-model entitlement were not established.
  • admin_control Can admins restrict image generation? [supported]: App feature controls enable/disable image generation and select the image model. Sources: gemini-enterprise:gemini-enterprise:g-features.
  • usage_terms What usage rights apply to output? [partial]: Google Cloud Generated Output terms apply; third-party links and underlying rights are not transferred by the service terms. Sources: gemini-enterprise:gemini-enterprise:g-terms.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-features, gemini-enterprise:gemini-enterprise:g-locations, gemini-enterprise:gemini-enterprise:g-terms.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access.

WORK-05 Voice and meetings

Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed.

Gemini Enterprise

Agent cross-checked Support: partial

Web dictation and mobile read-aloud are documented; live conversation and meeting workflow scope remain unverified.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace, Gemini Enterprise mobile app; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: voice_conversation, meeting_summaries, swiss_german_speech.
  • dictation Can users dictate prompts? [supported]: Admin-enabled web speech-to-text transcribes prompts; the guide states recordings are not stored. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • read_aloud Can answers be read aloud? [supported]: The mobile app can read generated answers aloud. Sources: gemini-enterprise:gemini-enterprise:g-use-mobile.
  • voice_conversation Is a live voice mode available? [unknown]: Unknown. No Enterprise-app-specific source or fixture established this voice/meeting behavior; generic Gemini Live API and Workspace Meet features were not carried over.
  • meeting_summaries Are meetings transcribed and summarised? [unknown]: Unknown. No Enterprise-app-specific source or fixture established this voice/meeting behavior; generic Gemini Live API and Workspace Meet features were not carried over.
  • swiss_german_speech Is Swiss German speech recognised? [unknown]: Unknown. No Enterprise-app-specific source or fixture established this voice/meeting behavior; generic Gemini Live API and Workspace Meet features were not carried over.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-use-mobile.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2.

WORK-06 Data analysis and document output

Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable.

Gemini Enterprise

Agent cross-checked Support: partial

The assistant documents spreadsheet code execution and Canvas document/slide exports.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: charts.
  • data_analysis Can it analyse spreadsheets with executed code? [partial]: Large XLSX/CSV files are analyzed with executed code and the guide says the executed code is displayed; fixture correctness was not tested. Sources: gemini-enterprise:gemini-enterprise:g-chat.
  • charts Can it produce charts? [unknown]: Unknown. A chart-generation example with downloadable/editable output was not verified through the shared spreadsheet fixture.
  • office_file_output Can it create Word, Excel or PowerPoint files? [partial]: Canvas exports DOCX documents and PowerPoint slides, plus PDF/Google formats. Native XLSX output was not established. Sources: gemini-enterprise:gemini-enterprise:g-canvas.
  • canvas_editing Is there a document or canvas editor for iterating on output? [supported]: The web Canvas supports manual formatting and AI edits; each slide update produces a new artifact rather than modifying the old one. Sources: gemini-enterprise:gemini-enterprise:g-canvas.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-canvas.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts.

WORK-07 Sharing and team spaces

Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to.

Gemini Enterprise

Agent cross-checked Support: partial

Projects share sources, while project chats stay private and conversation links share snapshots.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Knowledge ACL enforcement is distinct from the content already copied into a shared conversation.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-share, gemini-enterprise:gemini-enterprise:g-projects.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects.

WORK-08 Interface languages and accessibility

Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements.

Gemini Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin.

Administration and governance

ADM-01 Single sign-on and authentication

Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible.

Gemini Enterprise

Agent cross-checked Support: partial

Google Identity and SAML/OIDC federation are documented; tenant policy and domain capture need separate verification.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: mfa, conditional_access, domain_capture.
  • sso_protocols Which SSO protocols and identity providers work? [supported]: Google Identity or Workforce Identity Federation can use SAML 2.0/OIDC providers including Entra ID and Okta. Sources: gemini-enterprise:gemini-enterprise:g-identity.
  • sso_plan Which plan includes SSO? [supported]: The retrieved identity guide covers Standard/Plus and other Cloud-managed editions, not Business account administration. Sources: gemini-enterprise:gemini-enterprise:g-identity.
  • mfa Can MFA be enforced? [unknown]: Unknown. The identity setup guide did not establish this exact policy behavior and no SSO tenant test was performed.
  • conditional_access Do Entra conditional-access policies apply? [unknown]: Unknown. The identity setup guide did not establish this exact policy behavior and no SSO tenant test was performed.
  • domain_capture Can the company claim its email domain? [unknown]: Unknown. The identity setup guide did not establish this exact policy behavior and no SSO tenant test was performed.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-identity.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra.

ADM-02 User provisioning and lifecycle

Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content.

Gemini Enterprise

Agent cross-checked Support: partial

SCIM/group mapping and automatic licence assignment are documented; content ownership after deprovisioning was not tested.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: deprovisioning.
  • scim Is SCIM provisioning supported? [partial]: Entra and Okta SCIM configuration is documented for identity/group data and sharing autocomplete; complete content-lifecycle behavior was not verified. Sources: gemini-enterprise:gemini-enterprise:g-identity.
  • group_sync Are identity-provider groups synced? [supported]: Identity/group mappings support permission-aware stores; large Entra group counts require documented SCIM setup. Sources: gemini-enterprise:gemini-enterprise:g-identity.
  • jit_provisioning Are users created at first login? [supported]: A subscription can automatically assign a licence the first time an entitled user opens Enterprise or Notebook Enterprise. Sources: gemini-enterprise:gemini-enterprise:g-license-details.
  • deprovisioning What happens to a removed user's data and shared assets? [unknown]: Unknown. No leaver fixture established chat/agent/knowledge ownership transfer or final deletion after user removal.
  • seat_assignment Can admins assign and reclaim seats? [supported]: Admins can manually assign/unassign users and redistribute available licences across projects within a billing account. Sources: gemini-enterprise:gemini-enterprise:g-license-details.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-identity, gemini-enterprise:gemini-enterprise:g-license-details.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license.

ADM-03 Roles, groups and feature permissions

Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group.

Gemini Enterprise

Agent cross-checked Support: partial

IAM and app boundaries govern administrator access and feature controls; a verified per-group feature matrix remains open.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: multi_entity.
  • admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: Google defines Enterprise Admin/User IAM roles and fine-grained Discovery Engine permissions. Sources: gemini-enterprise:gemini-enterprise:g-access-control.
  • groups Can permissions be set per group? [partial]: IAM policies can target group principals; feature toggles shown in the guide are app-wide rather than a demonstrated per-group feature matrix. Sources: gemini-enterprise:gemini-enterprise:g-access-control, gemini-enterprise:gemini-enterprise:g-features.
  • feature_toggles Which features can be switched on or off per group? [partial]: App controls include agent/gallery creation, sharing, memory, projects, Canvas, model choice, images and speech-to-text; per-group enforcement was not tested. Sources: gemini-enterprise:gemini-enterprise:g-features.
  • multi_entity Can subsidiaries or departments be separated within one contract? [unknown]: Unknown. Projects/apps provide boundaries, but contract-level subsidiary separation and administration were not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-access-control, gemini-enterprise:gemini-enterprise:g-features.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights.

ADM-04 Usage and adoption analytics

Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring.

Gemini Enterprise

Agent cross-checked Support: partial

Adoption, agent and optional identifiable user reporting are documented, with downloadable analytics.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: privacy_modes.
  • adoption_dashboard Is there an adoption dashboard? [supported]: The Looker-based dashboard includes adoption and usage/quality metrics, refreshed about every six hours. Sources: gemini-enterprise:gemini-enterprise:g-analytics.
  • breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Agent and allowlisted User Level tabs are documented; model/group breakdown completeness was not established. Sources: gemini-enterprise:gemini-enterprise:g-analytics.
  • export Can usage data be exported? [supported]: The analytics API exports the past 30 days of metrics to a regional BigQuery table, with documented export-call quotas. Sources: gemini-enterprise:gemini-enterprise:g-analytics.
  • privacy_modes Can per-person reporting be limited or pseudonymised? [unknown]: Unknown. User-level reporting contains user identifiers when enabled; an administrator pseudonymization or works-council reporting mode was not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-analytics.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens.

ADM-05 Spend controls and cost allocation

Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts.

