Agent-readable comparison

LibreChat vs onAI

Name: LibreChat vs onAI: agent-readable comparison
Creator: onAI

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 16 criteria with sourced findings for both products, including 14 that a second agent cross-checked for both. 48 criteria have a sourced finding for at least one product, and 44 carry a statement by onAI. "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.

LibreChat source checks: 2026-10-21 to 2026-10-26. Website: https://www.librechat.ai
onAI source checks: 2026-10-21 to 2026-10-26. Website: https://onaihq.com/
Generated 2026-10-27; next source check due 2026-12-20.

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.

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

onAI

Agent cross-checked Support: partial

The public page offers user-selectable Claude, GPT, Gemini, Grok and Mistral families. Exact chat model versions, automatic routing and per-model input capabilities are not established.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat and Flat price public offers; exact model entitlements unspecified; add_ons=none stated; deployment_mode=not specified; region=Unspecified by source; os=not specified.

Limitations

Model-family marketing is not a tested model inventory or a release-lag measurement.

providers Which model providers are available? [supported]: The vendor names Anthropic, OpenAI, Google, xAI and Mistral AI model families; current selectable provider inventory was not observed. Sources: onai:public-models-display-20261026.
current_models Which current models are selectable on this plan? [partial]: The page names Claude, GPT, Gemini, Grok and Mistral families, but supplies no complete versioned chat-model list per plan. Sources: onai:public-models-display-20261026.
user_choice Can users pick the model per chat? [supported]: Employees choose a model for a task within the administrator-approved set. Sources: onai:public-models-display-20261026.
auto_routing Does the product route between models automatically, and is the chosen model shown? [unknown]: The public model section does not establish automatic routing or disclosure of its selected model; no app fixture was run.
multimodal_input Which models accept images, audio or files? [unknown]: Public chat-model copy does not map image, audio or file input to named model versions. Image Studio is a separate capability.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:public-models-display-20261026.

MOD-02 Model freshness

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

LibreChat

Agent cross-checked Support: partial

Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown.

Limitations

release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control.

release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
changelog Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases.
deprecation_notice How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
version_pinning Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

We enable new models shortly after their release.

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

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

LibreChat

Agent cross-checked Support: partial

Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented.

Limitations

byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established.

own_api_keys Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom.
own_cloud_contract Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex.
custom_endpoint Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom.
byo_pricing Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat.
byo_restrictions Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Your own provider contracts and API keys (for example Azure, OpenRouter) are possible on request.

MOD-04 Local and self-hosted models

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

LibreChat

Agent cross-checked Support: partial

Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack.

Limitations

feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run.
vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project.

self_hosted_chat Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom.
self_hosted_embeddings Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg.
feature_parity Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code.
vendor_hosted_open_models Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

With on-premises, local models can be connected (for example via Ollama).

MOD-05 Model control and usage limits

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

LibreChat

Agent cross-checked Support: partial

Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism.

Limitations

model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run.
data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides.
user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance.

model_allowlist_by_group Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access.
data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides.
default_model Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec.
user_limits What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod.
limit_behaviour What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-22

Admins decide per group which models are allowed.

Company knowledge

KNOW-01 Files in chat

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

LibreChat

Agent cross-checked Support: partial

Files can be indexed, injected as extracted text or sent directly to compatible model providers.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

File counts, sizes and provider acceptance depend on deployment settings.
Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested.

formats Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg.
limits What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr.
ocr Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr.
spreadsheets Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current.
full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Upload PDF, Word, Excel and other files directly in the chat and ask about them.

KNOW-02 Knowledge bases and shared collections

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

LibreChat

Agent cross-checked Support: partial

Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership.

Limitations

sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred.
size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent.

persistent_collections Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects.
sharing_scope Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects.
size_limits What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent.
assistant_binding Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Shared knowledge collections with access rights per group.

KNOW-03 Enterprise connectors

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

LibreChat

Agent cross-checked Support: partial

SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors.

Limitations

microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established.
google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint.
google_workspace Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
atlassian Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
other_systems Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
on_prem_sources Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg.
connector_provider Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp.

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

onAI

Agent cross-checked Support: partial

The vendor describes live Microsoft 365 access with specific delegated permissions. Other connector names are marketing leads with incomplete source and plan scope.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Microsoft 365 listed in Per seat and Flat price; optional Microsoft licences/permissions apply; add_ons=Optional existing Microsoft 365 Copilot licence for semantic search and meeting notes; deployment_mode=not specified; region=Source tenant region and model processing region depend on customer configuration; os=not specified.

Limitations

Microsoft 365 claims are vendor statements, not an observed tenant connection. Generic connector examples are not individually verified integrations.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: The page lists SharePoint/OneDrive files, SharePoint pages/lists, Outlook mail/attachments, calendar, Teams chats, OneNote, To Do/Planner and directory. Channels and meeting transcripts require additional admin approval; semantic Copilot search/meeting notes require eligible Microsoft 365 Copilot licences. Sources: onai:public-m365-display-20261026, onai:public-m365-permissions-display-20261026.
google_workspace Which Google sources are connected? [unknown]: The page’s Google sign-in is not a Google Drive/Gmail connector specification. No scoped Google Workspace data connector or trial was verified.
atlassian Confluence and Jira? [partial]: The FAQ names Confluence as a standard-connector example without setup, plan or permission details. Jira availability is not established. Sources: onai:public-other-connectors-display-20261026.
other_systems Which other business systems? [partial]: The FAQ names S3 and proprietary data sources through connectors or an API. No source-by-source catalogue for Notion, Box, Salesforce or ServiceNow was obtained. Sources: onai:public-other-connectors-display-20261026.
on_prem_sources Can on-prem file shares or databases be connected? [unknown]: Custom database and on-premises hosting copy does not establish an operational file-share/database connector, network gateway or associated plan requirements.
connector_provider Who builds and maintains each connector? [partial]: onAI says its Microsoft app supplies the Microsoft 365 connection and IT approves delegated permissions; no provider/maintenance contract is specified for the other example connectors. Sources: onai:public-m365-permissions-display-20261026.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:public-m365-display-20261026, onai:public-m365-permissions-display-20261026, onai:public-other-connectors-display-20261026.

KNOW-04 Permission-aware retrieval

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

LibreChat

Agent cross-checked Support: partial

Product resource ACLs and delegated Microsoft file selection are documented. Continuing source permissions for copied content remain untested.

Limitations

source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
enforcement_point: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established.
revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
admin_scope_controls: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established.
sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.

source_permissions_respected Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [partial]: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. Sources: librechat:librechat:access, librechat:librechat:sharepoint.
revocation_delay How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
admin_scope_controls Can admins exclude sites, folders or labels? [partial]: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. Sources: librechat:librechat:access, librechat:librechat:agents.
sensitivity_labels Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.

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

onAI

Agent cross-checked Support: partial

For Microsoft 365 the vendor claims per-user source permission checks at query time. Revocation delay, site exclusions and sensitivity-label behavior have not been tested.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat; Flat price includes everything in Per seat. Microsoft 365 connector consent and source-account access required.; add_ons=Customer Microsoft account and required delegated consent; deployment_mode=not specified; region=Customer Microsoft tenant; receiving model region configured separately; os=not specified.

