Agent-readable comparison

AnythingLLM: sourced findings

Name: AnythingLLM: agent-readable findings
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.

AnythingLLM has sourced findings for 46 of 51 criteria, including 46 that a second agent cross-checked. "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.

AnythingLLM source checks: 2026-10-21 to 2026-10-26. Website: https://anythingllm.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.

AnythingLLM

Agent cross-checked Support: partial

The customer selects provider/model combinations at system, workspace and Agent level; optional routing can choose per message.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

providers: Documented integrations include OpenAI, Azure, Anthropic, Google, Bedrock, Mistral, Cohere, OpenRouter, LiteLLM and local servers. Actual selectable models require configured accounts/endpoints; no endpoint was exercised.
current_models: Which current models are selectable on this plan? A complete current selectable-model catalog was not captured from configured provider accounts.
auto_routing: Model Router supports ordered rules and a fallback model, including LLM-classified rules. A complete chosen-model display/test was not established.
multimodal_input: System/workspace routes can accept image input with compatible models; exact audio/file and per-model behavior was not tested.

providers Which model providers are available? [partial]: Documented integrations include OpenAI, Azure, Anthropic, Google, Bedrock, Mistral, Cohere, OpenRouter, LiteLLM and local servers. Actual selectable models require configured accounts/endpoints; no endpoint was exercised. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:llmconfig.
current_models Which current models are selectable on this plan? [unknown]: current_models: Which current models are selectable on this plan? A complete current selectable-model catalog was not captured from configured provider accounts.
user_choice Can users pick the model per chat? [supported]: System/workspace/Agent selections are configurable; the current built-in provider also has a chat model picker. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:built-in.
auto_routing Does the product route between models automatically, and is the chosen model shown? [partial]: Model Router supports ordered rules and a fallback model, including LLM-classified rules. A complete chosen-model display/test was not established. Sources: anythingllm:anythingllm:router.
multimodal_input Which models accept images, audio or files? [partial]: System/workspace routes can accept image input with compatible models; exact audio/file and per-model behavior was not tested. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:constants-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:built-in, anythingllm:anythingllm:router, anythingllm:anythingllm:constants-pin.

MOD-02 Model freshness

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

AnythingLLM

Agent cross-checked Support: partial

Dated releases and version-specific changelogs are public, but the three-release lag benchmark was not measured.

Limitations

release_lag_days: What was the lag for each of the last three major releases, per provider? No paired last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted.
deprecation_notice: How much notice is given before a model is removed? No paired last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted.
version_pinning: Operators choose remote model IDs or download local GGUF models. Provider retention of old remote snapshots is outside the application’s control.

release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted.
changelog Is there a dated public model changelog? [supported]: GitHub releases and Desktop changelogs document dated changes; v1.18.0 was published 2026-10-13. Sources: anythingllm:anythingllm:releases, anythingllm:anythingllm:changelog.
deprecation_notice How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired last-three-major-release availability dates or guaranteed model-deprecation notice window was established. The built-in Desktop engine migration removes old downloaded models when accepted.
version_pinning Can an admin keep an older model version? [partial]: Operators choose remote model IDs or download local GGUF models. Provider retention of old remote snapshots is outside the application’s control. Sources: anythingllm:anythingllm:generic, anythingllm:anythingllm:built-in.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:releases, anythingllm:anythingllm:changelog, anythingllm:anythingllm:generic, anythingllm:anythingllm:built-in.

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

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

AnythingLLM

Agent cross-checked Support: partial

BYO provider keys, customer cloud contracts and generic compatible endpoints are documented; provider spend is separate from software licensing.

Limitations

byo_restrictions: Tool use and modalities depend on provider/model support; Cloud has additional explicit platform limits. No universal BYO feature-parity guarantee was established.

own_api_keys Can the customer use its own provider API keys? [supported]: Customers configure credentials for their selected cloud providers. Managed Cloud also asks customers to bring an LLM API key. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud.
own_cloud_contract Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Azure OpenAI, AWS Bedrock and Vertex have distinct documented configuration routes using customer accounts. Sources: anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex.
custom_endpoint Can an admin add any OpenAI-compatible endpoint? [supported]: Generic OpenAI supports an operator-configured compatible provider URL and settings. Sources: anythingllm:anythingllm:generic.
byo_pricing Does BYO change the licence price? [supported]: The self-hosted repository is MIT with no per-seat fee; customer provider/hosting costs remain separate. Cloud charges for the managed instance and still uses BYO inference. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud.
byo_restrictions Which features stop working with BYO? [partial]: Tool use and modalities depend on provider/model support; Cloud has additional explicit platform limits. No universal BYO feature-parity guarantee was established. Sources: anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:models.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud, anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex, anythingllm:anythingllm:generic, anythingllm:anythingllm:license, anythingllm:anythingllm:cloud-limits.

MOD-04 Local and self-hosted models

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

AnythingLLM

Agent cross-checked Support: partial

Local chat and local CPU embeddings are documented; built-in-engine availability differs by client and release.

Limitations

feature_parity: Chat/RAG are local-capable, but tools and vision depend on model support and optional online services. Cloud explicitly has no bundled built-in LLM. No full offline fixture was run.
vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? No vendor-hosted open-weight model service with verified EU/Swiss inference was established.

self_hosted_chat Can chat use a customer-hosted model? [supported]: Ollama and other local providers work as configured endpoints. Desktop’s current built-in engine uses Lemonade/llama.cpp; Docker built-in is opt-in on the latest images and releases after v1.18.0 according to current docs. Sources: anythingllm:anythingllm:ollama, anythingllm:anythingllm:built-in.
self_hosted_embeddings Can retrieval use customer-hosted embeddings? [supported]: The built-in all-MiniLM-L6-v2 embedder runs locally on CPU; other local embedding routes are configurable. Sources: anythingllm:anythingllm:local-embed, anythingllm:anythingllm:embed.
feature_parity Which features fail with self-hosted models? [partial]: Chat/RAG are local-capable, but tools and vision depend on model support and optional online services. Cloud explicitly has no bundled built-in LLM. No full offline fixture was run. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:built-in.
vendor_hosted_open_models Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? No vendor-hosted open-weight model service with verified EU/Swiss inference was established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:ollama, anythingllm:anythingllm:built-in, anythingllm:anythingllm:local-embed, anythingllm:anythingllm:embed, anythingllm:anythingllm:models, anythingllm:anythingllm:cloud-limits.

MOD-05 Model control and usage limits

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

AnythingLLM

Agent cross-checked Support: partial

Workspace models and admin roles control settings; non-admin multi-user message quotas have a source-inspected blocking path.

Limitations

model_allowlist_by_group: Can admins limit models per group? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run.
data_bound_models: Can admins restrict which models receive connector or knowledge content? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run.

model_allowlist_by_group Can admins limit models per group? [unknown]: model_allowlist_by_group: Can admins limit models per group? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run.
data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A group-based model allow-list and hard source-data/provider-binding policy were not established in the role and workspace guides. No two-group quota or model restriction fixture was run.
default_model Can admins set the default model? [supported]: The system LLM is the default, overridden by workspace and Agent model configuration. Sources: anythingllm:anythingllm:llmconfig.
user_limits What per-user message or token limits apply, and are they published? [supported]: A dailyMessageLimit may be set per user, is system-wide across workspaces, uses a trailing 24-hour count and exempts admins; null means no limit in the inspected function. Sources: anythingllm:anythingllm:user-pin.
limit_behaviour What happens when a limit is reached? [supported]: Pinned chat endpoints send an abort/quota message and return before generation when the user cannot send another chat. Sources: anythingllm:anythingllm:chat-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:user-pin, anythingllm:anythingllm:chat-pin.

Company knowledge

KNOW-01 Files in chat

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

AnythingLLM

Agent cross-checked Support: partial

Files can enter full context or workspace RAG; converters and a PDF OCR fallback are present, with fidelity untested.

Limitations

limits: What size and count limits apply per file and chat? No universal file/count limit was established across these deployments. Cloud documents CPU/memory limits, but they do not define a tested per-file allowance. Shared long/scanned/Excel/PowerPoint fixtures were not uploaded.
ocr: The PDF implementation attempts OCR when initial text extraction returns no pages. No scanned contract or mixed-content PDF was tested.
spreadsheets: XLSX conversion is registered and v1.18.0 reports spreadsheet parsing fixes; preservation of formula semantics and layout was not tested.

formats Which formats are accepted? [supported]: Pinned converters register PDF, DOCX, PPTX, XLSX, EPUB, text/CSV/JSON, image and audio formats. Legacy DOC is not in the active registered converter map. Sources: anythingllm:anythingllm:constants-pin.
limits What size and count limits apply per file and chat? [unknown]: limits: What size and count limits apply per file and chat? No universal file/count limit was established across these deployments. Cloud documents CPU/memory limits, but they do not define a tested per-file allowance. Shared long/scanned/Excel/PowerPoint fixtures were not uploaded.
ocr Are scanned PDFs read? [partial]: The PDF implementation attempts OCR when initial text extraction returns no pages. No scanned contract or mixed-content PDF was tested. Sources: anythingllm:anythingllm:pdf-pin.
spreadsheets Are Excel tables read with structure intact? [partial]: XLSX conversion is registered and v1.18.0 reports spreadsheet parsing fixes; preservation of formula semantics and layout was not tested. Sources: anythingllm:anythingllm:constants-pin, anythingllm:anythingllm:changelog.
full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [supported]: Current attachment mode injects full extracted text. On context overflow the UI offers cancellation, pruning or embedding; embedded documents retrieve chunks and become workspace-wide. Sources: anythingllm:anythingllm:docchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:constants-pin, anythingllm:anythingllm:pdf-pin, anythingllm:anythingllm:changelog, anythingllm:anythingllm:docchat.

KNOW-02 Knowledge bases and shared collections

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

AnythingLLM

Agent cross-checked Support: partial

Workspace embeddings persist across chats and are shared with every authorized workspace user.

Limitations

size_limits: What are the collection limits? No fixed collection storage allowance was established; capacity depends on local hardware or managed-instance tier.

persistent_collections Can users keep document collections across chats? [supported]: Embedding a document into a workspace makes it reusable across that workspace’s threads. Sources: anythingllm:anythingllm:docchat.
sharing_scope Can collections be shared with users, groups or the whole organisation? [supported]: In Docker multi-user mode, assigned workspace users can use its embedded documents. Admin/Manager roles have broader access; per-original-source ACLs were not established. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:security.
size_limits What are the collection limits? [unknown]: size_limits: What are the collection limits? No fixed collection storage allowance was established; capacity depends on local hardware or managed-instance tier.
assistant_binding Can collections be bound to an assistant? [supported]: Each workspace has configurable chat/Agent models and its embedded knowledge. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:docchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:security, anythingllm:anythingllm:llmconfig.