Gemini Enterprise

Agent cross-checked Support: partial

Eligible projects have real spend caps; these are project-level controls with delayed enforcement, not proven per-group budgets.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: chargeback.
  • cost_visibility Can admins see cost or consumption per user and group? [partial]: The console shows project consumption and 30-day overage/PAYG costs, excluding licence subscriptions; per-user/group cost allocation was not established. Sources: gemini-enterprise:gemini-enterprise:g-costs.
  • budgets Can budgets be set per user or group? [partial]: Eligible invoiced, non-trial projects can set a monthly cap across the app/platform/developer-tool service scope; per-user/group caps were not established. Sources: gemini-enterprise:gemini-enterprise:g-budget.
  • budget_enforcement Does reaching a budget alert, block or downgrade? [supported]: At the cap, overages stop and users see a limit error; enforcement may take minutes and charges can exceed the cap. Sources: gemini-enterprise:gemini-enterprise:g-budget.
  • chargeback Can costs be exported per cost centre? [unknown]: Unknown. Cost-centre export and attribution for all seat/model/agent charges were not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-costs, gemini-enterprise:gemini-enterprise:g-budget.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin.

ADM-06 Audit logs and compliance export

Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model.

Gemini Enterprise

Agent cross-checked Support: partial

Method-level audit events and configurable prompt/response logging are documented; retention and legal hold remain open.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: ediscovery, log_retention.
  • admin_events Are admin and security events logged? [supported]: Cloud Audit Logs enumerates administrative and data-access methods and required permissions. Sources: gemini-enterprise:gemini-enterprise:g-audit.
  • content_logging Can prompts and answers be retained for compliance, and is it configurable? [supported]: Usage logs include sensitive prompts/responses only when content logging is enabled; otherwise sensitive text is elided. Sources: gemini-enterprise:gemini-enterprise:g-usage-logs.
  • siem_export Can logs stream to a SIEM or be exported? [partial]: Cloud Logging supports log sinks, separate projects, views and field-level access control; a target SIEM integration was not tested. Sources: gemini-enterprise:gemini-enterprise:g-usage-logs.
  • ediscovery Are eDiscovery and legal hold supported? [unknown]: Unknown. No scoped legal-hold or eDiscovery export guarantee was established for this app.
  • log_retention How long are logs kept? [unknown]: Unknown. Usage-log documentation sends data to Cloud Logging but the applicable bucket retention/integrity configuration was not retrieved; no universal retention is asserted.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-audit, gemini-enterprise:gemini-enterprise:g-usage-logs.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin.

ADM-07 Data loss prevention and personal data

Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome.

Gemini Enterprise

Agent cross-checked Support: partial

Model Armor inspection and blocking and source-ingestion policies are documented. Effective PII redaction remains unknown because the setup summary conflicts with its linked integration guide.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: custom_patterns.
  • The redaction discrepancy is retained as an explicit gap, not a positive or negative redaction capability. No masking fixture was run; do not infer transformation from a blocked response.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-armor, gemini-enterprise:gemini-enterprise:g-dlp, gemini-enterprise:gemini-enterprise:g-admin-setup-correction.

LibreChat

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.

Checked ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318.

ADM-08 AI policy and guardrails

Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow.

Gemini Enterprise

Agent cross-checked Support: partial

Admins can add assistant instructions, banned phrases and configurable inspection/blocking policies.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: usage_notice.
  • org_instructions Can admins set organisation-wide instructions? [supported]: Admins can set additional LLM system instructions for the app assistant; instructions alone are not proof of enforcement. Sources: gemini-enterprise:gemini-enterprise:g-configure.
  • usage_notice Can users be required to accept a usage policy? [unknown]: Unknown. An enforced organization-specific usage-policy acknowledgement flow was not established.
  • content_filters Are content filters configurable? [supported]: Banned phrases reject matching input, and Model Armor templates separately configure inspect-only versus inspect-and-block behavior. Sources: gemini-enterprise:gemini-enterprise:g-configure, gemini-enterprise:gemini-enterprise:g-armor.
  • violation_reporting Are policy hits visible to admins? [partial]: Model Armor screening data can be logged/routed with access restrictions; a complete central policy-hit reporting interface was not established. Sources: gemini-enterprise:gemini-enterprise:g-armor.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-configure, gemini-enterprise:gemini-enterprise:g-armor.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod.

Data protection and sovereignty

DATA-01 Hosting location and data residency

Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions.

Gemini Enterprise

Agent cross-checked Support: partial

US/EU storage and model-processing commitments are feature-specific; this is not a blanket EU/Swiss data boundary.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Google Search grounding is global; optional features can route out of the selected location.
  • Remaining atomic gaps: backups_logs_region, support_access_region, swiss_hosting.
  • storage_region Where are chats, files and indexes stored? [supported]: Standard/Plus data stores offer global/us/eu and allowlisted Canada, India, Japan, Singapore and UK locations. Sources: gemini-enterprise:gemini-enterprise:g-locations.
  • inference_region Where do model calls run, per provider? [supported]: Base and named Gemini/Claude models support US/EU processing; 3.1 Pro EU, global-only image models and Google Search grounding have explicit exceptions. Sources: gemini-enterprise:gemini-enterprise:g-locations.
  • backups_logs_region Where are backups, logs and telemetry? [unknown]: Unknown. The residency page does not establish every backup, usage-log and telemetry location together.
  • support_access_region From where can vendor staff access data? [unknown]: Unknown. A source-region selection is not a staff-access restriction; the subprocessor list includes international support and no universal EU-only staff-access promise was established.
  • swiss_hosting Is Swiss hosting available? [unknown]: Unknown. Switzerland is not a named selectable location in the retrieved service location table; a separate Swiss-only offer was not verified.
  • residency_plan Which plan or option provides residency? [supported]: These location commitments apply to the named Cloud-managed editions; Business has separate documentation and is not inferred to inherit them. Sources: gemini-enterprise:gemini-enterprise:g-locations.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-locations.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license.

DATA-02 Deployment options

Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment.

Gemini Enterprise

Agent cross-checked Support: partial

The documented offer is Google-managed Cloud SaaS; private source connectivity does not establish private deployment of the whole assistant.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: dedicated_instance, customer_cloud, on_premise, air_gapped, mode_feature_gaps.
  • multi_tenant_saas Is a shared SaaS offered? [supported]: The documented managed service uses a Google Cloud project, selected service location and subscription. Sources: gemini-enterprise:gemini-enterprise:g-security, gemini-enterprise:gemini-enterprise:g-license-details.
  • dedicated_instance Is a dedicated single-tenant instance offered, from what size? [unknown]: Unknown. The residency, security and self-hosted-source guides did not establish this deployment mode, whole-platform operability, size threshold or mode-specific parity; source Private Service Connect is a connector route only.
  • customer_cloud Can it run in the customer's own cloud account, from what size? [unknown]: Unknown. The residency, security and self-hosted-source guides did not establish this deployment mode, whole-platform operability, size threshold or mode-specific parity; source Private Service Connect is a connector route only.
  • on_premise Can the whole platform run on customer infrastructure, from what size? [unknown]: Unknown. The residency, security and self-hosted-source guides did not establish this deployment mode, whole-platform operability, size threshold or mode-specific parity; source Private Service Connect is a connector route only.
  • air_gapped Can it run without internet access? [unknown]: Unknown. The residency, security and self-hosted-source guides did not establish this deployment mode, whole-platform operability, size threshold or mode-specific parity; source Private Service Connect is a connector route only.
  • mode_feature_gaps Which features are missing outside SaaS? [unknown]: Unknown. The residency, security and self-hosted-source guides did not establish this deployment mode, whole-platform operability, size threshold or mode-specific parity; source Private Service Connect is a connector route only.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-security, gemini-enterprise:gemini-enterprise:g-license-details.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code.

DATA-03 Training use and provider retention

Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so.

Gemini Enterprise

Agent cross-checked Support: partial

Google contract terms restrict training without customer permission; partner retention and human-review conditions need separate confirmation.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: provider_training, provider_retention, zero_retention, human_review.
  • vendor_training Does the vendor train on customer content? [supported]: The AI/ML service terms prohibit using Customer Data for model training/fine-tuning without prior customer permission or instruction. Sources: gemini-enterprise:gemini-enterprise:g-terms.
  • provider_training Do model providers train on it under this product's contracts? [unknown]: Unknown. Separate terms apply to partner offerings, but the accepted Enterprise-app Claude contract was not obtained; Google terms are not silently applied to every partner.
  • provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: Unknown. The core assistant/partner abuse-monitoring retention matrix was not established. Google Search grounding has separately documented logging exceptions.
  • zero_retention Is zero data retention available, and on which plan? [unknown]: Unknown. No end-to-end ZDR guarantee covering persistent chat, grounding, agents and every model provider was established.
  • human_review Can provider staff review content? [unknown]: Unknown. A complete plan/provider-specific human-review policy for the app was not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-terms.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat.

DATA-04 Retention and deletion

Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation.

Gemini Enterprise

Agent cross-checked Support: partial

Chat retention is configurable and legal deletion windows are documented, with different scopes.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The partial atomic answers state their documentation or verification limits.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-configure, gemini-enterprise:gemini-enterprise:g-organize, gemini-enterprise:gemini-enterprise:g-security, gemini-enterprise:gemini-enterprise:g-dpa.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings.