Limitations

Scope is the live Microsoft 365 connector. Native knowledge collection ACLs and copied/shared answers require separate checks.
Public pricing explicitly includes Microsoft 365 in Per seat and inherits it in Flat price. This establishes advertised plan scope, not a completed permission or deletion-propagation fixture.

source_permissions_respected Are source permissions enforced per user? [supported]: The vendor says onAI makes delegated read-only requests as the signed-in user and Microsoft checks that person’s source access. No two-user restricted-folder fixture was run. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [supported]: Microsoft is the stated enforcement point for live requests; the page says no mirrored Microsoft 365 library index is created. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026.
revocation_delay How quickly does a removed permission take effect? [unknown]: No measured permission-revocation propagation interval is published and no revoke/grant fixture was run.
admin_scope_controls Can admins exclude sites, folders or labels? [unknown]: The page lists optional source permissions and model restrictions but does not establish site/folder/label exclusion controls.
sensitivity_labels Are Microsoft Purview or similar labels respected? [unknown]: No Microsoft Purview sensitivity-label handling specification or label fixture was obtained.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026, onai:review-plan-m365-display-20261026.

KNOW-05 Freshness and sync model

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

LibreChat

Agent cross-checked Support: partial

The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization.

Limitations

sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.

live_or_indexed Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr.
sync_interval How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
deletion_propagation How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
index_location Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin.

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

onAI

Agent cross-checked Support: partial

Microsoft 365 is described as live retrieval without a second library index. Content read into a chat remains in that conversation, and no edit/delete timing was measured.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat; Flat price includes everything in Per seat. Microsoft 365 connector consent and source-account access required.; add_ons=Microsoft delegated connector consent; deployment_mode=not specified; region=Source data in customer Microsoft tenant; chat storage per deployment; os=not specified.

Limitations

This is the Microsoft 365 sync model only. Uploaded knowledge collections use a separate storage/retrieval mechanism.
Public pricing explicitly includes Microsoft 365 in Per seat and inherits it in Flat price. This establishes advertised plan scope, not a completed permission or deletion-propagation fixture.

live_or_indexed Is content searched live or copied into an index? [supported]: The vendor describes live Microsoft 365 reads, no copied library and no background synchronisation. This statement does not cover uploaded knowledge-base documents. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026.
sync_interval How often does an index refresh? [supported]: The described Microsoft 365 route has no library-index sync job; source service search freshness still depends on Microsoft. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026.
deletion_propagation How quickly does a deleted document disappear? [unknown]: No edit/delete fixture was run. The page says material already read stays in the user’s chat, so source deletion cannot be treated as retroactive chat erasure. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026.
index_location Where is indexed content stored? [supported]: No separate onAI Microsoft 365 library index is claimed. Retrieved content is retained in the asking user’s chat; the precise chat-storage country is separately unverified. Sources: onai:public-m365-permissions-display-20261026, onai:review-m365-boundaries-display-20261026.

KNOW-06 Grounding and retrieval quality

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

LibreChat

Agent cross-checked Support: partial

File-search citations are documented; retrieval accuracy remains unmeasured.

Limitations

citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.

citations Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access.
citation_accuracy Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
cross_language Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
no_answer_behaviour Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
observed_accuracy How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.

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

onAI

Agent cross-checked Support: partial

For Per seat and Flat price Microsoft 365 answers, the vendor describes numbered source citations. Grounding accuracy, abstention and cross-language retrieval remain unknown without the shared fixture.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat; Flat price includes everything in Per seat. Microsoft 365 connector consent and source-account access required.; add_ons=Required Microsoft delegated consent and customer source-account access; deployment_mode=not specified; region=Customer Microsoft tenant; receiving model region depends on configuration; os=not specified.

Limitations

This record covers Microsoft 365 source citations on the two named public offers. No observed accuracy, link verification, abstention or cross-language retrieval result is claimed.

citations Are answers linked to specific sources? [supported]: For Microsoft 365 answers included in Per seat and inherited by Flat price, the vendor describes numbered links to the original email, file or chat. The illustrated conversations are examples; citation accuracy was not observed. Sources: onai:review-plan-m365-display-20261026, onai:review-m365-boundaries-display-20261026.
citation_accuracy Do the cited passages support the answer? [unknown]: No fixture or real source-linked answer was checked for passage support or link accuracy.
cross_language Does a question in one language find documents in another? [unknown]: The DE/FR/EN question set was not run against a connected corpus; interface translation does not establish cross-language retrieval quality.
no_answer_behaviour Does it say when the corpus has no answer? [unknown]: No no-answer corpus fixture was run; the public example does not establish reliable abstention.
observed_accuracy How many of the question set were answered correctly? [unknown]: No observed question-set numerator, denominator, model/settings or repeat count is available. No accuracy percentage is invented.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:review-m365-boundaries-display-20261026, onai:review-plan-m365-display-20261026.

KNOW-07 Memory and personal context

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

LibreChat

Agent cross-checked Support: supported

Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions.

custom_instructions Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents.
cross_chat_memory Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory.
user_memory_controls Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory.
admin_memory_controls Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Personal instructions that apply across all chats.

Assistants and agents

AGT-01 Custom assistants

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

LibreChat

Agent cross-checked Support: supported

Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog.

create_assistants Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents.
creator_permissions Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access.
sharing_scope Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access.
catalogue Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents.
prompt_library Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Create your own assistants with instructions and knowledge and share them with your team.

AGT-02 Tools, actions and MCP

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

LibreChat

Agent cross-checked Support: partial

Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised.

builtin_tools Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images.
custom_actions Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents.
mcp_client Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg.
tool_auth Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg.
tool_approval Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Tools and your own API actions (OpenAPI); MCP not yet.

AGT-03 Web search and deep research

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

LibreChat

Agent cross-checked Support: partial

Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary.

Limitations

deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified.

web_search Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents.
admin_toggle Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web.
search_provider Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web.
deep_research Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web.
web_citations Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Web search with cited sources; admins grant it to groups.

AGT-04 Workflows and automation

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

LibreChat

Agent cross-checked Support: partial

Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries.

Availability: beta · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established.
event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified.

workflow_builder Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents.
scheduled_tasks Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule.
event_triggers Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api.
builder_audience Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api.

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

onAI

Agent cross-checked Support: partial

The public site labels the native workflow engine coming soon and offers n8n/custom workflow services meanwhile.

Stated by onAI We build workflows and automations as a service; a self-service builder is in progress. (vendor-statement, asserted 2026-10-23)

Availability: unknown · Delivery: official-integration
Scope: surfaces=onAI browser workspace; version=Undated public homepage checked 2026-10-26; no native workflow release verified.; plan=Public n8n/custom-workflow service offer on request; plan entitlement unspecified. Native workflow engine described as coming soon.; add_ons=none stated; deployment_mode=not specified; region=Workflow deployment and processing regions are not specified in the cited public homepage section.; os=not specified.