KNOW-03 Enterprise connectors

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

AnythingLLM

Agent cross-checked Support: partial

The source registers import connectors and SQL tools. Mail integrations are single-user features, not verified enterprise multi-user content search.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Source-specific credentials/registrations, Mail skills require single-user mode; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

microsoft_365: An Outlook skill searches/reads/modifies the connected mailbox, but is explicitly single-user only. SharePoint, OneDrive and Teams connectors were not verified for the multi-user deployment.
google_workspace: The Gmail skill is single-user only. A maintained Google Drive enterprise connector and source ACL sync were not verified.
atlassian: The pinned connector catalog includes Confluence import. Jira was not established and Confluence per-user permission synchronization was not tested.
other_systems: The connector catalog includes GitHub/GitLab/Gitea, websites, YouTube, Obsidian and other import sources; registration does not establish tested source access controls.
on_prem_sources: Self-hosted deployments can upload files and connect the SQL Agent to a reachable database. Automatic local-file watching is Desktop-only, not Docker browser upload.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: An Outlook skill searches/reads/modifies the connected mailbox, but is explicitly single-user only. SharePoint, OneDrive and Teams connectors were not verified for the multi-user deployment. Sources: anythingllm:anythingllm:outlook.
google_workspace Which Google sources are connected? [partial]: The Gmail skill is single-user only. A maintained Google Drive enterprise connector and source ACL sync were not verified. Sources: anythingllm:anythingllm:gmail.
atlassian Confluence and Jira? [partial]: The pinned connector catalog includes Confluence import. Jira was not established and Confluence per-user permission synchronization was not tested. Sources: anythingllm:anythingllm:connectors-pin, anythingllm:anythingllm:sync.
other_systems Which other business systems? [partial]: The connector catalog includes GitHub/GitLab/Gitea, websites, YouTube, Obsidian and other import sources; registration does not establish tested source access controls. Sources: anythingllm:anythingllm:connectors-pin.
on_prem_sources Can on-prem file shares or databases be connected? [partial]: Self-hosted deployments can upload files and connect the SQL Agent to a reachable database. Automatic local-file watching is Desktop-only, not Docker browser upload. Sources: anythingllm:anythingllm:sql, anythingllm:anythingllm:sync, anythingllm:anythingllm:localdocker.
connector_provider Who builds and maintains each connector? [supported]: These are built-in Mintplex project skills/import modules; third-party MCP servers remain separately maintained integrations. Sources: anythingllm:anythingllm:connectors-pin, anythingllm:anythingllm:outlook, anythingllm:anythingllm:gmail, anythingllm:anythingllm:mcp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:outlook, anythingllm:anythingllm:gmail, anythingllm:anythingllm:connectors-pin, anythingllm:anythingllm:sync, anythingllm:anythingllm:sql, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:mcp.

KNOW-04 Permission-aware retrieval

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

AnythingLLM

Agent cross-checked Support: partial

Workspace access is enforced as the product sharing boundary; original source permissions after copying remain unverified.

Limitations

source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown.
enforcement_point: Default users only access assigned workspaces, and an embedded file becomes available to every user assigned to its workspace. Continuing source-system ACL checks were not established.
revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown.
admin_scope_controls: Admins control workspace membership and selected documents. Source site/folder/sensitivity-label exclusion was not established.
sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown.

source_permissions_respected Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [partial]: Default users only access assigned workspaces, and an embedded file becomes available to every user assigned to its workspace. Continuing source-system ACL checks were not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat.
revocation_delay How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown.
admin_scope_controls Can admins exclude sites, folders or labels? [partial]: Admins control workspace membership and selected documents. Source site/folder/sensitivity-label exclusion was not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat.
sensitivity_labels Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation propagation test was run. Purview label enforcement and source ACL fidelity remain unknown.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat.

KNOW-05 Freshness and sync model

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

AnythingLLM

Agent cross-checked Support: partial

Knowledge is a copied index. Automatic source refresh is preview and differs between remote sources and Desktop local files.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Live document sync preview explicitly enabled for automatic refresh; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

Automatic sync is a preview, not a guaranteed freshness SLA.
No source edit/delete timing fixture was run.

live_or_indexed Is content searched live or copied into an index? [supported]: Embedded knowledge copies parsed chunks into the selected vector store; attachments instead inject extracted text. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:vector.
sync_interval How often does an index refresh? [partial]: Preview watched remote sources are checked hourly for staleness, defined as no refresh in seven days; Desktop local watched files are checked every ten minutes while running. No latency fixture was run. Sources: anythingllm:anythingllm:sync.
deletion_propagation How quickly does a deleted document disappear? [partial]: Deleting a watched local original marks it Not Found and unwatches it while retaining existing content/embeddings. System deletion must be explicit; remote-source deletion timing was not established. Sources: anythingllm:anythingllm:sync, anythingllm:anythingllm:privacy.
index_location Where is indexed content stored? [supported]: Self-hosting selects the configured local or external vector store and its country. Default local storage is distinct from any selected cloud database. Sources: anythingllm:anythingllm:vector, anythingllm:anythingllm:localdocker.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:docchat, anythingllm:anythingllm:vector, anythingllm:anythingllm:sync, anythingllm:anythingllm:privacy, anythingllm:anythingllm:localdocker.

KNOW-06 Grounding and retrieval quality

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

AnythingLLM

Agent cross-checked Support: partial

The client renders source citations and Query mode documents a no-relevant-content response; quality is untested.

Limitations

citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained.
cross_language: Does a question in one language find documents in another? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained.
no_answer_behaviour: Query mode documentation says it reports when no relevant information is found. This is documented behavior, not a passed no-answer fixture.
observed_accuracy: How many of the question set were answered correctly? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained.

citations Are answers linked to specific sources? [supported]: Pinned client code renders document/link citation details and source metadata. Sources: anythingllm:anythingllm:citation-pin.
citation_accuracy Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained.
cross_language Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained.
no_answer_behaviour Does it say when the corpus has no answer? [partial]: Query mode documentation says it reports when no relevant information is found. This is documented behavior, not a passed no-answer fixture. Sources: anythingllm:anythingllm:chatmodes.
observed_accuracy How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared DE/FR/EN factual/cross-document/no-answer corpus was not run. Citation correctness, link accuracy, cross-language retrieval and numerical observed accuracy remain unknown; the default embedder is primarily English-trained.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:citation-pin, anythingllm:anythingllm:chatmodes.

KNOW-07 Memory and personal context

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

AnythingLLM

Agent cross-checked Support: supported

Opt-in personalization stores private global/workspace memories with user controls and admin enablement.

custom_instructions Can users set persistent instructions? [supported]: Workspaces keep model/system instructions and may include user/time variables. Sources: anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig.
cross_chat_memory Does the product remember facts across chats? [supported]: User memories apply across chats within a workspace or globally; limits are 20 workspace and five global memories per user. Sources: anythingllm:anythingllm:memory.
user_memory_controls Can users view, edit and delete memories? [supported]: Users can add, edit, delete and move memories; selected memories are sent to the configured model in the system prompt. Sources: anythingllm:anythingllm:memory.
admin_memory_controls Can admins turn memory off? [supported]: Memories are off by default; in multi-user mode only admins enable/disable personalization. Sources: anythingllm:anythingllm:memory.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:memory.

Assistants and agents

AGT-01 Custom assistants

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

AnythingLLM

Agent cross-checked Support: partial

Workspaces combine instructions, a model, knowledge and configured Agent skills; a distinct shareable assistant object/catalog was not fully established.

Limitations

creator_permissions: Admin/Manager roles manage workspaces; Default users only chat in assigned workspaces. A separate assistant-creator permission matrix was not established.
sharing_scope: Docker workspaces can be assigned to users; Desktop is single-user. Group/everyone assistant-sharing and versioned assistant publishing were not established.
catalogue: Is there an internal assistant directory? A complete internal assistant directory/versioning contract and the HR assistant fixture were not verified.
prompt_library: Workspace prompts and no-code Agent Flows can be reused, but a separate organization prompt-template catalog was not verified.

create_assistants Can users create assistants with instructions, knowledge and tools? [supported]: Workspace and Agent settings combine a model, instructions, embedded knowledge and enabled skills/tools. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:docchat.
creator_permissions Can admins limit who creates them? [partial]: Admin/Manager roles manage workspaces; Default users only chat in assigned workspaces. A separate assistant-creator permission matrix was not established. Sources: anythingllm:anythingllm:security.
sharing_scope Can assistants be shared with users, groups or everyone? [partial]: Docker workspaces can be assigned to users; Desktop is single-user. Group/everyone assistant-sharing and versioned assistant publishing were not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:desktop.
catalogue Is there an internal assistant directory? [unknown]: catalogue: Is there an internal assistant directory? A complete internal assistant directory/versioning contract and the HR assistant fixture were not verified.
prompt_library Are shared prompt templates available? [partial]: Workspace prompts and no-code Agent Flows can be reused, but a separate organization prompt-template catalog was not verified. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:systemprompt.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:llmconfig, anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:docchat, anythingllm:anythingllm:security, anythingllm:anythingllm:desktop, anythingllm:anythingllm:flow, anythingllm:anythingllm:systemprompt.

AGT-02 Tools, actions and MCP

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

AnythingLLM

Agent cross-checked Support: partial

Self-hosted/desktop supports built-in skills, API-call flows and MCP. Managed Cloud explicitly excludes custom coded Agents and MCP.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Separate MCP servers or custom skill configuration, Mail integrations require single-user mode; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

Cloud does not support MCP or custom coded Agents.
Single-user mail approvals do not establish a complete multi-user side-effect policy.

builtin_tools Which tools are built in? [supported]: Skills include RAG/document search, web browsing, chart/document generation and SQL; single-user mail skills have a narrower scope. Sources: anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:sql, anythingllm:anythingllm:docgen, anythingllm:anythingllm:chart, anythingllm:anythingllm:outlook.
custom_actions Can admins add API actions? [supported]: No-code flows provide an API-call block and custom skills can be developed for self-hosted/desktop; Cloud excludes custom coded Agents. Sources: anythingllm:anythingllm:flow-api, anythingllm:anythingllm:cloud-limits.
mcp_client Can it use remote MCP servers, and with what admin control? [partial]: Self-hosted/desktop supports stdio, SSE and Streamable remote MCP with management controls. Managed Cloud explicitly does not support MCP. Sources: anythingllm:anythingllm:mcp, anythingllm:anythingllm:cloud-limits.
tool_auth Do tools act as the user or as a shared account? [partial]: MCP accepts environment variables/HTTP headers; single-user Outlook uses delegated Entra authorization. A general per-user OAuth model for every multi-user tool was not established. Sources: anythingllm:anythingllm:mcp, anythingllm:anythingllm:outlook.
tool_approval Can admins approve or block tools, and can users confirm actions before they run? [partial]: Outlook/Gmail modifying actions explicitly require approval in single-user mode. A mandatory approval policy for every custom/MCP action was not verified. Sources: anythingllm:anythingllm:outlook, anythingllm:anythingllm:gmail, anythingllm:anythingllm:mcp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:sql, anythingllm:anythingllm:docgen, anythingllm:anythingllm:chart, anythingllm:anythingllm:outlook, anythingllm:anythingllm:flow-api, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:mcp, anythingllm:anythingllm:gmail.