DATA-05 Sub-processors and foreign-law exposure

Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment.

Gemini Enterprise

Agent cross-checked Support: partial

Google publishes a global subprocessor list and contractual transfer rules; selected residency does not settle legal or support-access exposure.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: change_notification, parent_jurisdiction, government_access_policy.
  • subprocessor_list Is a dated sub-processor list published? [partial]: A public Cloud subprocessor list identifies service activities and processing locations; a single page-effective date was not established. Sources: gemini-enterprise:gemini-enterprise:g-subprocessors.
  • subprocessor_countries Which countries do sub-processors operate in? [supported]: Support examples span the US, Canada, India, Ireland, Romania and other countries; the full list is service-specific rather than a chosen-region-only list. Sources: gemini-enterprise:gemini-enterprise:g-subprocessors.
  • change_notification Are customers notified of sub-processor changes? [unknown]: Unknown. Subprocessor objection/notice provisions exist in CDPA section 11, but the exact notice period applicable to this procurement was not verified.
  • parent_jurisdiction Which jurisdiction governs the vendor and its parent? [unknown]: Unknown. The exact EMEA contracting-entity/parent chain was not independently retrieved; no entity is inferred from the selected data region.
  • transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [supported]: The CDPA provides adequacy/alternative-transfer mechanisms and SCC routes for restricted transfers, including Swiss-law adaptations. Sources: gemini-enterprise:gemini-enterprise:g-dpa.
  • government_access_policy Is there a published government-access or transparency policy? [unknown]: Unknown. The tested government-requests URL returned a short non-substantive response; a retrievable scoped policy and transparency report remain a gap.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-subprocessors, gemini-enterprise:gemini-enterprise:g-dpa.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner.

DATA-06 Contracts and regulatory coverage

Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict.

Gemini Enterprise

Agent cross-checked Support: partial

The public CDPA covers GDPR and Swiss FADP; sector and governing-law details remain procurement-specific.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: governing_law, ai_act_materials, sector_materials.
  • dpa Is a DPA available, and is it negotiable? [partial]: Google publishes the Cloud Data Processing Addendum; negotiability for a particular order was not established. Sources: gemini-enterprise:gemini-enterprise:g-dpa.
  • revdsg_gdpr Does the DPA cover revDSG and GDPR? [supported]: The CDPA defines European Data Protection Law to include applicable GDPR and Swiss FADP and includes Swiss transfer adaptations. Sources: gemini-enterprise:gemini-enterprise:g-dpa.
  • governing_law Which law and court govern the contract? [unknown]: Unknown. The base terms point to region-specific terms/contracting entities; the governing agreement for a Swiss/EU order was not established.
  • ai_act_materials Is EU AI Act documentation provided? [unknown]: Unknown. No scoped EU AI Act provider/deployer documentation pack was obtained for this app.
  • sector_materials Are FINMA or other sector materials provided? [unknown]: Unknown. General Cloud compliance materials do not establish FINMA/banking-secrecy coverage for a particular Enterprise deployment.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-dpa.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

DATA-07 Certifications and attestations

Judgment rule: Record each certificate or report separately: ISO 27001, 27017, 27018, 27701, 42001; SOC 2 Type I/II with period; BSI C5; TISAX; national schemes. Record issuer, scope (which product and entity), validity and access route. A cloud provider's certificate does not certify the product.

Gemini Enterprise

Agent cross-checked Support: partial

The vendor lists multiple compliance programs; certificates and report periods were not independently verified.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The public report-access route is documented; report scope, issuer, reporting period and a product-specific penetration-test summary remain unverified.

Checked ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: gemini-enterprise:gemini-enterprise:g-compliance, gemini-enterprise:gemini-enterprise:r4-compliance-reports, gemini-enterprise:gemini-enterprise:r4-compliance-scope.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

DATA-08 Encryption and key control

Judgment rule: Record encryption at rest and in transit, customer-managed keys (BYOK/HYOK), key location, and private networking (private link, IP allow-lists, VPN).

Gemini Enterprise

Agent cross-checked Support: partial

Regional CMEK and Cloud security controls are documented; tenant separation and all-tool coverage still need review.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: tenant_isolation.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-connect-overview, gemini-enterprise:gemini-enterprise:g-encryption, gemini-enterprise:gemini-enterprise:g-compliance, gemini-enterprise:gemini-enterprise:g-security, gemini-enterprise:gemini-enterprise:g-selfhosted-data.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:auth, librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:local.

DATA-09 Professional secrecy

Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment.

Gemini Enterprise

Agent cross-checked Support: partial

Profession-specific secrecy undertaking and add-on remain unknown; general confidentiality and scoped content-access controls do not establish §203 StGB or Art.321 StGB coverage.

Availability: unknown · Delivery: unknown
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard/Plus under applicable Google Cloud contract; Workspace Gemini excluded; add_ons=none stated; deployment_mode=multi-tenant-saas; region=No profession-specific DE/CH contractual scope verified; deployment/provider regions follow the other scoped claims.; os=not specified.

Limitations

  • Contract facts only; no legal suitability assessment. No profession-specific commitment or paid option inferred from generic confidentiality, hosting, encryption or no-training terms.
  • Public, unauthenticated source pass only; no sales contact, NDA request or authenticated access-control test.
  • secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Unknown. Reviewed Gemini Enterprise security/contract documentation and Google Cloud CDPA, and searched Google first-party material for professional secrecy, Berufsgeheimnis and §203. No Gemini Enterprise-specific §203 StGB or Art.321 StGB template or dedicated add-on was retrieved. A DPA or no-training clause alone does not answer whether a profession-specific undertaking is signed.
  • subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Unknown. No retrieved §203/Art.321 undertaking establishes flow-down to all relevant subcontractors/model providers. General DPA confidentiality is not equivalent.
  • secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: Unknown. No documented profession-specific plan, dedicated instance option or paid secrecy add-on and its entitlements/pricing were established.
  • content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Google CDPA section7.1.2 binds authorised processors to confidentiality; Appendix2 describes role-based access, personnel confidentiality and authorisation. These are general data-security commitments. Exact staff/subprocessor/model-provider plaintext-access conditions and a profession-specific undertaking for this procurement remain unverified. Sources: gemini-enterprise:gemini-enterprise:g-dpa.
  • secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Unknown. Reviewed Gemini Enterprise security/contract documentation and Google Cloud CDPA, and searched Google first-party material for professional secrecy, Berufsgeheimnis and §203. No Gemini Enterprise-specific §203 StGB or Art.321 StGB template or dedicated add-on was retrieved. General data-flow/security pages are available but do not document such a secrecy offering.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-dpa.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom.

Commercials and vendor

VEN-01 Pricing model and list prices

Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment.

Gemini Enterprise

Agent cross-checked Support: partial

Business advertises a starting seat price; Standard/Plus licence quotes and separately metered model/tool costs remain distinct.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace, Gemini Enterprise Business edition web app; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=optional third-party models and overages; billed separately; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • The partial atomic answers state their documentation or verification limits.
  • pricing_unit What is the pricing unit? [supported]: Standard/Plus use seat subscriptions plus optional paid overages; Pay-as-you-go meters usage, while Business markets a per-seat starting price. Sources: gemini-enterprise:gemini-enterprise:g-quotas, gemini-enterprise:gemini-enterprise:g-business.
  • list_prices What are list prices per plan, with date and currency? [partial]: Business advertises USD 21/seat/month starting price on 2026-10-21. Publicly retrievable Standard/Plus base licence amounts and commitment-adjusted rates were not established. Sources: gemini-enterprise:gemini-enterprise:g-business.
  • included_usage What usage is included? [supported]: Standard/Plus pool 30/75 GiB storage, 160/200 daily assistant queries and 3/10 daily research requests per seat, subject to legacy exceptions. Sources: gemini-enterprise:gemini-enterprise:g-quotas.
  • add_ons Which features cost extra? [supported]: Claude app tokens, overage usage and external/custom-agent costs are separate from included Gemini use; detailed regional rates are in the quota table. Sources: gemini-enterprise:gemini-enterprise:g-quotas.
  • overage What do usage beyond limits and premium models cost? [supported]: PAYG storage is USD 5/GiB/month; Claude and other feature rates vary by model and region. Entitlement requires eligible invoiced billing. Sources: gemini-enterprise:gemini-enterprise:g-quotas.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-quotas, gemini-enterprise:gemini-enterprise:g-business.

LibreChat

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.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens.

VEN-02 Scenario cost

Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts.