Limitations

workflow_builder: The native engine is announced as coming soon, without a release date. The current offer describes n8n integration run by onAI, the customer or a partner; no native self-service chain builder is counted as released.
scheduled_tasks: No user-facing scheduled-prompt service, schedule limits or plan entitlement was verified. Internal background task machinery is insufficient evidence. Search on 2026-10-26: https://onaihq.com/, https://onaihq.com/sitemap.xml, https://onaihq.com/docs/. No additional scoped evidence established this answer.
event_triggers: No documented email/form/business-system trigger or executed workflow was obtained; outbound webhooks do not establish inbound workflow triggers. Search on 2026-10-26: https://onaihq.com/, https://onaihq.com/sitemap.xml, https://onaihq.com/docs/. No additional scoped evidence established this answer.
builder_audience: For the described n8n alternative, onAI, the customer or a partner may operate it, and onAI offers workflow construction on request. This does not specify a shipped native builder audience, schedule limits or event-trigger coverage.
The public homepage is undated and combines a future native engine with an on-request service alternative. No public deployment/version or Per seat/Flat price workflow entitlement was established.

workflow_builder Is there a workflow or chain builder? [partial]: The native engine is announced as coming soon, without a release date. The current offer describes n8n integration run by onAI, the customer or a partner; no native self-service chain builder is counted as released. Sources: onai:onai:review-fix-public-workflow-scope-20261026.
scheduled_tasks Can prompts or assistants run on a schedule? [unknown]: No user-facing scheduled-prompt service, schedule limits or plan entitlement was verified. Internal background task machinery is insufficient evidence. Search on 2026-10-26: https://onaihq.com/, https://onaihq.com/sitemap.xml, https://onaihq.com/docs/. No additional scoped evidence established this answer.
event_triggers Can external events start a workflow? [unknown]: No documented email/form/business-system trigger or executed workflow was obtained; outbound webhooks do not establish inbound workflow triggers. Search on 2026-10-26: https://onaihq.com/, https://onaihq.com/sitemap.xml, https://onaihq.com/docs/. No additional scoped evidence established this answer.
builder_audience Is building aimed at business users, IT or developers? [partial]: For the described n8n alternative, onAI, the customer or a partner may operate it, and onAI offers workflow construction on request. This does not specify a shipped native builder audience, schedule limits or event-trigger coverage. Sources: onai:onai:review-fix-public-workflow-scope-20261026.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:onai:review-fix-public-workflow-scope-20261026.

AGT-05 Agentic task execution

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

LibreChat

Agent cross-checked Support: partial

Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls.

Limitations

No gather-documents, draft-summary and propose-email task was run.
Highly experimental attached workspaces are distinct from ordinary Agent tool use.

agent_mode Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code.
visible_steps Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents.
side_effect_confirmation Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code.
stop_control Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

No separate autonomous agent mode; tools run in the normal chat.

AGT-06 Programmable access

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

LibreChat

Agent cross-checked Support: partial

The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit.

Availability: beta · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified.
api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested.
mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface.

chat_api Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api.
knowledge_api Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api.
api_governance Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access.
mcp_server Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

API for chat and document processing on request.

Daily work

WORK-01 Clients and access points

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

LibreChat

Agent cross-checked Support: partial

The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified.

Limitations

desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established.
browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested.

web Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local.
desktop_apps Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
mobile_apps iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights.
browser_extension Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
managed_deployment Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
client_feature_gaps Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights.

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

onAI

Agent cross-checked Support: partial

The vendor offers a browser workspace requiring no installation. Native clients, extensions and managed deployment support remain unknown.

Stated by onAI An uncluttered interface without technical settings. At Manor, hundreds of employees use onAI every day. (vendor-statement, asserted 2026-10-22)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat and Flat price web workspace offers; add_ons=none stated; deployment_mode=not specified; region=Unspecified by source; os=Browser; operating system unspecified.

Limitations

Only browser access is established by public copy. No native-client absence is inferred from missing listings.

web Is a full web client available? [supported]: The public AI Tools section describes the employee workspace running in a current browser with nothing to install. Sources: onai:public-web-client.
desktop_apps Windows and macOS apps? [unknown]: No first-party Windows/macOS native client download, company-SSO support table or desktop fixture was located.
mobile_apps iOS and Android apps with SSO? [unknown]: No iOS/Android native app listing or mobile SSO fixture was verified. A responsive website would not establish native apps.
browser_extension Is there a browser extension or sidebar? [unknown]: No browser extension/sidebar release or installation instructions were located on the public product page or sitemap.
managed_deployment Can IT deploy and configure clients through MDM? [unknown]: No MDM/Intune deployment package, policy guide or client configuration profile was obtained.
client_feature_gaps Which features are missing on mobile? [unknown]: No matched desktop/mobile-browser/native-client fixture was run; no cross-client feature parity claim is made.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: onai:public-web-client.

WORK-02 Office suite and Teams integration

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

LibreChat

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.

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Outlook and Excel add-ins in preparation; Microsoft 365 is connected live.

WORK-03 Translation and writing

Judgment rule: Record document translation preserving layout, the translation engine (LLM or dedicated such as DeepL), glossaries, formality control, supported languages including Swiss German conventions (no ß), and rewriting/proofreading tools. Translate the shared German contract into French and Italian and record layout and glossary results.

LibreChat

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.

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-22

Translation with DeepL: documents with their layout, glossaries, formal or informal address. Plus adjusting style and tone.

WORK-04 Image generation and editing

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

LibreChat

Agent cross-checked Support: partial

Configured Agent image tools generate and edit images; model service rights/costs remain separate.

Limitations

admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established.
usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement.

image_generation Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images.
image_editing Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images.
admin_control Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access.
usage_terms What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement.

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

onAI

Agent cross-checked Support: partial

Image Studio advertises several image models, prompt-based editing and administrator controls. Its cost examples and commercial-use statement are vendor claims.

Stated by onAI The leading image models from OpenAI, Google, Black Forest Labs and xAI in one studio: one prompt to up to three models side by side, styles with automatic prompt enhancement, editing with up to ten reference images, cost shown before generating. (vendor-statement, asserted 2026-10-22)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Image Studio listed in Per seat and Flat price; model entitlements unspecified; add_ons=none stated; deployment_mode=not specified; region=Provider dependent; EU-only optional tier described separately; os=not specified.

Limitations

Displayed prices and timings are illustrative UI examples, not a general price list or measured benchmark. No provider-specific output-rights contract was reviewed.

image_generation Can users generate images, with which models? [supported]: The page lists GPT Image, Nano Banana Pro, Imagen 4 and FLUX.3, with up to three selected models per prompt and an estimated provider cost shown before generation. Exact version IDs and live plan entitlements were not tested. Sources: onai:public-images.
image_editing Can users edit uploaded images? [supported]: The page describes editing an uploaded image or a previous result using a text instruction and shows image-editing models. Inpainting masks and per-model limits were not verified. Sources: onai:public-images.
admin_control Can admins restrict image generation? [supported]: Administrators are said to choose image models and which users may use them; optional personal-data filtering is described. Sources: onai:public-images.
usage_terms What usage rights apply to output? [partial]: The vendor says generated images may be used commercially. It does not supply model-specific output licences, indemnities or restrictions in this section. Sources: onai:public-image-rights.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: onai:public-image-rights, onai:public-images.

WORK-05 Voice and meetings

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

LibreChat

Agent cross-checked Support: partial

LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified.

Limitations

Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified.
Audio location depends on the chosen engine. No meeting or Swiss German fixture was run.

dictation Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech.
read_aloud Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech.
voice_conversation Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2.
meeting_summaries Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation.
swiss_german_speech Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Voice input with transcription, and answers read aloud.

WORK-06 Data analysis and document output

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

LibreChat

Agent cross-checked Support: partial

The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run.
office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture.
canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established.

data_analysis Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code.
charts Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code.
office_file_output Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code.
canvas_editing Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Code execution (Python) for data analysis and charts.

WORK-07 Sharing and team spaces

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

LibreChat

Agent cross-checked Support: partial

Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care.

Limitations

group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy.
share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run.

share_chats Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share.
team_spaces Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects.
group_chat Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy.
share_permission_boundary Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Share chats with colleagues by link.

WORK-08 Interface languages and accessibility

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

LibreChat

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.

Limitations

dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.

ui_languages Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin.
dach_language_quality Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
accessibility_statement Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
admin_ui_languages Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Interface in German and English, more languages in preparation.

Administration and governance

ADM-01 Single sign-on and authentication

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

LibreChat

Agent cross-checked Support: partial

Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced.

Limitations

conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested.
domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim.

sso_protocols Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth.
sso_plan Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth.
mfa Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth.
conditional_access Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra.
domain_capture Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim.