AGT-03 Web search and deep research

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

AnythingLLM

Agent cross-checked Support: partial

The web-browsing skill supports explicit search-provider configuration. This claim covers the pinned self-hosted DuckDuckGo route; it makes no assertion about an unconfigured default.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Self-hosted v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, explicitly configured agent_search_provider=duckduckgo-engine; plan=MIT self-hosted deployment with an explicitly selected DuckDuckGo provider; auto-selected defaults, Desktop and managed Cloud defaults are outside this claim; add_ons=Enabled web-browsing skill; explicit agent_search_provider=duckduckgo-engine setting; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

The scope is an explicitly configured provider at one release pin, not an assertion about default routing in other installations.
Search queries leave the application for the selected external endpoint; processing region and a per-group enforcement fixture were not established.
Dedicated research-report quality and citation completeness remain untested.

web_search Is web search available? [supported]: The Agent web-browsing skill can search the web; this scoped self-hosted configuration explicitly selects the DuckDuckGo engine. Sources: anythingllm:anythingllm:browsing, anythingllm:anythingllm:search-configured-r2.
admin_toggle Can admins disable it per organisation or group? [partial]: The documented Agent Skills settings and chat prompt controls toggle skills. Separate per-group web-search enforcement under the standard role model was not established. Sources: anythingllm:anythingllm:agent-skills-r2, anythingllm:anythingllm:security.
search_provider Which search provider handles queries, and where? [partial]: At the pinned v1.18.0 revision, explicit agent_search_provider=duckduckgo-engine invokes _duckDuckGoEngine and sends the query to html.duckduckgo.com/html. Query processing country and a CH/EU residency commitment were not verified. Unconfigured defaults are outside this finding. Sources: anythingllm:anythingllm:search-configured-r2.
deep_research Is multi-step research with a report available? [partial]: Agent tools/flows can chain research steps; a dedicated tested report workflow and accuracy result were not established. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:agent-usage.
web_citations Are web sources cited? [partial]: The client renders source citations including links; correctness and completeness of web-source citations were not tested. Sources: anythingllm:anythingllm:citation-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:browsing, anythingllm:anythingllm:search-configured-r2, anythingllm:anythingllm:agent-skills-r2, anythingllm:anythingllm:security, anythingllm:anythingllm:flow, anythingllm:anythingllm:agent-usage, anythingllm:anythingllm:citation-pin.

AGT-04 Workflows and automation

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

AnythingLLM

Agent cross-checked Support: partial

No-code Agent Flows are available on Docker/Desktop. Scheduled Jobs are explicitly single-user only.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Scheduled Jobs require single-user mode; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

scheduled_tasks: Scheduled Jobs run recurring Agent prompts with cron, tool allow-lists and saved traces in single-user mode. They are unavailable in self-hosted multi-user mode.
event_triggers: Can external events start a workflow? A maintained incoming email/form/business-system event-trigger contract was not established; an API call alone is not a named trigger integration.

workflow_builder Is there a workflow or chain builder? [supported]: The visual flow editor builds reusable agentic skills with steps such as API calls, scraping and file operations. Sources: anythingllm:anythingllm:flow.
scheduled_tasks Can prompts or assistants run on a schedule? [partial]: Scheduled Jobs run recurring Agent prompts with cron, tool allow-lists and saved traces in single-user mode. They are unavailable in self-hosted multi-user mode. Sources: anythingllm:anythingllm:job.
event_triggers Can external events start a workflow? [unknown]: event_triggers: Can external events start a workflow? A maintained incoming email/form/business-system event-trigger contract was not established; an API call alone is not a named trigger integration.
builder_audience Is building aimed at business users, IT or developers? [supported]: Flows target non-coders; custom skill code targets technical users and developers. Sources: anythingllm:anythingllm:flow.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:job.

AGT-05 Agentic task execution

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

AnythingLLM

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.

AGT-06 Programmable access

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

AnythingLLM

Agent cross-checked Support: partial

Instance APIs manage workspaces, upload/embed content and run chats using provisioned API keys.

Limitations

api_governance: API keys are provisioned by authorized accounts and confer access to their holder. Full UI/API quota, model, audit and per-user boundary parity was not tested.
mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established from the client-MCP and API guides.

chat_api Is there an API for chat and assistants? [supported]: The documented developer API supports workspace management and chat, with instance OpenAPI docs at /api/docs. Sources: anythingllm:anythingllm:api.
knowledge_api Can documents be loaded through an API? [supported]: The developer API documents embedding/document management alongside workspace operations. Sources: anythingllm:anythingllm:api.
api_governance Do audit, budgets and model rules apply to API use? [partial]: API keys are provisioned by authorized accounts and confer access to their holder. Full UI/API quota, model, audit and per-user boundary parity was not tested. Sources: anythingllm:anythingllm:api, anythingllm:anythingllm:config.
mcp_server Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established from the client-MCP and API guides.

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

Daily work

WORK-01 Clients and access points

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

AnythingLLM

Agent cross-checked Support: partial

Docker serves a browser client, Desktop has native installers and Mobile is Android-only; these are different access/governance modes.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Mobile for Android, AnythingLLM browser content collection extension; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=Windows, macOS, Linux, Android.

Limitations

mobile_apps: A separate free Android app can run local models or pair with Desktop/Cloud/self-hosted servers. iOS and a tested native company-SSO flow were not established.
managed_deployment: Windows silent installer switches are documented for scripted/MDM packaging. Current User install is required; all-users install is unsupported and Enterprise/Server OS use has caveats. No Intune deployment was tested.

web Is a full web client available? [supported]: Docker provides the browser-accessible multi-user UI; Desktop network discovery exposes API endpoints rather than a web UI. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:docker.
desktop_apps Windows and macOS apps? [supported]: Desktop installers support Windows, macOS and Linux; the app is single-user rather than a shared company-login client. Sources: anythingllm:anythingllm:desktop.
mobile_apps iOS and Android apps with SSO? [partial]: A separate free Android app can run local models or pair with Desktop/Cloud/self-hosted servers. iOS and a tested native company-SSO flow were not established. Sources: anythingllm:anythingllm:mobile.
browser_extension Is there a browser extension or sidebar? [supported]: A content collection extension supports Chrome/Edge/Brave/Firefox and connects with an instance API key. Sources: anythingllm:anythingllm:ext.
managed_deployment Can IT deploy and configure clients through MDM? [partial]: Windows silent installer switches are documented for scripted/MDM packaging. Current User install is required; all-users install is unsupported and Enterprise/Server OS use has caveats. No Intune deployment was tested. Sources: anythingllm:anythingllm:windows.
client_feature_gaps Which features are missing on mobile? [supported]: Desktop lacks multi-user/workspace administration; Android is a separate local/pairing client; Desktop-only meeting features currently target Windows/macOS. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:mobile, anythingllm:anythingllm:meeting-intro.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:docker, anythingllm:anythingllm:mobile, anythingllm:anythingllm:ext, anythingllm:anythingllm:windows, anythingllm:anythingllm:meeting-intro.

WORK-02 Office suite and Teams integration

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

AnythingLLM

No public information found Support: not-published

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

WORK-03 Translation and writing

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

AnythingLLM

Agent cross-checked Support: partial

Optional Desktop Magic tools support system-wide rewriting, but layout-preserving translation and company glossary controls remain unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=Desktop free Magic allowances; optional Desktop Pro; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=Windows, macOS.

Limitations

document_translation: Can whole documents be translated with formatting kept? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified.
translation_engine: Generative rewrite work uses the selected model. A dedicated document translation engine/workflow was not established.
glossaries: Are company glossaries supported? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified.
formality_and_variants: Can formality and regional variants (de-CH) be set? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified.

document_translation Can whole documents be translated with formatting kept? [unknown]: document_translation: Can whole documents be translated with formatting kept? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified.
translation_engine Which engine translates? [partial]: Generative rewrite work uses the selected model. A dedicated document translation engine/workflow was not established. Sources: anythingllm:anythingllm:pro, anythingllm:anythingllm:llmconfig.
glossaries Are company glossaries supported? [unknown]: glossaries: Are company glossaries supported? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified.
formality_and_variants Can formality and regional variants (de-CH) be set? [unknown]: formality_and_variants: Can formality and regional variants (de-CH) be set? No whole-contract DE-to-FR/IT formatting test, company glossary, formality/de-CH control or dedicated layout-preserving translation service was verified.
writing_tools Are dedicated rewrite and proofreading tools available? [supported]: Desktop Magic Echo/Beacon/Tab offer dictation cleanup, selected-text revision and writing completion, with free allowances and optional Desktop Pro. Sources: anythingllm:anythingllm:pro.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:pro, anythingllm:anythingllm:llmconfig.

WORK-04 Image generation and editing

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

AnythingLLM

Agent cross-checked Support: partial

Configured image providers generate pictures and can edit references where supported.

Limitations

image_editing: OpenAI/OpenRouter and compatible Lemonade models use reference-image editing. The documented Ollama route drops image references and generates from text only.
admin_control: Admins configure provider credentials and model. A separate per-group image-generation cost/permission policy was not established.
usage_terms: What usage rights apply to output? Output rights and complete per-image cost visibility depend on the model/provider contract and were not established here.

image_generation Can users generate images, with which models? [supported]: The /img command uses configured OpenAI, OpenRouter, Ollama or Lemonade providers and an operator-selected model. Sources: anythingllm:anythingllm:images.
image_editing Can users edit uploaded images? [partial]: OpenAI/OpenRouter and compatible Lemonade models use reference-image editing. The documented Ollama route drops image references and generates from text only. Sources: anythingllm:anythingllm:images.
admin_control Can admins restrict image generation? [partial]: Admins configure provider credentials and model. A separate per-group image-generation cost/permission policy was not established. Sources: anythingllm:anythingllm:images, anythingllm:anythingllm:security.
usage_terms What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Output rights and complete per-image cost visibility depend on the model/provider contract and were not established here.

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

WORK-05 Voice and meetings

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

AnythingLLM

Agent cross-checked Support: partial

Audio transcription/read-aloud are configurable. Free meeting capture and local transcription are Desktop-only on Windows/macOS.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Desktop-only Meeting Assistant; downloaded transcription models, Optional provider-specific audio services; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

dictation: Transcription providers and Desktop Magic Echo support spoken input; exact supported dialects and a shared dictation fixture were not verified.
voice_conversation: Is a live voice mode available? No continuous live conversational voice mode or Swiss German recognition quality was verified.
swiss_german_speech: Is Swiss German speech recognised? No continuous live conversational voice mode or Swiss German recognition quality was verified.

dictation Can users dictate prompts? [partial]: Transcription providers and Desktop Magic Echo support spoken input; exact supported dialects and a shared dictation fixture were not verified. Sources: anythingllm:anythingllm:stt, anythingllm:anythingllm:pro.
read_aloud Can answers be read aloud? [supported]: System-native, local/browser Piper, self-hosted Kokoro and cloud TTS routes are documented; the chosen engine determines processing. Sources: anythingllm:anythingllm:tts.
voice_conversation Is a live voice mode available? [unknown]: voice_conversation: Is a live voice mode available? No continuous live conversational voice mode or Swiss German recognition quality was verified.
meeting_summaries Are meetings transcribed and summarised? [supported]: Desktop Meeting Assistant records/imports meetings, transcribes locally and summarizes with the chosen local/cloud model. A cloud summary sends the transcript to that provider; Linux is not currently supported. Sources: anythingllm:anythingllm:meeting-intro, anythingllm:anythingllm:meeting.
swiss_german_speech Is Swiss German speech recognised? [unknown]: swiss_german_speech: Is Swiss German speech recognised? No continuous live conversational voice mode or Swiss German recognition quality was verified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:stt, anythingllm:anythingllm:pro, anythingllm:anythingllm:tts, anythingllm:anythingllm:meeting-intro, anythingllm:anythingllm:meeting.

WORK-06 Data analysis and document output

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

AnythingLLM

Agent cross-checked Support: partial

Built-in Agent skills generate charts and downloadable Office/PDF documents; executed spreadsheet analysis and iterative canvas editing were not tested.