Gemini Enterprise

Agent cross-checked Support: partial

No defensible Standard/Plus 12-month CHF/EUR total was established for 200, 1,000 or 5,000 seats.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Standard/Plus, 12 months, ALM-14 shared cost assumptions v1.4, 2026-10-21; add_ons=Default hosted models only; partner models, custom agents, support and implementation prices remain unknown; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Standard/Plus scenario totals for 200, 1,000 and 5,000 users remain unpriced.
  • Named unknown cost components are documented in the atomic answer; Business starting rates do not price Standard/Plus.
  • cost_200 Year-one cost at 200 users? [unknown]: Unknown. Standard/Plus base licence/commitment prices and required custom-agent/support charges were not established, so CHF/EUR totals excluding VAT remain unknown. ALM-14 shared cost assumptions v1.4, 2026-10-21: 12 months, 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, each 3,000 input + 600 output tokens when separately billed; 330 messages/user/month on average. No invented discounts or proxy usage tariff. ECB reference 2026-10-20: EUR 1 = USD 1.1215 = CHF 0.9237; no currency conversion is applied to an unknown base amount. Sources: gemini-enterprise:gemini-enterprise:fx-ecb-2026-10-20.
  • cost_1000 Year-one cost at 1,000 users? [unknown]: Unknown. Standard/Plus base licence/commitment prices and required custom-agent/support charges were not established, so CHF/EUR totals excluding VAT remain unknown. ALM-14 shared cost assumptions v1.4, 2026-10-21: 12 months, 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, each 3,000 input + 600 output tokens when separately billed; 330 messages/user/month on average. No invented discounts or proxy usage tariff. ECB reference 2026-10-20: EUR 1 = USD 1.1215 = CHF 0.9237; no currency conversion is applied to an unknown base amount. Sources: gemini-enterprise:gemini-enterprise:fx-ecb-2026-10-20.
  • cost_5000 Year-one cost at 5,000 users? [unknown]: Unknown. Standard/Plus base licence/commitment prices and required custom-agent/support charges were not established, so CHF/EUR totals excluding VAT remain unknown. ALM-14 shared cost assumptions v1.4, 2026-10-21: 12 months, 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, each 3,000 input + 600 output tokens when separately billed; 330 messages/user/month on average. No invented discounts or proxy usage tariff. ECB reference 2026-10-20: EUR 1 = USD 1.1215 = CHF 0.9237; no currency conversion is applied to an unknown base amount. Sources: gemini-enterprise:gemini-enterprise:fx-ecb-2026-10-20.
  • variable_share Which part depends on usage? [supported]: Costs vary with storage/indexing, partner-model tokens, paid overages and externally hosted agents beyond included pools. Sources: gemini-enterprise:gemini-enterprise:g-quotas.
  • unknown_parts Which costs could not be priced? [supported]: Unpriced parts are the Standard/Plus base seat and commitment rates, partner-model mix, external/custom-agent charges, support and implementation. Public Business starting prices do not price these editions; unknown tariffs remain unknown under shared cost assumptions v1.4. Sources: gemini-enterprise:gemini-enterprise:r4-pricing-gap, gemini-enterprise:gemini-enterprise:g-quotas, gemini-enterprise:gemini-enterprise:g-editions.

Checked ; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: gemini-enterprise:gemini-enterprise:g-quotas, gemini-enterprise:gemini-enterprise:fx-ecb-2026-10-20, gemini-enterprise:gemini-enterprise:r4-pricing-gap, gemini-enterprise:gemini-enterprise:g-editions.

LibreChat

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.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.

VEN-03 Evaluation access

Judgment rule: Distinguish free tier, self-serve trial, sales-led pilot, paid proof of concept and open-source self-install. Record card requirement, duration, seat limit, and which features (SSO, connectors, admin) the trial includes. Map which shared scenarios can be run without sales approval.

Gemini Enterprise

Agent cross-checked Support: partial

Thirty-day Business and Plus evaluation routes are publicly advertised; a trial tenant was not provisioned.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: free_tier, trial_scope.
  • free_tier Is there a free tier for business use? [unknown]: Unknown. A permanent business-use free tier was not established; a time-limited trial is not recorded as one.
  • self_serve_trial Is a self-serve business trial available? [partial]: Business advertises 30 days; the main product FAQ offers a 30-day Plus trial without sales assistance. Card requirement was not verified. Sources: gemini-enterprise:gemini-enterprise:g-business, gemini-enterprise:gemini-enterprise:g-pricing.
  • trial_scope Do trials include SSO, connectors and admin features? [unknown]: Unknown. The exact trial seat cap, SSO, connector/admin feature entitlements and scenario access were not verified in a tenant.
  • sales_gate Does meaningful evaluation require sales contact? [supported]: Initial trial access is advertised without sales; larger seat counts and allowlisted regions may require the account team. Sources: gemini-enterprise:gemini-enterprise:g-pricing, gemini-enterprise:gemini-enterprise:g-license-details.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-business, gemini-enterprise:gemini-enterprise:g-pricing, gemini-enterprise:gemini-enterprise:g-license-details.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:demo, librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag, librechat:librechat:firstchat.

VEN-04 Contract terms and pricing transparency

Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint.

Gemini Enterprise

Agent cross-checked Support: partial

Published self-service procurement and cancellation mechanics do not provide a complete Enterprise price contract.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: local_invoicing.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-editions, gemini-enterprise:gemini-enterprise:g-license-details, gemini-enterprise:gemini-enterprise:g-business, gemini-enterprise:gemini-enterprise:g-quotas.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat.

VEN-05 Source licence

Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse.

Gemini Enterprise

Agent cross-checked Support: partial

The assistant is supplied as a commercial hosted Cloud service; open model/documentation licences do not grant a self-hosted platform licence.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: enterprise_features_closed.
  • licence_type Which licence applies to each component? [supported]: The scoped platform is governed by commercial Google Cloud service terms; documentation and sample-code licences are separate. Sources: gemini-enterprise:gemini-enterprise:g-terms-main.
  • branding_restrictions Do licence terms restrict branding or user counts? [partial]: The base terms reserve ungranted intellectual-property rights; specific product rebranding or user-count licence rights were not established. Sources: gemini-enterprise:gemini-enterprise:g-terms-main.
  • enterprise_features_closed Are enterprise features in a separate closed edition? [unknown]: Unknown. A component-by-component source and enterprise-extension licence inventory was not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-terms-main.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code.

VEN-06 Data export and exit

Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable.

Gemini Enterprise

Agent cross-checked Support: partial

User exports cover responses and Canvas artifacts; a complete admin exit package was not tested.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: chat_export, assistant_export, knowledge_export, post_termination_window.
  • chat_export Can admins export all chats? [unknown]: Unknown. User output export is documented, but no complete all-user admin chat export was retrieved or tested.
  • assistant_export Can assistants and prompts be exported in a reusable format? [unknown]: Unknown. No portable complete agent definition/tool/secret export was verified; a skill export is not assumed to cover agents.
  • knowledge_export Can knowledge bases and their sources be exported? [unknown]: Unknown. No complete indexed knowledge/ACL/source export was verified.
  • export_format Are formats documented and machine-readable? [partial]: Response export supports Docs/Sheets; Canvas documents export DOCX/PDF and slides PPTX/PDF. Complete chat/agent/knowledge export formats were not established. Sources: gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-canvas.
  • post_termination_window How long can data be retrieved after termination? [unknown]: Unknown. The CDPA describes return during the term and an up-to-30-day recovery period, but this does not establish a guaranteed customer retrieval window after termination.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-chat, gemini-enterprise:gemini-enterprise:g-canvas.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api.

VEN-07 Support and service levels

Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score.

Gemini Enterprise

Agent cross-checked Support: partial

Google publishes support tiers and status history; a scoped Enterprise uptime-credit SLA was not retrieved.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: support_languages, regional_presence, uptime_sla.
  • support_channels Which support channels are available on each plan? [partial]: Cloud Customer Care lists Basic, Standard, Enhanced and Premium support; service-specific response entitlements depend on the purchased tier. Sources: gemini-enterprise:gemini-enterprise:g-support.
  • support_languages Is support available in German, French or Italian? [unknown]: Unknown. German/French/Italian support coverage and hours for the purchased Gemini tier were not established.
  • regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: Unknown. A named DACH/Swiss implementation partner or service team was not independently verified.
  • uptime_sla Is there an uptime SLA with credits? [unknown]: Unknown. The tested Gemini Enterprise SLA path returned a non-substantive response; no percentage or credit terms are asserted.
  • status_page Is there a public status page with history? [supported]: Google Cloud Service Health publishes service status and incident history. Sources: gemini-enterprise:gemini-enterprise:g-status.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-support, gemini-enterprise:gemini-enterprise:g-status.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat.

VEN-08 Onboarding, training and adoption

Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings.

Gemini Enterprise

Agent cross-checked Support: partial

Public setup and role-based use-case materials exist; included onboarding and training services remain unpriced.