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

onAI

Agent cross-checked Support: partial

Public copy offers Microsoft, Google, OIDC and LDAP sign-in, with published plan differences. Native SAML, MFA enforcement and conditional-access behavior were not verified.

Availability: unknown · Delivery: official-integration
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat: Microsoft/Google; Flat price: Microsoft/Google/OIDC/LDAP; add_ons=none stated; deployment_mode=not specified; region=Identity-provider and deployment regions unspecified; os=not specified.

Limitations

No successful login or policy enforcement fixture was run. SAML and MFA are left unknown rather than inferred from corporate-login marketing.

sso_protocols Which SSO protocols and identity providers work? [supported]: The current page lists Microsoft Entra ID, Google, any OpenID Connect provider and LDAP. It does not establish native SAML support; generic corporate SSO language is insufficient. Sources: onai:public-pricing-display-20261026.
sso_plan Which plan includes SSO? [supported]: Per seat lists Entra ID and Google. Flat price lists Entra ID, Google, OIDC and LDAP. These are published offer terms, not an executed SSO fixture. Sources: onai:public-pricing-display-20261026.
mfa Can MFA be enforced? [unknown]: No onAI-native MFA requirement or tenant-enforced IdP-MFA setup was verified. IdP capabilities are not automatically onAI enforcement.
conditional_access Do Entra conditional-access policies apply? [unknown]: No Entra conditional-access compatibility statement or test policy/login result was obtained.
domain_capture Can the company claim its email domain? [unknown]: No domain-claim/verification workflow, automatic capture policy or ownership-transfer fixture was established from public material.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:public-pricing-display-20261026.

ADM-02 User provisioning and lifecycle

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

LibreChat

Agent cross-checked Support: partial

Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown.

Limitations

scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run.
deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested.
seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source.

scim Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run.
group_sync Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra.
jit_provisioning Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth.
deprovisioning What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth.
seat_assignment Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Users are created automatically at their first SSO sign-in and groups come from the directory; no SCIM.

ADM-03 Roles, groups and feature permissions

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

LibreChat

Agent cross-checked Support: partial

Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

Separate admin management UI is preview; the core authorization model is documented as available.
No two-group disabled-feature fixture was run.

admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access.
groups Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin.
feature_toggles Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access.
multi_entity Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-22

Roles and groups; admins decide per group which features (for example Image Studio, translator, web search) are used.

ADM-04 Usage and adoption analytics

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

LibreChat

Agent cross-checked Support: partial

Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail.

Limitations

breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established.
export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified.
privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established.

adoption_dashboard Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights.
breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens.
export Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified.
privacy_modes Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Usage reports by model, feature and person.

ADM-05 Spend controls and cost allocation

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

LibreChat

Agent cross-checked Support: partial

Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices.

Limitations

cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing.
budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established.
chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established.

cost_visibility Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights.
budgets Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance.
budget_enforcement Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin.
chargeback Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Cost limits per organisation and per person.

ADM-06 Audit logs and compliance export

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

LibreChat

Agent cross-checked Support: partial

Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified.

Limitations

admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established.
content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive.
siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified.
ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified.
log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks.

admin_events Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging.
content_logging Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin.
siem_export Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging.
ediscovery Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified.
log_retention How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Audit logging can be switched on; a built-in SIEM connection is not included.

ADM-07 Data loss prevention and personal data

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

LibreChat

Agent cross-checked Support: partial

Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown.

Availability: source-only · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

Development-source finding; no running instance or AHV/IBAN fixture.
Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class.
Redaction applies only to eligible fresh Agent text; encrypted originals remain stored.
A dedicated external DLP integration remains unverified.

pii_detection Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware.
pii_action Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware.
custom_patterns Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware.
dlp_integration Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration.
filter_location Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

For selected web search providers and image models, automatic redaction of sensitive text can be switched on.

ADM-08 AI policy and guardrails

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

LibreChat

Agent cross-checked Support: partial

Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement.

Limitations

org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement.
content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established.
violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established.

org_instructions Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents.
usage_notice Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface.
content_filters Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod.
violation_reporting Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Administrators set notice banners and system instructions for the AI.

Data protection and sovereignty

DATA-01 Hosting location and data residency

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

LibreChat

Agent cross-checked Support: partial

Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions.

Limitations

backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited.
support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment.
swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established.

storage_region Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote.
inference_region Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex.
backups_logs_region Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin.
support_access_region From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment.
swiss_hosting Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license.
residency_plan Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-22

Swiss contracting party. onAI runs on servers in Europe. On request a dedicated server, or onAI runs on your own servers (on-premises).

DATA-02 Deployment options

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

LibreChat

Agent cross-checked Support: partial

The project documents local and customer-cloud installs. A free public demo is separate from a production managed service.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence.
dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established.
air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified.
mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix.

multi_tenant_saas Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat.
dedicated_instance Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established.
customer_cloud Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license.
on_premise Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin.
air_gapped Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg.
mode_feature_gaps Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-22

Swiss contracting party. onAI runs on servers in Europe. On request a dedicated server, or onAI runs on your own servers (on-premises).

DATA-03 Training use and provider retention

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

LibreChat

Agent cross-checked Support: partial

The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established.

Limitations

vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service.
provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.

vendor_training Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat.
provider_training Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
zero_retention Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
human_review Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.

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

onAI

Sourced Support: partial

The site publishes general no-training copy and advertises an optional provider zero-retention tier. Their contractual applicability to Per seat and Flat price is unverified; no plan-specific provider-retention or human-review guarantee is established.

Stated by onAI Your data is not used to train AI models; we only use providers that exclude this by contract. (vendor-statement, asserted 2026-10-23)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Product-wide marketing only; Per seat/Flat price contractual applicability and EU-only tier eligibility unverified.; add_ons=EU-only processing and zero-retention option, terms unspecified; deployment_mode=not specified; region=Per-provider default unknown; optional EU tier claimed; os=not specified.

Limitations

Remains public-candidate because the public statements are not mapped to a named plan contract. No no-training or zero-retention entitlement is inferred for either plan.
The existence of a requestable DPA is not review of its terms; provider retention and human review remain explicit gaps.

vendor_training Does the vendor train on customer content? [partial]: The public product page makes a general no-training statement about prompts, files and answers. It is recorded only as unqualified marketing copy: no retrieved DPA or public plan mapping establishes the contractual rule for Per seat or Flat price. Sources: onai:review-contract-plan-gaps.
provider_training Do model providers train on it under this product's contracts? [unknown]: No provider contract or Per seat/Flat price policy mapping was retrieved. General no-training marketing does not establish model-provider contract terms, exceptions or enforcement. Sources: onai:review-contract-plan-gaps.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: No provider-by-provider prompt/abuse-monitoring retention period, default or exception schedule was obtained.
zero_retention Is zero data retention available, and on which plan? [unknown]: The page advertises an optional EU-only AI-processing tier with provider zero retention, but its applicable base plan, providers, exceptions and contractual terms were not retrieved. This is not counted as an established Per seat or Flat price entitlement. Sources: onai:review-contract-plan-gaps.
human_review Can provider staff review content? [unknown]: No product-specific provider human-review/abuse-monitoring policy or opt-out contract was retrieved.

Checked 2026-10-21; not separately cross-checked; check again by 2026-12-20. Sources: onai:review-contract-plan-gaps.

DATA-04 Retention and deletion

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

LibreChat

Agent cross-checked Support: partial

Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes.

Limitations

user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified.
contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer.

default_retention What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention.
admin_retention Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention.
user_deletion Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings.
contract_end_deletion What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Users delete their own chats at any time. At contract end we delete all of your organisation's data, with confirmation on request.