Limitations

data_analysis: Can it analyse spreadsheets with executed code? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter.
canvas_editing: Is there a document or canvas editor for iterating on output? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter.

data_analysis Can it analyse spreadsheets with executed code? [unknown]: data_analysis: Can it analyse spreadsheets with executed code? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter.
charts Can it produce charts? [supported]: An enabled chart skill creates charts from prompts or workspace data. Sources: anythingllm:anythingllm:chart.
office_file_output Can it create Word, Excel or PowerPoint files? [supported]: The built-in Document Generation skill lists text, PDF, Excel, DOCX and PowerPoint outputs; the guide recommends capable models for PowerPoint. Sources: anythingllm:anythingllm:docgen.
canvas_editing Is there a document or canvas editor for iterating on output? [unknown]: canvas_editing: Is there a document or canvas editor for iterating on output? No shared spreadsheet execution/formula analysis, editable PowerPoint fidelity or document-canvas fixture was run. Built-in chart creation does not establish a general code interpreter.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:chart, anythingllm:anythingllm:docgen.

WORK-07 Sharing and team spaces

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

AnythingLLM

Agent cross-checked Support: partial

Docker workspaces share knowledge with assigned users; shared live conversation behavior remains unverified.

Limitations

share_chats: Can chats be shared inside the organisation? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides.
group_chat: Can several people chat together with the AI? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides.
share_permission_boundary: Embedded files become accessible to every assigned workspace user; this does not preserve an arbitrary original source ACL. A cross-group chat-sharing fixture was not run.

share_chats Can chats be shared inside the organisation? [unknown]: share_chats: Can chats be shared inside the organisation? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides.
team_spaces Are shared projects or workspaces available? [supported]: Multi-user workspaces can be assigned to users, who share the embedded knowledge available there. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat.
group_chat Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Authenticated chat-share links, simultaneous multi-person AI conversation and recipient transcript/source visibility were not established by the workspace and chat-log guides.
share_permission_boundary Does sharing respect the recipient's access to sources? [partial]: Embedded files become accessible to every assigned workspace user; this does not preserve an arbitrary original source ACL. A cross-group chat-sharing fixture was not run. Sources: anythingllm:anythingllm:docchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:docchat.

WORK-08 Interface languages and accessibility

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

AnythingLLM

Agent cross-checked Support: partial

The pinned frontend registers English, German, French and Italian, with fallback behavior; translation quality and WCAG conformance remain unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=New code findings at v1.19.0 / 9b1fcab141000eaba9f78ed131151de04904454b (published 2026-10-26); earlier accepted facts retain their own pins; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

German administrator labels are present in pinned source; full German/French/Italian screen coverage and naturalness were not observed.
No WCAG conformance statement or full accessibility walkthrough was verified.

ui_languages Which UI languages are offered? [supported]: The locale implementation registers en, de, fr and it among other resources. Sources: anythingllm:anythingllm:i18n-pin.
dach_language_quality Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No full DE/FR/IT UI walkthrough, German admin-screen completeness review or WCAG conformance report was verified.
accessibility_statement Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No full DE/FR/IT UI walkthrough, German admin-screen completeness review or WCAG conformance report was verified.
admin_ui_languages Is the admin interface available in German? [partial]: The pinned German locale includes user management, invitations, event logs and administrator settings labels. Complete admin-screen coverage, translation quality and WCAG conformance were not observed. Sources: anythingllm:anythingllm:r4-german-admin.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: anythingllm:anythingllm:i18n-pin, anythingllm:anythingllm:r4-german-admin.

Administration and governance

ADM-01 Single sign-on and authentication

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

AnythingLLM

Agent cross-checked Support: partial

The standard Docker project documents a privileged simple-SSO passthrough; the commercial Enterprise offer advertises SSO without public protocol details.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Custom trusted login integration for Simple SSO, Quote-only Enterprise for the advertised SSO offer; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

sso_protocols: Simple SSO generates one-use temporary links for existing users through an API key. It is not evidence of built-in SAML/OIDC/LDAP federation; those protocol details were not verified.
sso_plan: Simple passthrough is documented for self-hosted multi-user mode. Quote-only Enterprise separately advertises SSO, with public protocol/feature scope unspecified.
mfa: Can MFA be enforced? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer.
conditional_access: Do Entra conditional-access policies apply? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer.
domain_capture: Can the company claim its email domain? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer.

sso_protocols Which SSO protocols and identity providers work? [partial]: Simple SSO generates one-use temporary links for existing users through an API key. It is not evidence of built-in SAML/OIDC/LDAP federation; those protocol details were not verified. Sources: anythingllm:anythingllm:config.
sso_plan Which plan includes SSO? [partial]: Simple passthrough is documented for self-hosted multi-user mode. Quote-only Enterprise separately advertises SSO, with public protocol/feature scope unspecified. Sources: anythingllm:anythingllm:config, anythingllm:anythingllm:cloud.
mfa Can MFA be enforced? [unknown]: mfa: Can MFA be enforced? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer.
conditional_access Do Entra conditional-access policies apply? [unknown]: conditional_access: Do Entra conditional-access policies apply? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer.
domain_capture Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? MFA enforcement, conditional-access compatibility and company-domain capture were not established from the standard authentication or public Enterprise offer.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:config, anythingllm:anythingllm:cloud.

ADM-02 User provisioning and lifecycle

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

AnythingLLM

Agent cross-checked Support: partial

Admins or API clients create users and assign workspaces; provisioning standards and leaver asset transfer remain unverified.

Limitations

scim: Is SCIM provisioning supported? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer.
group_sync: Are identity-provider groups synced? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer.
jit_provisioning: Simple SSO explicitly requires a user to exist before login; an external system can create the user through the API. This is custom provisioning, not a verified automatic IdP JIT flow.
deprovisioning: Admin routes implement user deletion and log the event. A fixture verifying chat/knowledge ownership transfer and active-session revocation was not run.

scim Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer.
group_sync Are identity-provider groups synced? [unknown]: group_sync: Are identity-provider groups synced? SCIM and identity-provider group synchronization were not established in the public configuration and Enterprise offer.
jit_provisioning Are users created at first login? [partial]: Simple SSO explicitly requires a user to exist before login; an external system can create the user through the API. This is custom provisioning, not a verified automatic IdP JIT flow. Sources: anythingllm:anythingllm:config.
deprovisioning What happens to a removed user's data and shared assets? [partial]: Admin routes implement user deletion and log the event. A fixture verifying chat/knowledge ownership transfer and active-session revocation was not run. Sources: anythingllm:anythingllm:admin-pin.
seat_assignment Can admins assign and reclaim seats? [supported]: Admins create/manage users and workspace membership under the no-seat-fee self-hosted licence. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:config, anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:security, anythingllm:anythingllm:license.

ADM-03 Roles, groups and feature permissions

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

AnythingLLM

Agent cross-checked Support: partial

Standard Docker multi-user governance uses Admin, Manager and Default roles plus workspace membership.

Limitations

groups: Can permissions be set per group? An independently configurable local/IdP group object and two-group permission fixture were not established.
feature_toggles: Operators configure available Agent skills, providers and workspaces. A fine-grained per-group feature matrix was not established for standard roles.
multi_entity: Workspaces separate access within one installation; legal-entity tenancy, separate operator boundaries and a multi-entity contract were not verified.

admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: Admins control the whole system; Managers manage workspaces but cannot change the system LLM/embedder/vector settings; Default users chat in assigned workspaces. Sources: anythingllm:anythingllm:security.
groups Can permissions be set per group? [unknown]: groups: Can permissions be set per group? An independently configurable local/IdP group object and two-group permission fixture were not established.
feature_toggles Which features can be switched on or off per group? [partial]: Operators configure available Agent skills, providers and workspaces. A fine-grained per-group feature matrix was not established for standard roles. Sources: anythingllm:anythingllm:agent-setup, anythingllm:anythingllm:security.
multi_entity Can subsidiaries or departments be separated within one contract? [partial]: Workspaces separate access within one installation; legal-entity tenancy, separate operator boundaries and a multi-entity contract were not verified. Sources: anythingllm:anythingllm:security.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:agent-setup.

ADM-04 Usage and adoption analytics

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

AnythingLLM

Agent cross-checked Support: partial

Authorized accounts can inspect chat/event activity and export chat logs; a full adoption/cost dashboard was not verified.

Limitations

adoption_dashboard: Is there an adoption dashboard? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow.
breakdowns: Chat logs are available per workspace/user to authorized accounts; complete model/feature/assistant/group adoption breakdowns were not established.
privacy_modes: Can per-person reporting be limited or pseudonymised? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow.

adoption_dashboard Is there an adoption dashboard? [unknown]: adoption_dashboard: Is there an adoption dashboard? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow.
breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Chat logs are available per workspace/user to authorized accounts; complete model/feature/assistant/group adoption breakdowns were not established. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:event.
export Can usage data be exported? [supported]: Chat logs export as CSV, JSON, Alpaca JSON or OpenAI-style JSONL once at least ten logs exist. Sources: anythingllm:anythingllm:logs.
privacy_modes Can per-person reporting be limited or pseudonymised? [unknown]: privacy_modes: Can per-person reporting be limited or pseudonymised? A dedicated adoption dashboard and pseudonymized/aggregated per-person reporting controls were not established; optional anonymous product telemetry is a separate data flow.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:event.

ADM-05 Spend controls and cost allocation

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

AnythingLLM

Agent cross-checked Support: partial

Per-user message quotas control consumption; monetary budgets and cost-centre allocation were not established.

Limitations

cost_visibility: Authorized users see chat activity by workspace/user. The reviewed sources do not establish actual billed currency cost by group.
budgets: Admins can set per-user daily message quotas. This is a count limit, not a documented CHF/EUR budget or pooled cost-centre allowance.
chargeback: Can costs be exported per cost centre? Monetary spend caps, model downgrades and cost-centre chargeback export were not verified.

cost_visibility Can admins see cost or consumption per user and group? [partial]: Authorized users see chat activity by workspace/user. The reviewed sources do not establish actual billed currency cost by group. Sources: anythingllm:anythingllm:logs.
budgets Can budgets be set per user or group? [partial]: Admins can set per-user daily message quotas. This is a count limit, not a documented CHF/EUR budget or pooled cost-centre allowance. Sources: anythingllm:anythingllm:user-pin.
budget_enforcement Does reaching a budget alert, block or downgrade? [supported]: The inspected non-admin multi-user chat route aborts before generation when the trailing-24-hour message quota is reached. Sources: anythingllm:anythingllm:chat-pin, anythingllm:anythingllm:user-pin.
chargeback Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Monetary spend caps, model downgrades and cost-centre chargeback export were not verified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:user-pin, anythingllm:anythingllm:chat-pin.

ADM-06 Audit logs and compliance export

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

AnythingLLM

Agent cross-checked Support: partial

Event logs record named administrative/security activity and chats are exportable. Immutable audit retention and legal hold remain unverified.

Limitations

siem_export: Can logs stream to a SIEM or be exported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive.
ediscovery: Are eDiscovery and legal hold supported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive.
log_retention: How long are logs kept? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive.

admin_events Are admin and security events logged? [supported]: Pinned admin routes log user creation/deletion, invitation and API-key events; docs also name logins, setting changes and uploads. Sources: anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:event.
content_logging Can prompts and answers be retained for compliance, and is it configurable? [supported]: Workspace chat history/logs retain prompts/responses and expose permissioned exports. Retention and external copies depend on the deployment. Sources: anythingllm:anythingllm:logs.
siem_export Can logs stream to a SIEM or be exported? [unknown]: siem_export: Can logs stream to a SIEM or be exported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive.
ediscovery Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive.
log_retention How long are logs kept? [unknown]: log_retention: How long are logs kept? No complete log retention period, tamper-evident integrity model, SIEM streaming contract or eDiscovery/legal-hold workflow was verified. These are event/chat logs, not a certified audit archive.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:admin-pin, anythingllm:anythingllm:event, anythingllm:anythingllm:logs.