Availability: unknown · Delivery: native
Scope: surfaces=Gemini Enterprise web app, distinct from Gemini in Google Workspace; version=not specified; plan=Gemini Enterprise Standard / Plus unless an atomic answer names Business or Pay-as-you-go; add_ons=none stated; deployment_mode=multi-tenant-saas; region=global, us or eu as selected; region and feature exceptions below; os=not specified.

Limitations

  • Remaining atomic gaps: onboarding_service, user_training, adoption_programme, service_cost.
  • onboarding_service Is guided onboarding included? [unknown]: Unknown. Public administrator setup documentation is available; included vendor-led onboarding was not established.
  • user_training Is end-user training offered, in which languages? [unknown]: Unknown. No scoped live/e-learning language catalogue with inclusion terms was obtained.
  • use_case_library Are role-based use cases and templates provided? [supported]: The app guide links role-specific examples for finance, HR, legal, marketing, sales and support, plus starter agents and skills. Sources: gemini-enterprise:gemini-enterprise:g-start.
  • adoption_programme Is there a champion or adoption programme? [unknown]: Unknown. No documented customer champion/change-management programme entitlement was established.
  • service_cost Which services cost extra? [unknown]: Unknown. Professional-service, partner-onboarding and training prices were not established.

Checked ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: gemini-enterprise:gemini-enterprise:g-start.

LibreChat

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 ; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat.

Sources

  1. Data residency for Gemini Enterprise Standard and Plus gemini-enterprise:gemini-enterprise:g-locations

    US/EU at-rest and processing commitments have model and tool exceptions; standard Google Search grounding is global.

    Multi-regions; In-country regions; Limitations table · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  2. Manage web app features gemini-enterprise:gemini-enterprise:g-features

    Administrators manage app-level model and feature toggles, including paid Claude models and image-generation model selection.

    Model availability; Enable Gemini models; Enable third-party models; feature controls · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  3. Chat with the assistant gemini-enterprise:gemini-enterprise:g-chat

    The chat guide documents direct file analysis, Auto routing, source attribution, spreadsheet code execution and specific connector search limitations.

    File formats and size limitations; Ask questions and view sources; Best practices; Limitations · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  4. Gemini Enterprise release notes gemini-enterprise:gemini-enterprise:g-releases

    Dated notes record new models, region-specific removals and corrections to prior deprecation announcements.

    2026-10-15 Claude launch; 2026-10-20 regional Gemini 2.5 Pro removal; 2026-08-06 postponement · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  5. Custom endpoints librechat:librechat:custom

    Operators configure compatible endpoints and customer-held keys, including local and hosted services.

    Endpoint setup; API key; base URL; model list · documented · Source date not stated · Retrieved 2026-10-21

  6. Azure OpenAI configuration librechat:librechat:azure

    Azure OpenAI uses customer deployment groups, instance names and credentials.

    Deployment groups; API credentials · documented · Source date not stated · Retrieved 2026-10-21

  7. AWS Bedrock object structure librechat:librechat:bedrock

    Bedrock routes use customer AWS configuration and region selection.

    Region; credentials; model selection · documented · Source date not stated · Retrieved 2026-10-21

  8. Anthropic Vertex AI configuration librechat:librechat:vertex

    Claude can run through customer Google Vertex AI credentials and regions.

    Project and region configuration · documented · Source date not stated · Retrieved 2026-10-21

  9. Model specifications librechat:librechat:modelspec

    Administrators can enforce configured model presets and defaults; available endpoints still depend on customer credentials.

    enforce; preset; modelSelect; addedEndpoints · documented · Source date not stated · Retrieved 2026-10-21

  10. Agents librechat:librechat:agents

    Agents combine instructions, models, files, tools, skills and sharing permissions, with visible execution and configurable approval.

    Builder; Capabilities; Version history; Sharing; Activity; tool approval · documented · Source date not stated · Retrieved 2026-10-21

  11. OCR for documents librechat:librechat:ocr

    OCR can augment text extraction, or files can be sent to compatible provider APIs; format and model limitations remain.

    File Context; Upload as Text; Optional OCR; Limitations · documented · Source date not stated · Retrieved 2026-10-21

  12. LibreChat v0.8.8 release librechat:librechat:releases

    The stable release documents agent controls, current model updates and explicitly experimental schedules/workspaces and beta Agents API.

    Highlights, 2026-10-01 · documented · Source date 2026-10-01 · Retrieved 2026-10-21

  13. Your first chat librechat:librechat:firstchat

    LibreChat ships without a model key; the public demo is for evaluation rather than private or durable data.

    Software you host yourself; endpoint credentials; public demo · documented · Source date not stated · Retrieved 2026-10-21

  14. Code Interpreter API librechat:librechat:code

    A separate code execution service supports multiple languages and downloadable generated files; stateful/attached modes are experimental.

    Setup; self-hosted service; workspace permissions; generated files · documented · Source date not stated · Retrieved 2026-10-21

  15. LibreChat v0.8.8 MIT licence librechat:librechat:license

    The pinned repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer.

    LICENSE, permission grant and notice requirement · documented · Source date not stated · Retrieved 2026-10-21

  16. RAG API configuration librechat:librechat:ragcfg

    OpenAI, Hugging Face and Ollama embedding configurations are documented; image choice affects local embedding support.

    Embedding providers; lite image; full image · documented · Source date not stated · Retrieved 2026-10-21

  17. Quotas and overages gemini-enterprise:gemini-enterprise:g-quotas

    Seat-based quotas are pooled per edition/project/location, while partner-model tokens and overages are billed separately.

    Feature and edition-based quotas; Standard and Plus table; Claude pricing · documented · Source date 2026-10-15 · Retrieved 2026-10-21

  18. Overview of overages and spend controls gemini-enterprise:gemini-enterprise:g-budget

    Invoiced non-trial projects can cap eligible project spending; enforcement can lag by minutes and blocks the exhausted feature.

    Cap costs with a project spend limit; End-user experience · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  19. Gemini Enterprise release notes gemini-enterprise:gemini-enterprise:r4-single-user-quotas

    Optional single-user quota multipliers are generally available for Standard, Plus and Standard Emerging Market editions; they operate within the shared edition/location pool.

    October 22, 2026: Single-user quota limits · documented · Source date 2026-10-22 · Retrieved 2026-10-26

  20. Gemini Enterprise quotas and overages gemini-enterprise:gemini-enterprise:r4-single-user-enforcement

    Single-user limits restrict the exhausted feature for that user while leaving other users and features available. Overages alter the exhaustion behavior; AI developer tools are excluded from the user quota multiplier.

    Single-user quota limits · documented · Source date not stated · Retrieved 2026-10-26

  21. Granular access control librechat:librechat:access

    Roles, groups and resource ACLs govern features and sharing, with Entra groups synchronized at sign-in.

    Feature permissions; Resource ACLs; System grants; Groups · documented · Source date not stated · Retrieved 2026-10-21

  22. LibreChat Admin Panel librechat:librechat:admin

    A separate browser management panel is available for testing and uses the underlying LibreChat admin APIs.

    Status Preview; separate service; admin APIs · documented · Source date not stated · Retrieved 2026-10-21

  23. Balance configuration librechat:librechat:balance

    Optional token-credit balances initialize and refill user credits; tracking is disabled by default.

    enabled; startBalance; refill configuration · documented · Source date not stated · Retrieved 2026-10-21

  24. Automated moderation librechat:librechat:mod

    Moderation scores abusive login/registration/message activity and may ban users; it is not a documented content DLP classifier.

    Violation scoring and limits · documented · Source date not stated · Retrieved 2026-10-21

  25. LibreChat balance admission implementation librechat:librechat:balance-pin

    The pinned middleware reserves user credits and throws a TOKEN_BALANCE error when the reservation cannot be admitted.

    packages/api/src/middleware/checkBalance.ts, checkBalance · source-inspected · Source date not stated · Retrieved 2026-10-21
    Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path packages/api/src/middleware/checkBalance.ts

  26. Introduction to connectors and data stores gemini-enterprise:gemini-enterprise:g-connect-overview

    Ingestion copies entities and permissions; full and incremental syncs differ in their handling of identities and deletion.

    Data store regions; Sync types; Sync schedules · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  27. RAG API librechat:librechat:rag

    A separate RAG API indexes uploaded content in PostgreSQL/PGVector for retrieval.

    Architecture; document indexing; embeddings; semantic search · documented · Source date not stated · Retrieved 2026-10-21

  28. Upload files as text librechat:librechat:text

    Text upload injects extracted file content rather than relying only on vector retrieval.

    Full text extraction and context · documented · Source date not stated · Retrieved 2026-10-21

  29. File configuration librechat:librechat:filecfg

    File limits and formats are configurable by endpoint and file processing route.