DATA-05 Sub-processors and foreign-law exposure

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

LibreChat

Agent cross-checked Support: partial

ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts.

Limitations

subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement.
transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.

subprocessor_list Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
subprocessor_countries Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
change_notification Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
parent_jurisdiction Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner.
transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
government_access_policy Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.

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

onAI

Agent cross-checked Support: partial

Telesoft AG is publicly identified in Switzerland. A product subprocessor/country/change-notice schedule and government-access policy were not obtained; website processors are scoped separately.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=All public offers for entity identity; product processor terms unspecified; add_ons=none stated; deployment_mode=not specified; region=Vendor Switzerland; product processor and parent countries unknown; os=not specified.

Limitations

No legal exposure verdict is made. Product contracts and website privacy terms must remain separate.

subprocessor_list Is a dated sub-processor list published? [unknown]: The homepage advertises a public subprocessor list but no product list/document was linked or retrieved through the sitemap and legal pages. The dated website policy is not the workspace processor list. Sources: onai:public-compliance-display-20261026, onai:public-website-privacy-display-20261026.
subprocessor_countries Which countries do sub-processors operate in? [unknown]: The product provider/country matrix is unknown. The website policy lists providers in Slovenia, Estonia, Ireland and the USA for website purposes only; these cannot be treated as product coverage. Sources: onai:public-website-privacy-display-20261026.
change_notification Are customers notified of sub-processor changes? [unknown]: No product subprocessor change-notice period, objection rule or notification subscription was located.
parent_jurisdiction Which jurisdiction governs the vendor and its parent? [partial]: The imprint names Telesoft AG at a Swiss address and a Swiss VAT registration. A parent-company ownership/jurisdiction record was not obtained. Sources: onai:public-imprint-display-20261026.
transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [unknown]: Website processing cites SCCs and provider-dependent DPF. No corresponding product AI-provider/data-transfer agreement was retrieved. Sources: onai:public-website-privacy-display-20261026.
government_access_policy Is there a published government-access or transparency policy? [unknown]: No product government-access/transparency policy or dated request report was found. Swiss incorporation alone does not establish foreign-law immunity.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:public-compliance-display-20261026, onai:public-imprint-display-20261026, onai:public-website-privacy-display-20261026.

DATA-06 Contracts and regulatory coverage

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

LibreChat

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.

onAI

Sourced Support: partial

The general public DPA inquiry path is established. DPA content, Swiss DSG/GDPR clauses, AI Act material and plan-specific document entitlements remain unverified for Per seat and Flat price; no compliance conclusion is drawn.

Stated by onAI Data processing agreement under the Swiss FADP and the GDPR on request. (vendor-statement, asserted 2026-10-23)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=General DPA inquiry/compliance copy only; Per seat/Flat price document entitlement unverified.; add_ons=none stated; deployment_mode=not specified; region=Swiss entity; claimed Swiss DSG/GDPR coverage; os=not specified.

Limitations

Remains public-candidate. A contact action and general legal labels do not establish plan-scoped contract terms or supplied regulatory documentation.
No product agreement, legal forum or sector-specific contract package was reviewed.

dpa Is a DPA available, and is it negotiable? [partial]: A general Request the DPA contact action is public. It establishes an inquiry path, not that a particular DPA, execution procedure or negotiability option is included in Per seat or Flat price; no contract was retrieved and no sales contact was made. Sources: onai:review-contract-plan-gaps.
revdsg_gdpr Does the DPA cover revDSG and GDPR? [unknown]: The website refers generally to Swiss DSG and GDPR, but no product DPA text or plan applicability was retrieved. Its actual revDSG/GDPR clauses and scope cannot be established from the vendor entity or marketing labels. Sources: onai:review-contract-plan-gaps, onai:public-imprint.
governing_law Which law and court govern the contract? [unknown]: A Swiss contracting entity does not determine governing law or court. No product agreement specifying either was obtained.
ai_act_materials Is EU AI Act documentation provided? [unknown]: The public page advertises AI Act transparency labels. No provider/deployer-role documentation, technical material, conformity scope or Per seat/Flat price delivery entitlement was obtained. Sources: onai:review-contract-plan-gaps.
sector_materials Are FINMA or other sector materials provided? [unknown]: No FINMA outsourcing, banking secrecy, public-sector or regulated-industry contract package was obtained.

Checked 2026-10-21; not separately cross-checked; check again by 2026-12-20. Sources: onai:public-imprint, onai:review-contract-plan-gaps.

DATA-07 Certifications and attestations

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

LibreChat

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.

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

onAI is not currently ISO 27001 certified and has no SOC 2 report.

DATA-08 Encryption and key control

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

LibreChat

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.

Limitations

encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.
customer_managed_keys: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified.
tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.

encryption_at_rest Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.
customer_managed_keys Can the customer manage or hold the keys? [partial]: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. Sources: librechat:librechat:auth, librechat:librechat:compose-pin.
private_networking Is private connectivity or IP restriction available? [supported]: Operators deploy the stack on their own network and configure reverse proxies/HTTPS for remote access. Sources: librechat:librechat:remote, librechat:librechat:local.
tenant_isolation How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Connections are encrypted over HTTPS, stored data is encrypted in the cloud, and each organisation's data is logically separated. Dedicated installations and on-premises: encryption and separation follow your infrastructure.

DATA-09 Professional secrecy

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

LibreChat

Agent cross-checked Support: partial

Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified.

Availability: unknown · Delivery: unknown
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified.

Limitations

The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown.
content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified.
Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made.

secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner.
subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy.
secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo.
content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom.
secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Professional-secrecy agreement (for example § 203 StGB / Art. 321 StGB) on request.

Commercials and vendor

VEN-01 Pricing model and list prices

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

LibreChat

Agent cross-checked Support: partial

MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured.

Limitations

add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts.
overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff.

pricing_unit What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat.
list_prices What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat.
included_usage What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat.
add_ons Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images.
overage What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat.

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

onAI

Agent cross-checked Support: partial

The page lists EUR 17/user/month with EUR 5 monthly model budget; Per seat overage is actual consumption with no minimum. Flat price and detailed tariffs remain quoted or unspecified.

Stated by onAI From €17 per user and month, including €5 of model use; lower for larger teams. Or one fixed price for the whole company. (vendor-statement, asserted 2026-10-22)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat EUR 17/month; Flat price annual quote; publication is not GA verification; add_ons=EU-only processing option, price unknown; deployment_mode=not specified; region=European hosting; dedicated CH/DE/on-premises by quoted plan; os=not specified.