ADM-07 Data loss prevention and personal data

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

AnythingLLM

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.

ADM-08 AI policy and guardrails

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

AnythingLLM

Agent cross-checked Support: partial

Workspace instructions can guide models; a mandatory organization-wide policy and violation system remain unverified.

Limitations

org_instructions: Admins/Managers configure workspace/system prompt context and model defaults. A single unavoidable organization policy and its enforcement were not established.
usage_notice: Can users be required to accept a usage policy? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee.
content_filters: Are content filters configurable? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee.
violation_reporting: Are policy hits visible to admins? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee.

org_instructions Can admins set organisation-wide instructions? [partial]: Admins/Managers configure workspace/system prompt context and model defaults. A single unavoidable organization policy and its enforcement were not established. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig.
usage_notice Can users be required to accept a usage policy? [unknown]: usage_notice: Can users be required to accept a usage policy? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee.
content_filters Are content filters configurable? [unknown]: content_filters: Are content filters configurable? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee.
violation_reporting Are policy hits visible to admins? [unknown]: violation_reporting: Are policy hits visible to admins? Required policy acknowledgement, semantic content filters and administrator policy-violation reporting were not established by the configuration/security sources. Model instructions are not a demonstrated content-control guarantee.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:systemprompt, anythingllm:anythingllm:llmconfig.

Data protection and sovereignty

DATA-01 Hosting location and data residency

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

AnythingLLM

Agent cross-checked Support: partial

Self-hosted locations are customer-selected. Managed Cloud uses AWS, but a guaranteed country for all storage/inference/support was not established.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

backups_logs_region: Self-hosted logs/storage follow deployment choices; telemetry is optional. Cloud backup/log geography and actual egress were not audited.
support_access_region: Cloud privacy explicitly allows necessary Mintplex team access for debugging/maintenance; support-access country restrictions were not established.
swiss_hosting: Customers can self-host on Swiss infrastructure. A vendor-managed Swiss Cloud region and Swiss inference/support commitment were not established.
residency_plan: Customer-operated placement is available with self-hosting. Public Basic/Pro/Enterprise offers do not establish a complete Swiss/EU data-boundary package.

storage_region Where are chats, files and indexes stored? [supported]: Docker data/embedding storage is customer configured; Desktop uses its local OS data directory. Managed Cloud documentation identifies AWS but does not establish a country. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:storage, anythingllm:anythingllm:cloud-overview.
inference_region Where do model calls run, per provider? [supported]: Local endpoints run where the operator deploys them; Azure/AWS/Vertex routes and cloud APIs use the selected provider. Self-hosting the UI does not fix inference geography. Sources: anythingllm:anythingllm:built-in, anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex.
backups_logs_region Where are backups, logs and telemetry? [partial]: Self-hosted logs/storage follow deployment choices; telemetry is optional. Cloud backup/log geography and actual egress were not audited. Sources: anythingllm:anythingllm:privacy, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:localdocker.
support_access_region From where can vendor staff access data? [partial]: Cloud privacy explicitly allows necessary Mintplex team access for debugging/maintenance; support-access country restrictions were not established. Sources: anythingllm:anythingllm:privacy-cloud.
swiss_hosting Is Swiss hosting available? [partial]: Customers can self-host on Swiss infrastructure. A vendor-managed Swiss Cloud region and Swiss inference/support commitment were not established. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:cloud-overview.
residency_plan Which plan or option provides residency? [partial]: Customer-operated placement is available with self-hosting. Public Basic/Pro/Enterprise offers do not establish a complete Swiss/EU data-boundary package. Sources: anythingllm:anythingllm:docker, anythingllm:anythingllm:cloud.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:storage, anythingllm:anythingllm:cloud-overview, anythingllm:anythingllm:built-in, anythingllm:anythingllm:azure, anythingllm:anythingllm:bedrock, anythingllm:anythingllm:vertex, anythingllm:anythingllm:privacy, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:docker, anythingllm:anythingllm:cloud.

DATA-02 Deployment options

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

AnythingLLM

Agent cross-checked Support: partial

Docker supports customer-cloud/on-premise operation; Cloud sells isolated managed instances and Desktop is a separate local client.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

multi_tenant_saas: Is a shared SaaS offered? A shared multi-tenant SaaS was not established: the public managed offer describes private isolated instances.
air_gapped: Local models/embeddings can run after assets are downloaded. A full disconnected fixture was not run; online tools and optional periodically validated Desktop Pro need separate treatment.

multi_tenant_saas Is a shared SaaS offered? [unknown]: multi_tenant_saas: Is a shared SaaS offered? A shared multi-tenant SaaS was not established: the public managed offer describes private isolated instances.
dedicated_instance Is a dedicated single-tenant instance offered, from what size? [supported]: The managed Cloud overview describes one isolated AWS instance per customer. Current pricing lists Basic and Pro, with Enterprise custom services; no numeric seat minimum is published in the reviewed offer. Sources: anythingllm:anythingllm:cloud-overview, anythingllm:anythingllm:cloud.
customer_cloud Can it run in the customer's own cloud account, from what size? [supported]: Docker can run on customer-selected servers/cloud accounts without an MIT software seat minimum. Sources: anythingllm:anythingllm:docker, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:license.
on_premise Can the whole platform run on customer infrastructure, from what size? [supported]: Customers can operate the Docker stack with local providers; commercial Enterprise also advertises on-premise support. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:models, anythingllm:anythingllm:cloud.
air_gapped Can it run without internet access? [partial]: Local models/embeddings can run after assets are downloaded. A full disconnected fixture was not run; online tools and optional periodically validated Desktop Pro need separate treatment. Sources: anythingllm:anythingllm:built-in, anythingllm:anythingllm:local-embed, anythingllm:anythingllm:pro-key.
mode_feature_gaps Which features are missing outside SaaS? [supported]: Desktop is single-user; Docker provides multi-user administration; Cloud explicitly excludes built-in inference, custom coded Agents and MCP. Scheduled Jobs and mail skills are single-user only. Sources: anythingllm:anythingllm:desktop, anythingllm:anythingllm:cloud-limits, anythingllm:anythingllm:job, anythingllm:anythingllm:outlook.

DATA-03 Training use and provider retention

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

AnythingLLM

Agent cross-checked Support: partial

Application locality and provider retention are separate; no universal no-training or zero-retention contract was verified.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

vendor_training: The Desktop policy describes local chat/document storage and optional anonymous telemetry. Cloud terms grant platform-improvement usage rights without a specific reviewed model-training exclusion. This is not a blanket no-training assurance.
provider_training: Do model providers train on it under this product's contracts? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.
provider_retention: How long do model providers keep prompts, including for abuse monitoring? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.
zero_retention: Is zero data retention available, and on which plan? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.
human_review: Can provider staff review content? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.

vendor_training Does the vendor train on customer content? [partial]: The Desktop policy describes local chat/document storage and optional anonymous telemetry. Cloud terms grant platform-improvement usage rights without a specific reviewed model-training exclusion. This is not a blanket no-training assurance. Sources: anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:terms-cloud.
provider_training Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.
zero_retention Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.
human_review Can provider staff review content? [unknown]: human_review: Can provider staff review content? No configured provider agreement was reviewed for training use, abuse-retention/human review or zero-data-retention eligibility. Cloud summary models receive meeting transcripts, and memories are sent to the selected chat provider.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:terms-cloud.

DATA-04 Retention and deletion

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

AnythingLLM

Agent cross-checked Support: partial

Removing workspace access differs from full document erasure; managed Cloud states immediate unrecoverable deletion on cancellation.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

default_retention: Self-hosted documents/history remain in local storage until removed; a universal duration covering chats, indexes, logs, backups and memory was not established.
admin_retention: Can admins set retention periods? A general time-based admin retention scheduler and verified deletion of backups/external-provider copies were not established.

default_retention What is retained and for how long by default? [partial]: Self-hosted documents/history remain in local storage until removed; a universal duration covering chats, indexes, logs, backups and memory was not established. Sources: anythingllm:anythingllm:privacy, anythingllm:anythingllm:storage.
admin_retention Can admins set retention periods? [unknown]: admin_retention: Can admins set retention periods? A general time-based admin retention scheduler and verified deletion of backups/external-provider copies were not established.
user_deletion Can users delete their chats and files permanently? [supported]: Workspace removal deletes that workspace’s vectors but retains the reusable document. My Documents deletion removes the parsed source/cache and all workspace copies according to the privacy guide. Sources: anythingllm:anythingllm:privacy.
contract_end_deletion What is deleted at contract end, and when? [supported]: For managed Cloud only, the current policy and generic terms state permanent non-recoverable instance/data deletion at cancellation, nonpayment or manual termination. No grace period is promised. Sources: anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:privacy, anythingllm:anythingllm:storage, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud.

DATA-05 Sub-processors and foreign-law exposure

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

AnythingLLM

No public information found Support: not-published

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

DATA-06 Contracts and regulatory coverage

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

AnythingLLM

Agent cross-checked Support: partial

Generic Cloud terms specify California law; a negotiated DPA and regulatory or sector package were not verified.

Availability: generally-available · Delivery: native
Scope: surfaces=AnythingLLM Cloud managed instance, Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

dpa: Is a DPA available, and is it negotiable? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.
revdsg_gdpr: Does the DPA cover revDSG and GDPR? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.
governing_law: Managed Cloud terms specify California, United States law and explicitly exclude self-hosted deployments. A specific court and enterprise override were not established.
ai_act_materials: Is EU AI Act documentation provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.
sector_materials: Are FINMA or other sector materials provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.

dpa Is a DPA available, and is it negotiable? [unknown]: dpa: Is a DPA available, and is it negotiable? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.
revdsg_gdpr Does the DPA cover revDSG and GDPR? [unknown]: revdsg_gdpr: Does the DPA cover revDSG and GDPR? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.
governing_law Which law and court govern the contract? [partial]: Managed Cloud terms specify California, United States law and explicitly exclude self-hosted deployments. A specific court and enterprise override were not established. Sources: anythingllm:anythingllm:terms-cloud.
ai_act_materials Is EU AI Act documentation provided? [unknown]: ai_act_materials: Is EU AI Act documentation provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.
sector_materials Are FINMA or other sector materials provided? [unknown]: sector_materials: Are FINMA or other sector materials provided? No reviewed/negotiable DPA, revDSG/GDPR processing annex, EU AI Act role documentation or FINMA/sector secrecy agreement was obtained. Privacy-policy rights are not substituted for a DPA.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:terms-cloud.

DATA-07 Certifications and attestations

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

AnythingLLM

No public information found Support: not-published

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

DATA-08 Encryption and key control

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

AnythingLLM

Agent cross-checked Support: partial

Private deployment and managed-instance isolation are documented; default encryption of all content and a product key-custody service were not verified.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

encryption_at_rest: Is data encrypted at rest? Default encryption-at-rest/transit settings for every database, file, backup and provider route were not verified.
customer_managed_keys: Self-hosted operators control infrastructure/secrets. A product-level BYOK/HYOK content-encryption contract was not established.
tenant_isolation: Managed Cloud describes private isolated AWS instances and resources per customer. This was not independently tested and is separate from source/workspace access control.

encryption_at_rest Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? Default encryption-at-rest/transit settings for every database, file, backup and provider route were not verified.
customer_managed_keys Can the customer manage or hold the keys? [partial]: Self-hosted operators control infrastructure/secrets. A product-level BYOK/HYOK content-encryption contract was not established. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:config.
private_networking Is private connectivity or IP restriction available? [supported]: Docker can be placed on customer infrastructure; Desktop API listens on loopback unless optional network discovery is enabled. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:desktop.
tenant_isolation How are customers separated in shared SaaS? [partial]: Managed Cloud describes private isolated AWS instances and resources per customer. This was not independently tested and is separate from source/workspace access control. Sources: anythingllm:anythingllm:cloud-overview.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:config, anythingllm:anythingllm:desktop, anythingllm:anythingllm:cloud-overview.