    File limits; MIME patterns; provider routes · documented · Source date not stated · Retrieved 2026-10-21

  30. LibreChat spreadsheet text parser librechat:librechat:r4-spreadsheet-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.

    getParserForMimeType; excelSheetToText, lines 109-129 · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
    Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/files/documents/crud.ts

  31. LibreChat current Upload as Text guide librechat:librechat:r4-text-current

    The development guide lists XLSX/XLS/ODS parsing up to 15 MB and token-bounded text injection, not a formatted spreadsheet editor.

    Built-in parser; supported documents; truncation · documented · Source date not stated · Retrieved 2026-10-26

  32. Compare editions of Gemini Enterprise gemini-enterprise:gemini-enterprise:g-editions

    Business has a 1–500 seat range and a limited connector set; Standard and Plus include the full connector ecosystem and differ in pooled storage.

    Compare features, Seats and Storage rows · documented · Source date 2026-10-16 · Retrieved 2026-10-21

  33. Create and manage projects gemini-enterprise:gemini-enterprise:g-projects

    Projects hold up to 50 files/links; linked sources preserve source ACLs, local uploads are shared with all project members and chats stay private.

    Limitations; Manage project knowledge; Chat with assistant · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  34. Create a chat agent gemini-enterprise:gemini-enterprise:g-agents

    Users configure custom chat-agent instructions, uploaded knowledge and connected tools in Workflow Builder.

    Instructions; Knowledge; Tools; publishing steps · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  35. Projects librechat:librechat:projects

    Projects persist files and instructions across a user’s chats but cannot be shared or transferred.

    Availability; personal scope; files and instructions · documented · Source date not stated · Retrieved 2026-10-21

  36. Connect a third-party data source gemini-enterprise:gemini-enterprise:g-connectors

    Google distinguishes GA connectors from public-preview sources and warns that federated queries reach third-party systems under their terms.

    Sources by launch stage; federated-query warning · documented · Source date 2026-10-15 · Retrieved 2026-10-21

  37. Introduction to self-hosted data sources gemini-enterprise:gemini-enterprise:g-selfhosted-data

    Private Service Connect connects the Google-managed platform to customer-hosted sources, without establishing a self-hosted assistant.

    Access patterns; Private Service Connect · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  38. SharePoint and OneDrive integration librechat:librechat:sharepoint

    The Microsoft file picker uses Entra token reuse and delegated on-behalf-of downloads to attach files.

    Prerequisites; delegated permissions; admin consent · documented · Source date not stated · Retrieved 2026-10-21

  39. MCP librechat:librechat:mcp

    MCP servers can be configured through YAML or the permission-gated UI, including per-user OAuth.

    YAML/UI setup; authentication; ownership and selection · documented · Source date not stated · Retrieved 2026-10-21

  40. MCP server configuration librechat:librechat:mcpcfg

    Configuration includes stdio, SSE and Streamable HTTP transports and server-specific credentials.

    Transport examples; headers; OAuth · documented · Source date not stated · Retrieved 2026-10-21

  41. Protect sensitive data in sources gemini-enterprise:gemini-enterprise:g-dlp

    Sensitive Data Protection can block source ingestion/uploads and inspect Microsoft/Workspace labels, excluding Business and audio/video scans.

    Supported editions and regions; inbound data; Metadata labels · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  42. LibreChat Docker service configuration librechat:librechat:compose-pin

    The pinned example runs a MongoDB primary store and a separate PGVector/RAG service with customer-mounted data.

    docker-compose.yml, api/mongodb/vectordb/rag_api services · source-inspected · Source date not stated · Retrieved 2026-10-21
    Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path docker-compose.yml

  43. Configure personalization and memory gemini-enterprise:gemini-enterprise:g-personalization

    Users can manage saved memories and connected sources; admins can disable memory and profiles across an app.

    Data control; Save information as memories; Turn off personalization and memory · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  44. User memory librechat:librechat:memory

    Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats.

    Key/value store; controls; disabled by default · documented · Source date not stated · Retrieved 2026-10-21

  45. Workflow Builder overview gemini-enterprise:gemini-enterprise:g-workflow

    Workflow Builder provides no-code/low-code chat agents and multi-step workflows with sources, tools, publishing and sharing.

    Capabilities; Agent types · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  46. Get started with using the Gemini Enterprise app gemini-enterprise:gemini-enterprise:g-start

    The app guide identifies web/mobile access, shared skills, agent sharing and role-based use-case guides.

    Choose your app experience; Share and collaborate · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  47. Use assistant actions gemini-enterprise:gemini-enterprise:g-actions

    Users authorize each connector to act through their own account after an administrator enables actions.

    Authorize your connected services; supported service actions · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  48. Set up your custom MCP server gemini-enterprise:gemini-enterprise:g-mcp

    Administrators configure remote MCP servers, OAuth and Cloud Run service-agent authentication; the route is not a local desktop MCP client.

    Limitations; authentication; data-store configuration · documented · Source date 2026-10-19 · Retrieved 2026-10-21

  49. Image generation and editing librechat:librechat:images

    Agents can use configured image tools for generation/editing; provider credentials and model parameters are separate.

    OpenAI Image Tools; provider setup; admin configuration · documented · Source date not stated · Retrieved 2026-10-21

  50. Deep Research gemini-enterprise:gemini-enterprise:g-research

    Deep Research plans multiple searches over enterprise indexes and optionally the web, then produces a cited report.

    Research sources; generated reports and citations · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  51. Configure the assistant gemini-enterprise:gemini-enterprise:g-configure

    Admins can set assistant instructions, block phrases, select grounding and choose chat retention of 1 to 180 days, default 60.

    Additional LLM system instructions; web grounding; banned phrases; retention · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  52. Web search librechat:librechat:web

    Search can use Serper, SearXNG, Tavily or Keenable, with independently configured scraping and optional reranking.

    Provider, scraper and reranker configuration · documented · Source date not stated · Retrieved 2026-10-21

  53. Schedule chat agent executions gemini-enterprise:gemini-enterprise:g-schedule

    Non-workflow chat agents can run recurring personal tasks, but credentials need manual renewal every 14 days and other-person actions are constrained.

    Schedule and refresh; Limitations; View and approve scheduled runs · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  54. Scheduled Chats librechat:librechat:schedule

    Opt-in experimental schedules execute saved Agents with cron/time zones and recheck access and balance before running.

    Experimental and disabled by default; runtime and permissions · documented · Source date not stated · Retrieved 2026-10-21

  55. Agents API beta librechat:librechat:api

    The beta API exposes chat/Responses inference, Agent/Skill management and authenticated event delivery.

    Inference; management; Agent Events; authentication · documented · Source date not stated · Retrieved 2026-10-21

  56. Gemini Enterprise audit logging gemini-enterprise:gemini-enterprise:g-audit

    Cloud Audit Logs documents method-level administrative and data-access event categories for Discovery Engine.

    Audited methods and permission types · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  57. Gemini Enterprise REST reference gemini-enterprise:gemini-enterprise:g-api

    The REST reference lists assistant, agent, search and data-store methods with machine-readable API definitions.

    Discovery Engine service; assistants, agents, dataStores documents and sessions resources · documented · Source date 2026-10-09 · Retrieved 2026-10-21

  58. Authenticate to Gemini Enterprise API gemini-enterprise:gemini-enterprise:g-api-auth

    API authentication is documented using Google Cloud identity, credentials and supported client libraries.

    Authentication options; client libraries · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  59. Create and edit documents and slides in Canvas gemini-enterprise:gemini-enterprise:g-canvas

    The web-only Canvas exports documents as DOCX/PDF and slides as PPTX/PDF, with manual and instructed editing.

    Editing; export; Limitations · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  60. Configure the mobile app gemini-enterprise:gemini-enterprise:g-mobile

    The mobile app supports Google/third-party identities and administrator distribution through MDM, QR codes or links.

    Before you begin; MDM; third-party identity provider configuration · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  61. Temporary chat and data retention librechat:librechat:retention

    Operators configure expiry for chats/messages/files/shared links; normal chats do not expire by default and memories are excluded.

    Default 30-day temporary retention; all/ephemeral; deadlines; memories · documented · Source date not stated · Retrieved 2026-10-21

  62. Admin Insights librechat:librechat:insights

    Insights reports persisted MongoDB activity and identifiable recent conversations; it is not monetary billing analytics.

    Opt-in; capabilities; metrics; tenant scope · documented · Source date not stated · Retrieved 2026-10-21

  63. Docker installation librechat:librechat:local

    Docker self-installation runs LibreChat with its configured service dependencies.

    Installation; configuration; updating · documented · Source date not stated · Retrieved 2026-10-21

  64. Google Workspace admin controls for Gemini Enterprise gemini-enterprise:gemini-enterprise:r5-workspace-agent-access

    Enabled users can use Gemini Enterprise agents in a side panel, the Enterprise assistant and CLI. Enterprise licences are separate from Workspace subscriptions; service and data access are separately controlled. Exact per-editor coverage is not listed.