Limitations

add_ons: Per seat lists models, Image Studio, translator and Microsoft 365 access. Flat price additionally lists dedicated/on-premises hosting, own models, branding and onboarding. An EU-only processing tier is offered without a public surcharge or connector/agent add-on tariff.
overage: For Per seat, usage beyond the included model budget is billed at actual consumption, with no minimum and invoices itemized by model and quantity; the usage journal shows provider-reported token counts. No complete tariff, model conversion/multiplier, top-up or rollover schedule was retrieved.

pricing_unit What is the pricing unit? [supported]: Per seat is priced per user/month. Flat price is one fixed annual company price with unlimited users; unlimited seats do not establish unlimited model usage. Sources: onai:onai:public-automation-status-20261026.
list_prices What are list prices per plan, with date and currency? [supported]: As retrieved 2026-10-21, Per seat is EUR 17/user/month excluding VAT. The Flat price amount is on request; no CHF list price is shown. Sources: onai:onai:public-automation-status-20261026.
included_usage What usage is included? [supported]: Per seat includes EUR 5 model budget per user/month. The page does not translate this into message/token/image quotas or state the Flat price usage allowance. Sources: onai:onai:public-automation-status-20261026.
add_ons Which features cost extra? [partial]: Per seat lists models, Image Studio, translator and Microsoft 365 access. Flat price additionally lists dedicated/on-premises hosting, own models, branding and onboarding. An EU-only processing tier is offered without a public surcharge or connector/agent add-on tariff. Sources: onai:onai:public-automation-status-20261026.
overage What do usage beyond limits and premium models cost? [partial]: For Per seat, usage beyond the included model budget is billed at actual consumption, with no minimum and invoices itemized by model and quantity; the usage journal shows provider-reported token counts. No complete tariff, model conversion/multiplier, top-up or rollover schedule was retrieved. Sources: onai:onai:public-automation-status-20261026.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: onai:onai:public-automation-status-20261026.

VEN-02 Scenario cost

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

LibreChat

Agent cross-checked Support: partial

ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified.

Limitations

ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise.
The budget is a floor because named infrastructure and service costs are unpriced.

cost_200 Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
cost_1000 Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
cost_5000 Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
variable_share Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort.
unknown_parts Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license.

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

onAI

Agent cross-checked Support: partial

Under ALM-14 shared cost assumptions v1.4, 2026-10-21, only the published Per seat component is calculable. The scenario is from that EUR/CHF floor plus unknown usage/option charges; Flat price requires a quote.

Stated by onAI From €17 per user and month, including €5 of model use; lower for larger teams. Or one fixed price for the whole company. (vendor-statement, asserted 2026-10-22)

Availability: beta · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat list-price scenario only; Flat price and customer-operated totals unknown; add_ons=No priced add-ons included; option costs unknown; deployment_mode=multi-tenant-saas; region=Published European-hosting offer; GA unverified; os=not specified.

Limitations

ALM-14 shared cost assumptions v1.4, 2026-10-21. Horizon 12 months, full paid seats, list price, excluding VAT, no invented discounts. These are plan components, not complete workload totals.
The included model allowance is not counted twice. Annual model usage is 11.88M input and 2.376M output tokens per user under the disclosed mix, but the product billing tariff is unknown.

cost_200 Year-one cost at 200 users? [partial]: 200 seats for 12 months: from EUR 40,800 / CHF 37,686.96 excluding VAT, plus unknown usage/option costs. EUR 12,000 annual model budget is already included, not added again. Flat price and actual workload overage are unpriced. Sources: onai:public-pricing, onai:ecb-fx.
cost_1000 Year-one cost at 1,000 users? [partial]: 1,000 seats for 12 months: from EUR 204,000 / CHF 188,434.80 excluding VAT, plus unknown usage/option costs. EUR 60,000 annual model budget is already included. Flat price and actual workload overage are unpriced. Sources: onai:public-pricing, onai:ecb-fx.
cost_5000 Year-one cost at 5,000 users? [partial]: 5,000 seats for 12 months: from EUR 1,020,000 / CHF 942,174 excluding VAT, plus unknown usage/option costs. EUR 300,000 annual model budget is already included. Flat price and actual workload overage are unpriced. Sources: onai:public-pricing, onai:ecb-fx.
variable_share Which part depends on usage? [partial]: Shared workload: 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month; each message has 3,000 input and 600 output tokens including retrieval. This is 330 messages/month/user. No onAI default-model tariff or credit-to-provider mapping is public, so no variable charge or variable percentage is invented. Sources: onai:public-pricing.
unknown_parts Which costs could not be priced? [partial]: Unknowns include Flat price quotes, model usage beyond the included allowance, premium features/EU-only options and customer-operated infrastructure/support. No proxy API price substitutes for an unpublished onAI tariff. FX is ECB 2026-10-20: EUR 1 = CHF 0.9237 and USD 1.1215; USD/EUR reciprocal 0.8916629514043692. Sources: onai:public-pricing, onai:public-processing, onai:ecb-fx.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: onai:ecb-fx, onai:public-pricing, onai:public-processing, onai:review-plan-m365, onai:review-residency-parts.

VEN-03 Evaluation access

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

LibreChat

Agent cross-checked Support: supported

Customers can self-install without licence payment; the public demo is an evaluation-only alternative.

free_tier Is there a free tier for business use? [supported]: MIT self-installation permits organizational use without a software licence fee. Sources: librechat:librechat:license.
self_serve_trial Is a self-serve business trial available? [supported]: Self-installation has no trial clock or software card requirement; the free hosted Demo can be tried separately under its terms. Sources: librechat:librechat:local, librechat:librechat:demo.
trial_scope Do trials include SSO, connectors and admin features? [supported]: Self-installed instances can configure SSO, Agents, file retrieval and administration with their own service accounts. It is not evidence that every experimental add-on is enabled by default. Sources: librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag.
sales_gate Does meaningful evaluation require sales contact? [supported]: The documented Docker install does not require sales approval; optional third-party services have separate account requirements. Sources: librechat:librechat:local, librechat:librechat:firstchat.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-22

A personal demo, then trial access for your team.

VEN-04 Contract terms and pricing transparency

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

LibreChat

Agent cross-checked Support: partial

The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence.

Limitations

cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies.
local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services.
transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer.

minimum_commitment What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license.
contract_length What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license.
cancellation How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services.
transparency_class Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat.

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

onAI

Agent cross-checked Support: partial

Per seat has a public EUR headline and monthly seat flexibility; Flat price is quoted annually. Legal commitment, cancellation rules and CHF invoicing remain unverified.

Stated by onAI From €17 per user and month, including €5 of model use; lower for larger teams. Or one fixed price for the whole company. (vendor-statement, asserted 2026-10-22)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Per seat monthly price/seat flexibility; Flat price annual quote; add_ons=none stated; deployment_mode=not specified; region=Swiss provider; EUR display; CHF invoicing unknown; os=not specified.

Limitations

Published billing frequency is not an executed minimum-term contract. No undisclosed enterprise discount is assumed.

minimum_commitment What seat or spend minimum applies? [unknown]: No minimum seat count or spend commitment is stated on the current pricing page. The about-50-user flat-price break-even is not a contractual minimum. Sources: onai:public-pricing.
contract_length What contract lengths are offered? [partial]: Per seat is quoted monthly and says seats can be added/removed each month. Flat price is quoted annually; the legal contract length and billing options are not supplied. Sources: onai:public-pricing.
cancellation How can the contract be cancelled or reduced? [partial]: The page promises monthly Per seat seat changes. Cancellation notice, proration, refunds, price-change rules and downgrade terms were not obtained. Sources: onai:public-pricing.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [partial]: Prices are displayed in EUR and the identified provider is Swiss Telesoft AG. Actual invoice currency, CHF availability and VAT/payment terms were not verified. Sources: onai:public-pricing, onai:public-imprint.
transparency_class Is pricing transparent, partial, quote-only or unknown? [supported]: Partially specified: the Per seat headline and allowance are public; Flat price is quote-only and usage overage, option prices and legal terms are missing. Sources: onai:public-pricing.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: onai:public-imprint, onai:public-pricing.

VEN-05 Source licence

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

LibreChat

Agent cross-checked Support: partial

The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence.

Limitations

enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established.

licence_type Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license.
branding_restrictions Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license.
enterprise_features_closed Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Proprietary software from onAI; the source code is not public. Included open-source components are under their own licences.

VEN-06 Data export and exit

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

LibreChat

Agent cross-checked Support: partial

Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified.