DATA-09 Professional secrecy

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

AnythingLLM

Agent cross-checked Support: partial

Local/self-hosted and managed Cloud content-access paths differ. Cloud permits necessary operational team access; a Mintplex staff/sub-processor professional-secrecy undertaking and its plan/add-on terms remain unverified.

Availability: unknown · Delivery: unknown
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation and managed-service terms retrieved 2026-10-21; this row does not infer contract terms from the source-code licence; plan=Mixed modes identified per answer: Docker/Desktop on customer infrastructure; Basic/Pro managed Cloud dedicated AWS instance; Enterprise custom services checked separately; add_ons=none stated; deployment_mode=not specified; region=Customer-selected Docker/Desktop location; managed Cloud AWS country and provider/support staff locations unverified; no DE/CH secrecy-contract variant established; os=not specified.

Limitations

The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown.
content_access: Exact Cloud staff/sub-processor plain-text access, provider human access and deployment-specific operator grants remain unverified.
Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made.

secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No § 203 StGB / Art. 321 StGB or equivalent professional-secrecy undertaking binding Mintplex staff was obtained from the reviewed Cloud terms/privacy, Desktop privacy, pricing and product documentation. Generic privacy commitments are not recorded as that undertaking. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:privacy-desktop.
subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: The Cloud policy names AWS, Stripe and PostHog, but no professional-secrecy undertaking extending to covered sub-processors and their personnel was obtained. Customer-selected model/tool services require separate terms; coverage of their staff remains unknown. Sources: anythingllm:anythingllm:privacy-cloud.
secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: The public Basic, Pro and quote-only Enterprise descriptions did not establish a professional-secrecy package, paid add-on, plan entitlement or price. Availability under a separately negotiated Enterprise agreement remains unknown; no sales contact was made. Sources: anythingllm:anythingllm:cloud.
content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Docker data is held on customer-mounted storage; Desktop documents local chat/file storage. Local or external models can be selected. For the separate managed Cloud service, the policy permits necessary Mintplex team instance access for debugging and maintenance and names AWS infrastructure; configured remote models process inference requests. The documents do not establish exactly which plain-text fields operational staff/sub-processors can see or each provider’s human-access permissions. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:secrecy-cloud-access, anythingllm:anythingllm:secrecy-model-routing.
secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public Cloud terms/privacy, Desktop privacy and setup guides provide general data-handling information. No product-scoped DE/CH secrecy contract template, staff/sub-processor annex or professional-body guidance was located in the reviewed public sources and targeted searches. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:secrecy-cloud-access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:privacy-desktop, anythingllm:anythingllm:cloud, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:secrecy-cloud-access, anythingllm:anythingllm:secrecy-model-routing.

Commercials and vendor

VEN-01 Pricing model and list prices

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

AnythingLLM

Agent cross-checked Support: partial

The current public offer page advertises Cloud Basic at $50/month and Pro at $99/month. These are advertised card prices; legacy tier identities, capacities and checkout entitlements are not mapped here.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public offer cards and Desktop Pro documentation retrieved 2026-10-21; no inference of renamed checkout/legacy tier equivalence; plan=MIT self-hosted/core Desktop; advertised Cloud Basic/Pro cards and quote-only Enterprise; optional Desktop Pro is a separate offer; add_ons=none stated; deployment_mode=not specified; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

This claim quotes advertised offer-card prices only; it does not assert that Basic/Pro and Starter/Professional are equivalent SKUs.
Legacy-tier capacity limits are excluded. Current-card capacity, model-credit allowances, ISO currency and Desktop Pro numeric pricing remain unverified.

pricing_unit What is the pricing unit? [supported]: Self-hosted software has no per-seat MIT licence fee. The current Cloud cards quote a private instance per month; optional Desktop Pro is a separate licence. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud-cards-r2, anythingllm:anythingllm:pro.
list_prices What are list prices per plan, with date and currency? [partial]: As retrieved 2026-10-21, the public Cloud cards advertise Basic $50/month and Pro $99/month; Enterprise requires a quote. The page does not give an ISO currency code. These prices are not mapped to Starter/Professional checkout identifiers; Desktop Pro pricing remains unverified. Sources: anythingllm:anythingllm:cloud-cards-r2, anythingllm:anythingllm:pro-key.
included_usage What usage is included? [partial]: The Basic card explicitly requires a customer LLM API key. Included model credits, overage tariffs and quantified capacity/entitlements for the current Basic/Pro cards were not established. Legacy limitations-page tier names are not used to infer them. Sources: anythingllm:anythingllm:cloud-cards-r2.
add_ons Which features cost extra? [partial]: Optional Desktop Pro removes Magic-feature daily limits and document watermarks. Its price and custom Enterprise integration/support prices remain unverified; Cloud Pro is a separate product offer. Sources: anythingllm:anythingllm:pro, anythingllm:anythingllm:cloud-cards-r2.
overage What do usage beyond limits and premium models cost? [partial]: Customer-selected model/tool accounts incur their own provider charges. No current-card included allowance or AnythingLLM token-overage tariff was verified. Sources: anythingllm:anythingllm:models, anythingllm:anythingllm:cloud-cards-r2.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud-cards-r2, anythingllm:anythingllm:pro, anythingllm:anythingllm:pro-key, anythingllm:anythingllm:models.

VEN-02 Scenario cost

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

AnythingLLM

Agent cross-checked Support: partial

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

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified.

Limitations

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

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

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

VEN-03 Evaluation access

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

AnythingLLM

Agent cross-checked Support: partial

Self-installation and free Desktop permit evaluation without sales; managed Cloud offers paid self-serve instance checkout.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

self_serve_trial: Free self-install has no software trial clock/card requirement. Cloud has paid self-serve signup links, but a free business Cloud trial and its card/duration terms were not established.
trial_scope: Docker self-install includes standard multi-user administration and workspace knowledge; Enterprise SSO/custom service scope is quote-only and Cloud excludes MCP/custom Agents.
sales_gate: Standard self-install and paid public Cloud tiers have self-serve paths. Custom Enterprise services require a quote; no vendor was contacted.

free_tier Is there a free tier for business use? [supported]: MIT self-hosting and the core Desktop download are free; Magic features have a free allowance with optional Desktop Pro. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:desktop, anythingllm:anythingllm:pro.
self_serve_trial Is a self-serve business trial available? [partial]: Free self-install has no software trial clock/card requirement. Cloud has paid self-serve signup links, but a free business Cloud trial and its card/duration terms were not established. Sources: anythingllm:anythingllm:localdocker, anythingllm:anythingllm:cloud.
trial_scope Do trials include SSO, connectors and admin features? [partial]: Docker self-install includes standard multi-user administration and workspace knowledge; Enterprise SSO/custom service scope is quote-only and Cloud excludes MCP/custom Agents. Sources: anythingllm:anythingllm:security, anythingllm:anythingllm:cloud, anythingllm:anythingllm:cloud-limits.
sales_gate Does meaningful evaluation require sales contact? [partial]: Standard self-install and paid public Cloud tiers have self-serve paths. Custom Enterprise services require a quote; no vendor was contacted. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:localdocker.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:desktop, anythingllm:anythingllm:pro, anythingllm:anythingllm:localdocker, anythingllm:anythingllm:cloud, anythingllm:anythingllm:security, anythingllm:anythingllm:cloud-limits.

VEN-04 Contract terms and pricing transparency

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

AnythingLLM

Agent cross-checked Support: partial

The self-hosted MIT grant has no seat commitment; Cloud publishes monthly prices and cancellation terms, with immediate deletion.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Desktop, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

minimum_commitment: The MIT grant has no user-count minimum; Cloud per-instance pricing lists no numeric seat floor. Enterprise minima were not established.
local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR billing from a European contracting entity and Enterprise-specific renewal/price-change terms were not established.
transparency_class: Self-host licensing and Cloud Basic/Pro headlines are disclosed. Enterprise service scope, Desktop Pro tariff and full all-in provider spend are only partially specified or unknown.

minimum_commitment What seat or spend minimum applies? [partial]: The MIT grant has no user-count minimum; Cloud per-instance pricing lists no numeric seat floor. Enterprise minima were not established. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud.
contract_length What contract lengths are offered? [supported]: Cloud Basic/Pro are listed monthly; MIT software use has no subscription term. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:license.
cancellation How can the contract be cancelled or reduced? [supported]: Cloud can be cancelled via the dashboard or email under the generic terms, with immediate non-recoverable deletion and a stated prorated-current-cycle refund provision. Self-hosted service contracts are separate. Sources: anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR billing from a European contracting entity and Enterprise-specific renewal/price-change terms were not established.
transparency_class Is pricing transparent, partial, quote-only or unknown? [partial]: Self-host licensing and Cloud Basic/Pro headlines are disclosed. Enterprise service scope, Desktop Pro tariff and full all-in provider spend are only partially specified or unknown. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:pro-key, anythingllm:anythingllm:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:cloud, anythingllm:anythingllm:terms-cloud, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:pro-key.

VEN-05 Source licence

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

AnythingLLM

Agent cross-checked Support: partial

The pinned main repository is MIT. Paid hosted/Desktop entitlements must be distinguished from that source licence.

Limitations

enterprise_features_closed: Cloud Enterprise and Desktop Pro add commercial services/entitlements. Whether particular enterprise-only implementations are closed or separately licensed was not established from the main MIT file.

licence_type Which licence applies to each component? [supported]: The pinned main client/server repository at v1.18.0 uses MIT. Mobile, browser extension and optional paid-service components require their own component licence review. Sources: anythingllm:anythingllm:license.
branding_restrictions Do licence terms restrict branding or user counts? [supported]: MIT requires notice preservation but has no UI-branding or user-count clause. Optional Desktop Pro removes watermarks from generated documents; that is a paid feature entitlement, not a restriction in the main MIT source licence. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:pro.
enterprise_features_closed Are enterprise features in a separate closed edition? [partial]: Cloud Enterprise and Desktop Pro add commercial services/entitlements. Whether particular enterprise-only implementations are closed or separately licensed was not established from the main MIT file. Sources: anythingllm:anythingllm:cloud, anythingllm:anythingllm:pro, anythingllm:anythingllm:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:license, anythingllm:anythingllm:pro, anythingllm:anythingllm:cloud.