    Get licenses; side panel; service status; Workspace data access · documented · Source date not stated · Retrieved 2026-10-26

  65. Official Gemini Enterprise Workspace add-on codelab gemini-enterprise:gemini-enterprise:r5-workspace-custom-addon

    Google demonstrates a customer-built Apps Script add-on invoking the Enterprise StreamAssist API inside Gmail and Chat with message context. Docs/Sheets/Slides are extension targets. Standard/Plus, a billed Cloud project, Workspace Business/Enterprise and permissions are prerequisites; sample code requires production hardening.

    Prerequisites; default agent as Google Workspace add-on; StreamAssist; deploy to Gmail and Chat · documented · Source date not stated · Retrieved 2026-10-26

  66. Google Gemini Enterprise and Gemini app scope gemini-enterprise:gemini-enterprise:r5-offer-boundaries

    Gemini Enterprise app is separately licensed; the Gemini app included with Workspace and Agent Platform are distinct offers. Their names do not establish that all Workspace editor features are included in the Enterprise app subscription.

    Gemini app differences; Agent Platform separate purchase · documented · Source date not stated · Retrieved 2026-10-26

  67. Gemini Enterprise Canvas tone and editing scope gemini-enterprise:gemini-enterprise:r5-canvas-tone

    Canvas offers Change tone/length and selected-text instructions. Editing applies to generated content in the active session; exporting DOCX/PDF is not a documented layout-preserving translation engine or corporate glossary.

    Edit a document; export; limitations · documented · Source date not stated · Retrieved 2026-10-26

  68. Cloud Translation Advanced document translation gemini-enterprise:gemini-enterprise:r5-translation-separate-api

    A separate Cloud Translation Advanced API documents formatted-document translation and glossary parameters. It needs enabled APIs, authenticated project access and relevant storage/IAM; no included Enterprise-app feature or engine relationship is established.

    API setup; translate documents; use AutoML or a glossary · documented · Source date not stated · Retrieved 2026-10-26

  69. Google Cloud service specific terms gemini-enterprise:gemini-enterprise:g-terms

    The contract restricts Google model training without customer instruction and states separate terms for third-party offerings.

    AI/ML Services Training Restriction; Generated Output; Grounding with Google Search · documented · Source date not stated · Retrieved 2026-10-21

  70. Use the mobile app gemini-enterprise:gemini-enterprise:g-use-mobile

    Mobile users can dictate and play spoken answers; prompt audio is described as ephemeral.

    Voice; Speech to Text; Text to Speech · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  71. Speech configuration librechat:librechat:speech

    Administrators configure audio provider engines and models separately from text generation.

    Speech-to-text and text-to-speech engines · documented · Source date not stated · Retrieved 2026-10-21

  72. LibreChat conversation-mode speech settings librechat:librechat:speech-conversation-r2

    Conversation mode chains transcription, auto-send and TTS playback for hands-free turns after microphone activation; engines and audio routing are separately configured.

    Speech Tab: conversationMode, autoTranscribeAudio, autoSendText, automaticPlayback; engine and allowedAddresses settings · documented · Source date not stated · Retrieved 2026-10-21

  73. Artifacts librechat:librechat:artifacts

    Artifacts render generated React, HTML and Mermaid content in the chat interface.

    React, HTML and Mermaid previews · documented · Source date not stated · Retrieved 2026-10-21

  74. Share your conversations gemini-enterprise:gemini-enterprise:g-share

    A share link exposes the existing prompts, answers and generated content to permitted recipients, including sensitive content.

    Important warning; Create link; View shared conversations · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  75. Shareable links librechat:librechat:share

    Shared links publish a transcript branch and optional file snapshots independently of the owner’s live file ACL.

    Authentication defaults; file snapshots; continuation · documented · Source date not stated · Retrieved 2026-10-21

  76. LibreChat locale registration librechat:librechat:i18n-pin

    The pinned client registers English, German, French and Italian translations among its supported locales.

    client/src/locales/i18n.ts, language resources · source-inspected · Source date not stated · Retrieved 2026-10-21
    Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path client/src/locales/i18n.ts

  77. Configure identity provider gemini-enterprise:gemini-enterprise:g-identity

    Identity can use Google or a SAML/OIDC provider through federation; SCIM/group mapping has documented sharing and source-access roles.

    Google Identity; Workforce Identity Federation; Entra/Okta SCIM · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  78. Authentication system librechat:librechat:auth

    Local/LDAP accounts can be required to use TOTP; federated MFA belongs to the identity provider and account creation/deletion scripts are documented.

    Required two-factor authentication; Registration; User scripts · documented · Source date not stated · Retrieved 2026-10-21

  79. OAuth2 and OIDC librechat:librechat:openid

    LibreChat documents OAuth2/OIDC providers including Microsoft Entra, Google, Keycloak and Auth0.

    Supported providers; setup · documented · Source date not stated · Retrieved 2026-10-21

  80. SAML authentication librechat:librechat:saml

    SAML is a documented authentication option for the self-hosted application.

    Overview and requirements · documented · Source date not stated · Retrieved 2026-10-21

  81. Azure Entra authentication librechat:librechat:entra

    Entra OIDC supports group-based admission and Graph integration using configured scopes and token reuse.

    Group claims; token reuse; Microsoft Graph integration · documented · Source date not stated · Retrieved 2026-10-21

  82. Get subscriptions and assign licenses gemini-enterprise:gemini-enterprise:g-license-details

    Seats can be assigned manually or on first access; console purchase limits depend on billing account type and cancellation disables renewal.

    Subscription seat quantity limits; auto-assignment; cancel a subscription · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  83. Access control with IAM gemini-enterprise:gemini-enterprise:g-access-control

    IAM defines administrators, users and granular permissions at project/app boundaries.

    Gemini Enterprise Admin/User roles; app-level access · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  84. View and export analytics data gemini-enterprise:gemini-enterprise:g-analytics

    Analytics exposes app adoption and agent metrics, BigQuery export and allowlisted identifiable user-level reporting.

    Adoption; Usage and Quality; Agent; User Level; export · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  85. Token usage librechat:librechat:tokens

    Usage and estimated costs use recorded tokens and configured provider rates; transactions are distinct from balance enforcement.

    Context cost; transactions; per-endpoint token rates · documented · Source date not stated · Retrieved 2026-10-21

  86. View costs gemini-enterprise:gemini-enterprise:g-costs

    The 30-day billing summary covers overage/PAYG consumption and explicitly excludes seat subscription charges.

    Billing tab; Before you begin · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  87. Access Gemini Enterprise usage audit logs with Cloud Logging gemini-enterprise:gemini-enterprise:g-usage-logs

    Prompt/response content logging is configurable, and log routing plus field-level restrictions are documented.

    Logged information; Control access to logs · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  88. Logging librechat:librechat: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.

    Error/debug logs; rotation; external tools · documented · Source date not stated · Retrieved 2026-10-21

  89. Enable Model Armor in Gemini Enterprise gemini-enterprise:gemini-enterprise:g-armor

    Model Armor can inspect/block prompts and responses but explicitly does not mask or alter PII in this integration.

    Inspect and block vs Inspect only; PII; templates; logging · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  90. Set up Gemini Enterprise as an administrator gemini-enterprise:gemini-enterprise:g-admin-setup-correction

    The setup summary mentions redaction, whereas its linked integration guide expressly excludes PII masking; effective redaction is not established.

    Enable Model Armor safety controls; linked Model Armor integration guide · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  91. LibreChat development content-filter configuration librechat:librechat:r4-content-filter

    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.

    Source-Aware Filters; Pattern Configuration; Redaction; File Fields · documented · Source date not stated · Retrieved 2026-10-26

  92. LibreChat content-inspection runtime librechat:librechat:r4-pii-runtime

    Source-aware configured inspection executes in the LibreChat API. Missing policy disables that scope; configured actions and fields bound inspection.

    createConfiguredContentInspector; source rule configuration · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
    Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/runtime.ts

  93. LibreChat pattern detector librechat:librechat:r4-patterns

    Default starter patterns detect credential-shaped tokens/headers. Operator custom patterns use bounded regular expressions; a generic comprehensive PII classifier is not established.

    STARTER_PATTERNS; configured RE2JS rules · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
    Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/detectors/pattern.ts

  94. LibreChat private text submission librechat:librechat:r4-private-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.

    createPrivateTextIngress; fresh Agent text and clientRequestId checks · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
    Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/private/submission.ts

  95. LibreChat API content-filter middleware librechat:librechat:r4-filter-middleware

    The server middleware applies configured inspection and rejects blocked/uninspectable requests with HTTP 400. No deployment or detection fixture was run.

    createMessageFilterPii; contentFilterBlockResponse; uninspectable response · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
    Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/middleware/messageFilterPii.ts

  96. LibreChat config v1.3.18 changelog librechat:librechat:r4-config-1318

    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.