Limitations

chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established.
assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified.
knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.
post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.

chat_export Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin.
assistant_export Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api.
knowledge_export Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.
export_format Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin.
post_termination_window How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.

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

onAI

Stated by onAI Support: stated Evidence type: vendor-statement; asserted 2026-10-23

Users export their chats as JSON; an export for the whole organisation on request.

VEN-07 Support and service levels

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

LibreChat

Agent cross-checked Support: partial

Public project/community channels are available; a binding business support SLA was not established.

Limitations

support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting.
support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.

support_channels Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat.
support_languages Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
uptime_sla Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
status_page Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.

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

onAI

Sourced Support: partial

The Swiss provider identity, general company contact and Website-only public status history are established. Support channels, languages/hours, response targets and uptime credits for Per seat and Flat price remain unknown.

Stated by onAI A direct line to the team, no call centre, in German and English. Onboarding and training are included in the fixed price. We build custom agents and workflows as a service. Service levels and response times are agreed in the contract. (vendor-statement, asserted 2026-10-23)

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public provider website and status sources retrieved 2026-10-21; plan=Company identity/contact and Website-only status facts; Per seat/Flat price support entitlement unverified.; add_ons=none stated; deployment_mode=not specified; region=Swiss legal entity; support staffing/access countries unknown; os=not specified.

Limitations

Remains public-candidate: entity identity and website-status facts are separated from unverified product-plan support commitments.
The Website-only service history and generic custom-development SLA wording do not establish a workspace uptime target or credit schedule.

support_channels Which support channels are available on each plan? [unknown]: The company publishes info@onaihq.com and a general inquiry/demo form. No public evidence maps these to a contracted support desk for Per seat or Flat price, or states hours, escalation and response commitments. Sources: onai:public-imprint, onai:public-services.
support_languages Is support available in German, French or Italian? [unknown]: English/German website and UI copy do not establish contractual DE/FR/IT support languages or support hours.
regional_presence Is there a DACH or Swiss entity, team or partner? [supported]: The imprint identifies Telesoft AG in Oberwil-Lieli, Switzerland, with a Swiss VAT registration. No reseller roster is inferred. Sources: onai:public-imprint.
uptime_sla Is there an uptime SLA with credits? [unknown]: Custom development copy mentions SLAs but supplies no product uptime target, measurement, exclusions or credit schedule. A status percentage is not a contractual SLA. Sources: onai:public-services.
status_page Is there a public status page with history? [partial]: The first-party-linked status page has notice history for Website only. This is a marketing-website status fact, not a Per seat/Flat price workspace/API status promise or support entitlement. Sources: onai:review-status-service-scope.

Checked 2026-10-21; not separately cross-checked; check again by 2026-12-20. Sources: onai:public-imprint, onai:public-services, onai:review-status-service-scope.

VEN-08 Onboarding, training and adoption

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

LibreChat

Agent cross-checked Support: partial

Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified.

Limitations

onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established.
adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.

onboarding_service Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
user_training Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
use_case_library Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat.
adoption_programme Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
service_cost Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.

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

onAI

Agent cross-checked Support: partial

The vendor offers training, workshops and custom agent services. Flat price lists onboarding/training/workshops; languages, delivery scope and separate service costs remain unknown.

Availability: unknown · Delivery: native
Scope: surfaces=onAI browser workspace; version=Public page retrieved 2026-10-21; plan=Flat price named services included; Per seat/service contract unspecified; add_ons=Bespoke agent/workflow development, quoted scope; deployment_mode=not specified; region=Delivery geography and languages unspecified; os=not specified.

Limitations

Vendor/partner professional services are distinguished from native product workflow automation. No service outcome or price is invented.

onboarding_service Is guided onboarding included? [supported]: The public Flat price offer includes onboarding, training and workshops. Per seat inclusion and precise deliverables are not specified. Sources: onai:public-pricing, onai:public-services.
user_training Is end-user training offered, in which languages? [partial]: The vendor offers practical prompt/tool/best-practice sessions tailored to Marketing, HR and IT. Session format, DE/FR/IT languages, hours and e-learning availability were not retrieved. Sources: onai:public-services.
use_case_library Are role-based use cases and templates provided? [unknown]: The site describes use-case workshops and public guides, but no role-based in-product use-case/template library inventory or licence was obtained.
adoption_programme Is there a champion or adoption programme? [unknown]: No scoped champion programme, change-management package or measured adoption service deliverable was retrieved; generic skills guides do not establish one.
service_cost Which services cost extra? [unknown]: Flat price includes named services but its amount is quoted; separate Per seat onboarding, training, workshops and custom-development fees are not published. Sources: onai:public-pricing, onai:public-services.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: onai:public-pricing, onai:public-services.