VEN-06 Data export and exit

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

AnythingLLM

Agent cross-checked Support: partial

Authorized accounts can export chat logs; a complete assistant/knowledge exit fixture was not run. Cloud cancellation leaves no recovery window.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Cloud managed instance; version=Public documentation retrieved 2026-10-21; inspected source v1.18.0 / 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba; plan=MIT self-hosted Docker multi-user unless explicitly identified as single-user, Desktop, Mobile or Cloud; add_ons=none stated; deployment_mode=on-premise; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

assistant_export: Can assistants and prompts be exported in a reusable format? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms.
knowledge_export: Can knowledge bases and their sources be exported? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms.

chat_export Can admins export all chats? [supported]: Permissioned exports cover workspace/user chat logs in CSV, JSON, Alpaca JSON or OpenAI-style JSONL once at least ten logs exist. No all-organization export fixture was run. Sources: anythingllm:anythingllm:logs.
assistant_export Can assistants and prompts be exported in a reusable format? [unknown]: assistant_export: Can assistants and prompts be exported in a reusable format? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms.
knowledge_export Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No reusable complete assistant/prompt export, knowledge/source fidelity export or admin leaver/exit fixture was verified. Export Cloud data before cancellation under its current terms.
export_format Are formats documented and machine-readable? [supported]: Documented chat-log formats are machine-readable. This does not establish complete source-file, assistant or index portability. Sources: anythingllm:anythingllm:logs.
post_termination_window How long can data be retrieved after termination? [supported]: Managed Cloud policy states permanent unrecoverable data deletion at cancellation/nonpayment/termination, so no post-termination retrieval window is promised. Self-hosted data remains under operator control. Sources: anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:logs, anythingllm:anythingllm:privacy-cloud, anythingllm:anythingllm:terms-cloud.

VEN-07 Support and service levels

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

AnythingLLM

Agent cross-checked Support: partial

Public community/team support routes and the generic managed Cloud no-offline-credit terms are documented. No bespoke Enterprise SLA or Pro response-time entitlement is established by this claim.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, AnythingLLM Cloud managed instance; version=Public support guide and generic Cloud terms (last updated 2024-07-01) retrieved 2026-10-21; plan=Self-hosted community/team support and managed Cloud under the published generic terms only; separately negotiated Enterprise SLAs and advertised Pro response terms are outside verified contractual scope; add_ons=none stated; deployment_mode=not specified; region=Self-hosted location selected by customer; managed Cloud AWS country and external provider processing require separate confirmation; os=not specified.

Limitations

Generic Cloud contract facts are not extended to a bespoke Enterprise agreement.
Advertised support timing is excluded from contractual uptime/compensation findings.
Support languages, hours, regional staffing and a status history remain unverified.

support_channels Which support channels are available on each plan? [supported]: The public guide lists GitHub issues, team email and community Discord, recommending GitHub/email for direct team assistance. These channels do not establish contracted response hours. Sources: anythingllm:anythingllm:support-r2.
support_languages Is support available in German, French or Italian? [unknown]: Contracted German, French or Italian support coverage, service hours and time zones were not established in the scoped guide and generic terms.
regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: A CH/DACH support entity, staffed local presence or named support partner was not verified from these sources.
uptime_sla Is there an uptime SLA with credits? [partial]: The generic managed Cloud terms deny refunds/credits for an offline instance and do not establish an uptime percentage/credit schedule. This is a finding about those generic terms only; no executed Enterprise override or contractual definition of advertised Pro support timing was reviewed. Sources: anythingllm:anythingllm:cloud-terms-r2.
status_page Is there a public status page with history? [unknown]: A first-party public service-status page with incident history was not verified in the support/contract sources.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:support-r2, anythingllm:anythingllm:cloud-terms-r2.

VEN-08 Onboarding, training and adoption

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

AnythingLLM

Agent cross-checked Support: partial

Public setup/skill tutorials are available and Enterprise advertises custom services; a priced workforce adoption package was not verified.

Limitations

onboarding_service: Is guided onboarding included? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified.
user_training: Is end-user training offered, in which languages? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified.
use_case_library: Public Agent Flow, SQL, mail, document-generation and meeting guides provide use-case examples. A formal role-based workforce curriculum was not established.
adoption_programme: Is there a champion or adoption programme? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified.
service_cost: Enterprise premium service/custom integrations/on-premise support are quote-only. Included rollout/training deliverables and prices were not established.

onboarding_service Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified.
user_training Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified.
use_case_library Are role-based use cases and templates provided? [partial]: Public Agent Flow, SQL, mail, document-generation and meeting guides provide use-case examples. A formal role-based workforce curriculum was not established. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:docgen, anythingllm:anythingllm:meeting, anythingllm:anythingllm:sql.
adoption_programme Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, DE/FR/IT end-user training, champion programme or change-management package was verified.
service_cost Which services cost extra? [partial]: Enterprise premium service/custom integrations/on-premise support are quote-only. Included rollout/training deliverables and prices were not established. Sources: anythingllm:anythingllm:cloud.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: anythingllm:anythingllm:flow, anythingllm:anythingllm:docgen, anythingllm:anythingllm:meeting, anythingllm:anythingllm:sql, anythingllm:anythingllm:cloud.