    October 22, 2026; opt-in PII redaction; retention mode · documented · Source date 2026-10-22 · Retrieved 2026-10-26

  97. Interface configuration librechat:librechat:interface

    Administrators configure UI feature permissions and usage terms in the self-hosted deployment.

    Feature permissions; custom welcome and terms · documented · Source date not stated · Retrieved 2026-10-21

  98. Remote hosting librechat:librechat:remote

    The application can be deployed on customer-selected remote servers with operator-managed security.

    Hosting options; security considerations · documented · Source date not stated · Retrieved 2026-10-21

  99. Gemini Enterprise security overview gemini-enterprise:gemini-enterprise:g-security

    The security overview documents managed Cloud security controls and a user-requested deletion window, distinct from on-premise deployment.

    End user security; data security; compliance · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  100. LibreChat Demo terms librechat:librechat:demo

    The free hosted Demo is offered as-is with possible data cleanups and no durable business-service guarantee.

    Evaluation scope; retention; disclaimer · documented · Source date 2026-03-12 · Retrieved 2026-10-21

  101. Organize your conversations gemini-enterprise:gemini-enterprise:g-organize

    Users can remove chats from their lists; this does not establish immediate deletion of all backend copies.

    Manage chats; delete and retention · documented · Source date 2026-10-14 · Retrieved 2026-10-21

  102. Cloud Data Processing Addendum gemini-enterprise:gemini-enterprise:g-dpa

    The CDPA covers GDPR and Swiss FADP, data return/deletion and subprocessor/transfer obligations.

    General Terms 6 and 11; European Data Protection Law terms · documented · Source date not stated · Retrieved 2026-10-21

  103. Personal settings librechat:librechat:settings

    Users configure interface language, audio and personal data controls.

    Language; speech; data controls · documented · Source date not stated · Retrieved 2026-10-21

  104. Google Cloud subprocessors gemini-enterprise:gemini-enterprise:g-subprocessors

    The public subprocessor list includes international technical-support processing, which is separate from selected storage regions.

    Google Cloud Platform; technical support locations · documented · Source date not stated · Retrieved 2026-10-21

  105. ClickHouse acquisition of LibreChat librechat:librechat:owner

    ClickHouse announced the acquisition of LibreChat and that Danny Avila and the team joined ClickHouse.

    Announcement, November 4, 2025 · documented · Source date 2025-11-04 · Retrieved 2026-10-21

  106. Compliance certifications and security controls gemini-enterprise:gemini-enterprise:g-compliance

    Google lists compliance programs for relevant editions and exceptions, but this page does not supply issuer, report period or validity.

    Certifications; product-scope instructions; Security controls · vendor-claimed · Source date 2026-10-14 · Retrieved 2026-10-21

  107. Google Cloud Compliance Reports Manager gemini-enterprise:gemini-enterprise:r4-compliance-reports

    Google provides on-demand ISO certificates and SOC reports without additional cost; selected resources require a Google Cloud or Workspace sign-in and confidential documents remain subject to customer-agreement confidentiality.

    Compliance Reports Manager access and confidentiality · documented · Source date not stated · Retrieved 2026-10-26

  108. Gemini Enterprise compliance and security controls gemini-enterprise:gemini-enterprise:r4-compliance-scope

    Standard/Plus Agentic AI Service scope is distinguished from Notebook and developer-tool exceptions. Listing a compliance program is not verification of a current certificate/report.

    Certifications; AlphaEvolve and Antigravity limitations · documented · Source date not stated · Retrieved 2026-10-26

  109. Customer-managed encryption keys gemini-enterprise:gemini-enterprise:g-encryption

    CMEK, EKM/HSM and regional limitations are documented; a key option does not make all tools residency compliant.

    Supported locations; limitations; external key management · documented · Source date 2026-10-15 · Retrieved 2026-10-21

  110. LibreChat website privacy policy librechat:librechat:siteprivacy

    Website, demo and self-hosted software are distinct privacy scopes; website terms do not establish a customer deployment DPA.

    Scope and exclusions · documented · Source date not stated · Retrieved 2026-10-21

  111. LibreChat v0.8.8 message storage schema librechat:librechat:secrecy-message-pin

    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.

    packages/data-schemas/src/schema/message.ts, text at lines 55-58 and content at lines 139-143 · source-inspected · Source date not stated · Retrieved 2026-10-21
    Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path packages/data-schemas/src/schema/message.ts

  112. LibreChat Demo privacy policy librechat:librechat:secrecy-demo-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.

    Scope; section 4 Third-Party AI Model Providers; section 6 Data Sharing and Sub-Processors · documented · Source date 2026-03-12 · Retrieved 2026-10-21

  113. Gemini Enterprise Business edition gemini-enterprise:gemini-enterprise:g-business

    Business advertises a starting seat price and 30-day trial, with a separate connector/admin package.

    Starting price; FAQs on trial, security and admin controls · vendor-claimed · Source date not stated · Retrieved 2026-10-21

  114. ECB historical euro foreign exchange reference rates gemini-enterprise:gemini-enterprise:fx-ecb-2026-10-20

    The October 20 reference rates are EUR 1 = USD 1.1215 = CHF 0.9237. Unknown Gemini licence totals are not converted.

    Cube time=2026-10-20; USD and CHF reference rates · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  115. Gemini Enterprise app FAQ gemini-enterprise:gemini-enterprise:r4-pricing-gap

    The FAQ directs purchase of Standard, Plus and Frontline to Google Cloud sales without a public base price. Business and the standalone Notebook purchase/trial routes are separate.

    Access and purchase of Standard, Plus and Frontline; business trial · documented · Source date not stated · Retrieved 2026-10-26

  116. Azure Retail Prices, Switzerland North Linux VMs librechat:librechat:cost-vm

    EUR hourly PAYG rates retrieved 2026-10-21 are 0.2226, 0.4453 and 0.8905 for D4s, D8s and D16s v5 respectively.

    Consumption; Virtual Machines Dsv5 Series; Standard_D4s_v5/D8s_v5/D16s_v5 · documented · Source date not stated · Retrieved 2026-10-21

  117. Azure Retail Prices, PostgreSQL Flexible Server librechat:librechat:cost-pg

    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.

    General Purpose Ddsv5 Series Compute, 2/4/8 vCore; Flex Server Storage · documented · Source date not stated · Retrieved 2026-10-21

  118. ECB euro reference rate history librechat:librechat:cost-fx

    The 2026-10-20 reference rates are EUR 1 = USD 1.1215 and CHF 0.9237.

    Cube time=2026-10-20; USD and CHF · documented · Source date 2026-10-20 · Retrieved 2026-10-21

  119. OpenAI API pricing librechat:librechat:cost-model

    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.

    Standard, short-context gpt-6-luna row · documented · Source date not stated · Retrieved 2026-10-21

  120. GPT-6 Luna model documentation librechat:librechat:cost-effort

    The model accepts reasoning effort none, the lowest documented effort, and lists the same standard text-token rates.

    Reasoning effort and text-token pricing · documented · Source date not stated · Retrieved 2026-10-21

  121. Gemini for business product page gemini-enterprise:gemini-enterprise:g-pricing

    The top-level universal-agent marketing page says several capabilities and third-party choice are early access; it is broader than the current Enterprise app docs.

    FAQ: models; evaluation; early-access disclosure · vendor-claimed · Source date not stated · Retrieved 2026-10-21

  122. Google Cloud terms of service gemini-enterprise:gemini-enterprise:g-terms-main

    The hosted service is supplied under commercial Cloud terms; these terms do not license the platform for self-hosting.

    Intellectual Property Rights; licence and service terms · documented · Source date not stated · Retrieved 2026-10-21

  123. LibreChat conversation export implementation librechat:librechat:export-pin

    The pinned user conversation exporter supports JSON, CSV, Markdown and text, plus screenshot export.

    client/src/hooks/Conversations/useExportConversation.ts, export dispatch · source-inspected · Source date not stated · Retrieved 2026-10-21
    Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path client/src/hooks/Conversations/useExportConversation.ts

  124. Google Cloud Customer Care gemini-enterprise:gemini-enterprise:g-support

    Support is packaged in separate Customer Care tiers; the retrieved page does not establish a Gemini-specific local-language SLA.

    Basic, Standard, Enhanced and Premium support · documented · Source date not stated · Retrieved 2026-10-21

  125. Google Cloud Service Health gemini-enterprise:gemini-enterprise:g-status

    Google publishes Cloud service health and dated incident information; this is not itself a Gemini Enterprise uptime commitment.

    Service status and incident history · documented · Source date not stated · Retrieved 2026-10-21