Sources

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
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
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
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
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
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
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
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
onAI public product and pricing page onai:public-models-display-20261026
The page names Claude, GPT, Gemini, Grok and Mistral, user model selection and administrator allow-lists, without exact chat model IDs.
Ready for the whole company from day one > Every leading model; AI Gateway; re-retrieved 2026-10-26, public web-reader representation SHA256 f2b7d5764994efe8fb87021fe13d7295155dd04ec09c8ed7826fcb52acc42b19 · vendor-claimed · Source date not stated · Retrieved 2026-10-26
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
onAI public product and pricing page onai:public-m365-display-20261026
The page lists live Microsoft 365 sources, optional channel/transcript permissions and optional Copilot-licensed search and meeting notes.
Answers from your Microsoft 365, live > Where onAI looks; Your admin can add; re-retrieved 2026-10-26, public web-reader representation SHA256 f2b7d5764994efe8fb87021fe13d7295155dd04ec09c8ed7826fcb52acc42b19 · vendor-claimed · Source date not stated · Retrieved 2026-10-26
onAI public product and pricing page onai:public-m365-permissions-display-20261026
The vendor describes delegated read-only requests under each user, no copied library index, source citations, admin model restrictions and Microsoft administrator consent.
Your Microsoft permissions stay in charge; For IT; Every permission onAI can request; re-retrieved 2026-10-26, public web-reader representation SHA256 f2b7d5764994efe8fb87021fe13d7295155dd04ec09c8ed7826fcb52acc42b19 · vendor-claimed · Source date not stated · Retrieved 2026-10-26
onAI public product and pricing page onai:public-other-connectors-display-20261026
The FAQ describes Microsoft 365 live retrieval and names Confluence, S3 and custom sources through standard connectors or an API; it gives no connector-by-connector setup or plan catalogue.
FAQ > How is our data integrated into the system?; re-retrieved 2026-10-26, public web-reader representation SHA256 f2b7d5764994efe8fb87021fe13d7295155dd04ec09c8ed7826fcb52acc42b19 · vendor-claimed · Source date not stated · Retrieved 2026-10-26
onAI live Microsoft 365 retrieval and citation description onai:review-m365-boundaries-display-20261026
The vendor describes delegated Microsoft permission checks, live reads without a second library index, retrieved material retained in the asking user’s chat and numbered source links.
Your Microsoft permissions stay in charge; Nothing copied, nothing indexed; Sources on every answer; re-retrieved 2026-10-26, HTTP 200 body SHA256 a074779dc4d08c5e48440218bbc01353565673585b9e0f7eab517ed9687b77fa · vendor-claimed · Source date not stated · Retrieved 2026-10-26
onAI live pricing: named Microsoft 365 plan scope onai:review-plan-m365-display-20261026
The Per seat card expressly includes Microsoft 365 answers and the Flat price card includes everything in Per seat; the cards do not establish separate DPA, provider-retention or support entitlements.
Per seat > Answers from Microsoft 365, with each user’s own permissions; Flat price > Everything in Per seat, for every employee; re-retrieved 2026-10-26, HTTP 200 body SHA256 a074779dc4d08c5e48440218bbc01353565673585b9e0f7eab517ed9687b77fa · vendor-claimed · Source date not stated · Retrieved 2026-10-26
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
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
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
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
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
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
onAI public workflow and service offer onai:onai:review-fix-public-workflow-scope-20261026
The undated public homepage labels the native workflow engine coming soon and describes n8n integration operated by onAI, the customer or a partner, with workflow construction offered on request. It gives no native release date or plan-specific workflow entitlement.
Automation platform; Coming soon; n8n service/operator sentence; direct public GET HTTP200 2026-10-26, body SHA256 1ea21a62b3a2bb75b66287a93fd86a47984d51519e7fd99f4ca53930996219bc · vendor-claimed · Source date not stated · Retrieved 2026-10-26
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
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
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
onAI public product and pricing page onai:public-web-client
The vendor describes an employee workspace in a current browser with nothing to install; native client availability is unspecified.
The platform > AI Tools; FAQ > What prerequisites do we need to meet? · vendor-claimed · Source date not stated · Retrieved 2026-10-21
onAI public product and pricing page onai:public-images
Image Studio advertises GPT Image, Nano Banana Pro, Imagen 4 and FLUX.3, up to three models per prompt, upload editing, per-image estimated costs and administrator controls.
Every leading image model in one studio; Compare side by side; Edit in plain words; Run by your admins · vendor-claimed · Source date not stated · Retrieved 2026-10-21
onAI public product and pricing page onai:public-image-rights
The vendor says generated images may be used commercially; provider-specific output terms are not supplied.
Every leading image model in one studio > commercial use · vendor-claimed · Source date not stated · Retrieved 2026-10-21
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
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
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
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
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
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
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
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
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
onAI public product and pricing page onai:public-pricing-display-20261026
Published EUR pricing is 17 per user/month with 5 of monthly model budget; a flat annual price is on request, with unlimited users and dedicated/on-premises options.
Pay per seat, or one price for everyone > Per seat; Flat price; prices excluding VAT; re-retrieved 2026-10-26, public web-reader representation SHA256 f2b7d5764994efe8fb87021fe13d7295155dd04ec09c8ed7826fcb52acc42b19 · vendor-claimed · Source date not stated · Retrieved 2026-10-26
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
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
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
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
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
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
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
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
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
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
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
onAI live general privacy and contract-request copy onai:review-contract-plan-gaps
General no-training, optional zero-retention and DPA/AI Act copy is published outside the plan cards, without a retrieved contract or eligibility mapping to Per seat and Flat price.
No training on your data; EU-only processing on request; Everything your data protection officer will ask for; Request the DPA; Per seat/Flat price cards · vendor-claimed · Source date not stated · Retrieved 2026-10-21
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
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
onAI public product and pricing page onai:public-compliance-display-20261026
The vendor advertises a DPA, a public subprocessor list, retention periods and AI Act labels, but the DPA link opens contact rather than the documents.
Everything your data protection officer will ask for; Swiss contract, two laws; re-retrieved 2026-10-26, public web-reader representation SHA256 f2b7d5764994efe8fb87021fe13d7295155dd04ec09c8ed7826fcb52acc42b19 · vendor-claimed · Source date not stated · Retrieved 2026-10-26
onAI imprint onai:public-imprint-display-20261026
The imprint identifies Telesoft AG in Oberwil-Lieli, Switzerland and Swiss VAT number CHE-106.160.588.
Contact; Represented by; VAT number; re-retrieved 2026-10-26, public web-reader representation SHA256 fcb4521fcdfb47e2ab714fee34a0fae0c1bdebca90481980bb3cb136410908fd · documented · Source date not stated · Retrieved 2026-10-26
onAI website privacy policy onai:public-website-privacy-display-20261026
The policy expressly covers the marketing website, including website processors and retention; it does not establish product workspace processor or retention terms.
Last updated October 2026; introductory scope; sections 5, 6 and 9; re-retrieved 2026-10-26, public web-reader representation SHA256 42ebec9df5cca263fd029ce2dcd8195487b6ee8e72cff07a6431731d8d462ec4 · documented · Source date not stated · Retrieved 2026-10-26
onAI imprint onai:public-imprint
The imprint identifies Telesoft AG in Oberwil-Lieli, Switzerland and Swiss VAT number CHE-106.160.588.
Contact; Represented by; VAT number · documented · Source date not stated · Retrieved 2026-10-21
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
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
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
onAI automation and open interfaces onai:onai:public-automation-status-20261026
The homepage labels its own workflow engine and MCP coming soon. Until then it describes n8n integration operated by onAI, the customer or a partner, with custom workflows as a requested service. No native release date or schedule/trigger entitlement is published.
Automation platform, Open interfaces and service sections; HTTP 200, body SHA256 a074779dc4d08c5e48440218bbc01353565673585b9e0f7eab517ed9687b77fa · vendor-claimed · Source date not stated · Retrieved 2026-10-26
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
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
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
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
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
onAI public product and pricing page onai:public-processing
The vendor claims no model training, filtered search/image prompts and an optional EU-only processing tier with provider zero retention; contracts and provider exceptions are not supplied.
What leaves, and how > No training; Personal data; European AI; EU-only processing on request · vendor-claimed · Source date not stated · Retrieved 2026-10-21
onAI public product and pricing page onai:public-pricing
Published EUR pricing is 17 per user/month with 5 of monthly model budget; a flat annual price is on request, with unlimited users and dedicated/on-premises options.
Pay per seat, or one price for everyone > Per seat; Flat price; prices excluding VAT · vendor-claimed · Source date not stated · Retrieved 2026-10-21
ECB euro reference exchange rates onai:ecb-fx
On 2026-10-20 one EUR equals USD 1.1215 and CHF 0.9237; USD to EUR is the reciprocal, 0.8916629514043692.
Cube time=2026-10-20; currency USD and CHF · documented · Source date 2026-10-20 · Retrieved 2026-10-21
onAI live pricing: named Microsoft 365 plan scope onai:review-plan-m365
The Per seat card expressly includes Microsoft 365 answers and the Flat price card includes everything in Per seat; the cards do not establish separate DPA, provider-retention or support entitlements.
Per seat > Answers from Microsoft 365, with each user’s own permissions; Flat price > Everything in Per seat, for every employee · vendor-claimed · Source date not stated · Retrieved 2026-10-21
onAI live residency statements and external processing paths onai:review-residency-parts
The page separately describes European application/storage infrastructure, named dedicated locations, external AI/search/image/translation services and an optional EU-only AI-processing tier; its unqualified secured-EU-server line does not establish default end-to-end processing, backup, log or support-access residency.
Ready for your security review; European from the contract down to the DNS; Where your data lives; External services, filtered; EU-only processing on request; pricing cards · vendor-claimed · Source date not stated · Retrieved 2026-10-21
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
onAI public product and pricing page onai:public-services
The vendor offers tailored training, workshops and custom agent services; Flat price lists onboarding, training and workshops without itemised service prices.
AI Trainings; AI Workshops; Custom AI Agent Development; Flat price inclusions · vendor-claimed · Source date not stated · Retrieved 2026-10-21
onAI live public status service scope onai:review-status-service-scope
The public status page lists Website and notice history; it does not identify a Per seat or Flat price workspace service or a contractual SLA.
Service list and recent notice history, retrieved 2026-10-21 · documented · Source date not stated · Retrieved 2026-10-21