Sources

Language models anythingllm:anythingllm:models
The product documents multiple cloud and local provider integrations, with selected models supplied by the connected account/server.
Supported local/cloud providers · documented · Source date not stated · Retrieved 2026-10-21
LLM configuration anythingllm:anythingllm:llmconfig
System defaults can be overridden per workspace and separately for agent use.
System, Workspace and Agent LLMs · documented · Source date not stated · Retrieved 2026-10-21
Built-in local model engine anythingllm:anythingllm:built-in
Desktop is moving its built-in engine from Ollama to Lemonade/llama.cpp; current Docker documentation describes opt-in local inference on images after v1.18.0.
Lemonade/llama.cpp; Desktop migration; Docker opt-in · documented · Source date not stated · Retrieved 2026-10-21
Model Router anythingllm:anythingllm:router
Self-hosted and Desktop installations can route messages by ordered calculated or model-classified rules, with a fallback provider/model.
Availability; rule types; fallback · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM file converter registration anythingllm:anythingllm:constants-pin
The pinned collector registers PDF, DOCX, PPTX, XLSX, EPUB, text, image and audio converters; legacy DOC is commented out.
collector/utils/constants.js, accepted MIME and converter maps · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path collector/utils/constants.js
Generic OpenAI configuration anythingllm:anythingllm:generic
Operators can configure an OpenAI-compatible provider, with endpoint-specific behavior and configuration caveats.
Compatible API route · documented · Source date not stated · Retrieved 2026-10-21
Desktop v1.18.0 changelog anythingllm:anythingllm:changelog
Desktop v1.18.0 changes the built-in engine from Ollama to Lemonade/llama.cpp and records format/sync fixes.
Lemond/Lemonade migration; reasoning controls; fixes · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM v1.18.0 release anythingllm:anythingllm:releases
The latest retrieved stable GitHub release is v1.18.0, published 2026-10-13.
Release date and change list · documented · Source date 2026-10-13 · Retrieved 2026-10-21
Azure OpenAI configuration anythingllm:anythingllm:azure
The Azure route uses the customer Azure subscription and its model access.
Customer Azure subscription · documented · Source date not stated · Retrieved 2026-10-21
AWS Bedrock configuration anythingllm:anythingllm:bedrock
Bedrock is a separately configured customer cloud-account route.
Credentials and provider settings · documented · Source date not stated · Retrieved 2026-10-21
Google Vertex AI configuration anythingllm:anythingllm:vertex
Vertex uses customer Google Cloud credentials and deployment configuration.
Service account, project and region · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM Cloud pricing anythingllm:anythingllm:cloud
Current public pricing lists private Cloud Basic at $50/month, Pro at $99/month and quote-only Enterprise with SSO/custom services.
Basic, Pro and Enterprise offer table · vendor-claimed · Source date not stated · Retrieved 2026-10-21
Cloud limitations anythingllm:anythingllm:cloud-limits
Managed Cloud explicitly excludes built-in inference, custom coded Agents and MCP; local/self-hosted capabilities cannot be assumed there.
No built-in LLM; no custom Agents; no MCP · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM v1.18.0 licence anythingllm:anythingllm:license
The pinned main repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer.
LICENSE, MIT grant and notice · documented · Source date not stated · Retrieved 2026-10-21
Ollama configuration anythingllm:anythingllm:ollama
A separately installed Ollama endpoint can provide customer-operated chat inference.
Local provider setup · documented · Source date not stated · Retrieved 2026-10-21
Built-in embedding provider anythingllm:anythingllm:local-embed
The built-in all-MiniLM-L6-v2 embedder runs on CPU and is primarily trained on English; it must first be downloaded.
CPU model and download · documented · Source date not stated · Retrieved 2026-10-21
Embedding models anythingllm:anythingllm:embed
Retrieval embedding providers are configured separately from chat inference.
Local and cloud embedding options · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM user quota implementation anythingllm:anythingllm:user-pin
The pinned user quota counts chats over the preceding 24 hours for non-admin multi-user accounts; null limits and admins are exempt.
server/models/user.js, canSendChat and dailyMessageLimit validation · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path server/models/user.js
AnythingLLM chat quota enforcement anythingllm:anythingllm:chat-pin
The pinned chat endpoints abort before generation when a multi-user account reaches its configured 24-hour quota.
server/endpoints/chat.js, multiUserMode and canSendChat checks · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path server/endpoints/chat.js
Documents in chat, current interface anythingllm:anythingllm:docchat
Attachments inject full text while embedded documents are retrieved as chunks and become available to every authorized workspace user.
v1.8.5+; attachment vs embedding; context; workspace scope · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM PDF extraction implementation anythingllm:anythingllm:pdf-pin
The pinned PDF handler attempts OCR when its initial text loader returns no pages, without establishing scan accuracy.
collector/processSingleFile/convert/asPDF/index.js, no-text fallback · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path collector/processSingleFile/convert/asPDF/index.js
Security and access anythingllm:anythingllm:security
Docker multi-user roles are Admin, Manager and Default; Default users only chat in explicitly assigned workspaces.
Docker only; single-user vs multi-user; roles · documented · Source date not stated · Retrieved 2026-10-21
Automatic document sync preview anythingllm:anythingllm:sync
Preview sync refreshes watched sources; removing a watched Desktop original leaves existing parsed content and embeddings in place.
Docker vs Desktop scope; intervals; missing local file · documented · Source date not stated · Retrieved 2026-10-21
MCP compatibility anythingllm:anythingllm:mcp
Self-hosted/desktop MCP supports local stdio and remote SSE/Streamable transports with configured credentials/headers.
Configuration file; management UI; transport types · documented · Source date not stated · Retrieved 2026-10-21
Outlook Agent anythingllm:anythingllm:outlook
The single-user Outlook skill uses a customer Entra application and requests approval for mailbox-modifying operations.
Single-user only; delegated scopes; approvals · documented · Source date not stated · Retrieved 2026-10-21
Gmail Agent anythingllm:anythingllm:gmail
The Gmail skill is single-user only and distinguishes read actions from modifying actions requiring approval.
Single-user only; setup; action approvals · documented · Source date not stated · Retrieved 2026-10-21
SQL Agent anythingllm:anythingllm:sql
A configurable SQL Agent can query a separately connected database.
Database connection and tool use · documented · Source date not stated · Retrieved 2026-10-21
Local Docker installation anythingllm:anythingllm:localdocker
Self-hosting runs the application in customer-controlled infrastructure and mounted storage.
Volumes; local network; configuration · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM connector registration anythingllm:anythingllm:connectors-pin
The pinned UI registers Confluence, repository, website, YouTube, Obsidian and other import connectors; no source ACL test was performed.
frontend/src/components/Modals/ManageWorkspace/DataConnectors/index.jsx · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path frontend/src/components/Modals/ManageWorkspace/DataConnectors/index.jsx
Vector databases anythingllm:anythingllm:vector
The application supports configurable local and external vector databases rather than a single fixed vendor region.
Local and cloud storage choices · documented · Source date not stated · Retrieved 2026-10-21
Privacy and data handling anythingllm:anythingllm:privacy
Telemetry is optional; deleting a document from a workspace differs from deleting it from My Documents and all workspaces.
Telemetry; document removal vs full erasure · documented · Source date not stated · Retrieved 2026-10-21
Chat modes anythingllm:anythingllm:chatmodes
Agent mode uses configured tools; Query mode is documented to report when it finds no relevant document information.
Agent, Chat and Query modes · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM source citation rendering anythingllm:anythingllm:citation-pin
The pinned client renders citation sources with file/link/provider metadata and source-detail controls.
frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/Citation/index.jsx · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/Citation/index.jsx
Memories and personalization anythingllm:anythingllm:memory
Admins enable user-scoped workspace/global memory, and users can edit/delete it; selected memories go to the configured model.
Off by default; user scope; limits; extraction · documented · Source date not stated · Retrieved 2026-10-21
System prompt variables anythingllm:anythingllm:systemprompt
Workspace system prompts can include dynamic user/time context; this does not establish a mandatory organization policy.
Workspace prompt variables and context · documented · Source date not stated · Retrieved 2026-10-21
Agent setup anythingllm:anythingllm:agent-setup
Operators configure Agent models and skills per workspace; the setup guide still names DuckDuckGo as the default search engine.
Workspace model; enabled skills; search configuration · documented · Source date not stated · Retrieved 2026-10-21
Agent Flows anythingllm:anythingllm:flow
A visual no-code flow editor creates reusable Agent skills; code skills remain a separate developer route.
No-code builder; Desktop vs Docker · documented · Source date not stated · Retrieved 2026-10-21
Desktop installation overview anythingllm:anythingllm:desktop
Desktop supports Windows/macOS/Linux, is single-user and exposes only its API when optional LAN discovery is enabled.
OS support; single-player; network discovery · documented · Source date not stated · Retrieved 2026-10-21
Agent Flow API-call block anythingllm:anythingllm:flow-api
A flow block calls a configured API and passes its result into later flow steps.
HTTP action configuration · documented · Source date not stated · Retrieved 2026-10-21
Document generation skill anythingllm:anythingllm:docgen
The enabled built-in skill generates text, PDF, Excel, DOCX and PowerPoint files, with model-dependent results.
Availability; document types · documented · Source date not stated · Retrieved 2026-10-21
Chart generation skill anythingllm:anythingllm:chart
An Agent chart skill generates charts from prompts and workspace data.
Examples and workspace data · documented · Source date not stated · Retrieved 2026-10-21
Using agents anythingllm:anythingllm:agent-usage
Agent sessions use configured skills and tool-capable models.
Skills and tool use · documented · Source date not stated · Retrieved 2026-10-21
Agent web browsing anythingllm:anythingllm:browsing
The web-browsing skill searches the internet from an Agent request.
Built-in search skill · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM v1.18.0 explicitly configured DuckDuckGo route anythingllm:anythingllm:search-configured-r2
At the pinned revision, explicit agent_search_provider=duckduckgo-engine routes queries to the DuckDuckGo HTML search endpoint; this finding makes no default-provider claim.
agent_search_provider lookup; duckduckgo-engine switch case at lines 96-98; _duckDuckGoEngine at lines 1117-1210 · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path server/utils/agents/aibitat/plugins/web-browsing.js
AnythingLLM Agent skill controls anythingllm:anythingllm:agent-skills-r2
The setup guide documents skill selection in Settings > Agent Skills and tool toggles from the chat prompt menu.
Configure your available skills, excluding the unversioned default-search example · documented · Source date not stated · Retrieved 2026-10-21
Scheduled Jobs anythingllm:anythingllm:job
Recurring Agent jobs are available only in single-user mode, with allowed tools, execution history and generated-file downloads.
Single-user restriction; schedules; run traces · documented · Source date not stated · Retrieved 2026-10-21
Developer API anythingllm:anythingllm:api
Instance APIs manage workspaces, document embedding and chat; API keys confer access and must be protected.
Instance /api/docs; key management; workspace APIs · documented · Source date not stated · Retrieved 2026-10-21
Configuration anythingllm:anythingllm:config
Simple SSO issues short-lived one-use login links for already-provisioned users through a privileged API key; it is not a native SAML/OIDC protocol implementation.
Simple SSO passthrough; multi-user prerequisites · documented · Source date not stated · Retrieved 2026-10-21
Docker installation overview anythingllm:anythingllm:docker
Docker provides the shared browser/server deployment with multi-user administration; Desktop is a separate single-user application.
Desktop/Docker comparison; server deployment · documented · Source date not stated · Retrieved 2026-10-21
Windows installation anythingllm:anythingllm:windows
Silent installation can support MDM packaging, but all-users installation is explicitly unsupported and Enterprise/Server OS use has caveats.
Current User only; silent install and uninstall · documented · Source date not stated · Retrieved 2026-10-21
Browser extension installation anythingllm:anythingllm:ext
The extension sends pages/selected text into workspaces using an API connection; it does not by itself enforce original web content ACLs.
Supported browsers; API connection; collected content · documented · Source date not stated · Retrieved 2026-10-21
Mobile overview anythingllm:anythingllm:mobile
A separate Android app runs local models and can pair with Desktop or server instances; iOS is not currently available.
Android only; local models; pairing; feature set · documented · Source date not stated · Retrieved 2026-10-21
Meeting Assistant introduction anythingllm:anythingllm:meeting-intro
Free Desktop meeting recording/transcription is local on Windows/macOS; a selected cloud summary model receives the transcript.
Desktop exclusivity; supported OS; privacy · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM Pro overview anythingllm:anythingllm:pro
Optional Desktop Pro removes daily Magic-feature limits and generated-document watermarks; it is separate from Cloud Pro.
Desktop v1.15+; Magic features; document watermarks · documented · Source date not stated · Retrieved 2026-10-21
Image generation anythingllm:anythingllm:images
Configured OpenAI/OpenRouter/Lemonade tools can edit reference images, while the documented Ollama route generates without using references.
Provider table; reference-image editing; /img · documented · Source date not stated · Retrieved 2026-10-21
Text to speech anythingllm:anythingllm:tts
Read-aloud uses configured local/browser or external TTS engines, depending on the selected provider.
Provider engines and configuration · documented · Source date not stated · Retrieved 2026-10-21
Transcription models anythingllm:anythingllm:stt
Audio transcription is a separately configurable provider route.
Transcription provider overview · documented · Source date not stated · Retrieved 2026-10-21
Meeting Assistant features anythingllm:anythingllm:meeting
The Desktop meeting workflow records/imports audio, identifies speakers, allows transcript corrections and summarizes meetings.
Transcription; speakers; editable text; summaries · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM locale registration anythingllm:anythingllm:i18n-pin
The pinned frontend registers English, German, French and Italian resources; completeness and naturalness are not established.
frontend/src/locales/resources.js, English/German/French/Italian imports · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path frontend/src/locales/resources.js
AnythingLLM German administrator locale anythingllm:anythingllm:r4-german-admin
German locale resources include user/invite/event-log and administrator settings labels. This establishes partial admin localization, not completeness or naturalness.
settings users, invites, event-logs and role/admin labels · source-inspected · Source date 2026-10-25 · Retrieved 2026-10-26
Commit 9b1fcab141000eaba9f78ed131151de04904454b, path frontend/src/locales/de/common.js
AnythingLLM administrative events anythingllm:anythingllm:admin-pin
The pinned admin routes record user creation/deletion, invitation and API-key lifecycle events.
server/endpoints/admin.js, user, invite and API-key routes · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit 3e4f9411b67f2dd7fa9fc6f2b95dfacbda0633ba, path server/endpoints/admin.js
Workspace chat logs anythingllm:anythingllm:logs
Authorized users export workspace/user chat logs in CSV, JSON, Alpaca JSON or JSONL once at least ten logs are available.
Permissions; export formats; minimum log count · documented · Source date not stated · Retrieved 2026-10-21
Event logs anythingllm:anythingllm:event
The UI records login attempts, messages, setting changes and uploads with user/time details, without a stated immutable retention model.
Events and fields · documented · Source date not stated · Retrieved 2026-10-21
Cloud overview anythingllm:anythingllm:cloud-overview
Mintplex describes each managed customer instance as isolated AWS infrastructure operated and updated by its team.
Private managed instance · documented · Source date not stated · Retrieved 2026-10-21
Cloud privacy policy anythingllm:anythingllm:privacy-cloud
The managed-service policy excludes self-hosting, names AWS/Stripe/PostHog, permits necessary team access and states deletion at cancellation.
Service scope; AWS; operational access; deletion · documented · Source date 2024-07-01 · Retrieved 2026-10-21
Desktop storage anythingllm:anythingllm:storage
Desktop data is stored in an OS-specific local data directory controlled by its user.
Data location and backup · documented · Source date not stated · Retrieved 2026-10-21
Desktop Pro activation anythingllm:anythingllm:pro-key
A purchased Desktop Pro key is periodically validated; free feature allowances remain without a subscription.
Periodic licence validation; free allowances · documented · Source date not stated · Retrieved 2026-10-21
Cloud terms anythingllm:anythingllm:terms-cloud
Managed-service terms name Mintplex Labs Inc in California, California law, cancellation deletion and no credits for offline service under the generic terms.
Scope; entity; payment; cancellation; offline credits; law · documented · Source date 2024-07-01 · Retrieved 2026-10-21
Desktop privacy policy anythingllm:anythingllm:privacy-desktop
The policy describes local Desktop data and optional telemetry; connected external models still need separately scoped data processing.
Desktop-only scope; telemetry · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM Cloud operational access policy anythingllm:anythingllm:secrecy-cloud-access
The managed-only policy permits operational team instance access, names AWS infrastructure and excludes self-hosted deployments; it does not enumerate plain-text field permissions.
Instance Access and Management; Third-Party Services; Data Storage and Security; policy scope · documented · Source date 2024-07-01 · Retrieved 2026-10-21
AnythingLLM local and cloud model routing anythingllm:anythingllm:secrecy-model-routing
System, workspace and agent models can use local or cloud providers; the selected inference path is separate from where the application is hosted.
System LLM; Workspace LLM; Agent LLM; Supported LLM Providers · documented · Source date not stated · Retrieved 2026-10-21
AnythingLLM advertised Cloud plan cards anythingllm:anythingllm:cloud-cards-r2
The current offer page advertises Basic at $50/month and Pro at $99/month, with Enterprise by quote; Basic explicitly asks for an LLM API key.
Basic $50/month, Pro $99/month and quote-only Enterprise cards; Basic BYO LLM key · vendor-claimed · Source date not stated · Retrieved 2026-10-21
Azure Retail Prices, Switzerland North Linux VMs anythingllm:anythingllm: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 anythingllm:anythingllm: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 anythingllm:anythingllm: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 anythingllm:anythingllm: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 anythingllm:anythingllm: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
AnythingLLM generic managed Cloud contract scope anythingllm:anythingllm:cloud-terms-r2
The published generic terms cover managed Cloud, exclude self-hosting and deny offline-service credits; no bespoke Enterprise override was reviewed.
Scope of Agreement; Instance Offline Recovery; last-updated date · documented · Source date 2024-07-01 · Retrieved 2026-10-21
AnythingLLM public support channels anythingllm:anythingllm:support-r2
Public support routes are GitHub, team email and community Discord; the guide recommends GitHub/email for direct team assistance.
GitHub Issues; team email; Discord Community; direct-assistance note · documented · Source date not stated · Retrieved 2026-10-21