Anytype vs Capacities

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round drawn
   Anytype✓fullprobed8/10

   A direct probe confirms Anytype hosts an llms.txt file at doc.anytype.io/llms.txt returning HTTP 200 with organized links to agent-oriented docs, and the developer docs explicitly provide an 'anytype-agents-skill' page meant to be dropped into Claude Code, Cursor, Gemini CLI, etc. so agents can operate on Anytype data directly. This shows both a machine-readable llms.txt entrypoint and human-authored agent-oriented documentation designed for pointing coding agents at. missing for 10: no independent/community confirmation that agents actually consume llms.txt successfully in practice beyond the vendor's own docs and probe.

   • [probe] “PROBE llms.txt: HTTP 200 at https://doc.anytype.io/llms.txt # Anytype Docs ## English - [Welcome](https://doc.anytype.io/anytype/getting-s…”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”

   proof ↗⚑ flag

   Capacities✓fullprobed8/10

   A live probe confirms docs.capacities.io/llms.txt returns HTTP 200 with structured, agent-readable content describing Capacities' documentation, directly matching the story of pointing an agent at an llms.txt file; this is corroborated by the broader developer docs (MCP, API) being machine-consumable and openly hosted. Missing for 10: independent third-party confirmation that agents actually consume this llms.txt successfully in practice, and no explicit vendor statement promoting llms.txt as a first-class agent onboarding feature.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.capacities.io/llms.txt # Capacities Documentation > Documentation for Capacities, a note-taking an…”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client using the Model Context Proto…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to Anytype
   Anytype~partialprobed5/10

   Anytype's docs explicitly claim a CLI that can run Anytype as a headless server for automation and scripting (anytype-docs-2), and a Docker image is maintained for self-hosted network use (anytype-docs-19). However, the only runtime evidence available is for the MCP integration, which requires the desktop GUI app to be actively running and reachable ('Can't connect to API... ensure Anytype is running'), undercutting a fully headless story for the primary automation surface, and there is no independent corroboration of the CLI's headless-server behavior itself. Missing for 10: hands-on verification that the CLI truly runs without any GUI/app dependency, CI-pipeline examples, and independent reports of headless automation in production.

   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [claimed-docs] “There's also a docker image that's maintained by the team.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”

   proof ↗⚑ flag

   Capacities~partialprobed3/10

   Capacities exposes a REST API with bearer/OAuth auth and a hosted MCP server (verified live with 401/OAuth challenge), which could be scripted from a CI pipeline to automate content creation/export, but there is no documented CLI, container image, or explicit 'headless mode' for running the app itself in automation contexts. Missing for 10: dedicated CI/headless-mode documentation, CLI or batch-automation examples, and independent evidence of the API being used in automated pipelines.

   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750).”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round drawn
   Anytype—none0/10

   All evidence describes Anytype exposing its own local API as an MCP server for external AI assistants (Claude, Cursor, etc.) to consume — the reverse direction of this story, which asks whether Anytype itself can plug in and use external MCP servers' tools. No evidence shows Anytype acting as an MCP client that consumes third-party MCP servers.

   ⚑ flag

   Capacities—none0/10

   Evidence consistently shows Capacities exposes itself AS an MCP server (and its own chat-connector/API) so external AI clients (ChatGPT, Claude, custom agents) can connect TO Capacities — the reverse of this story, which asks whether Capacities can consume external MCP servers to use their tools. No documentation or probe shows Capacities' AI assistant/chat feature acting as an MCP client that plugs in third-party MCP servers.

   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client using the Model Context Proto…”
   • [claimed-docs] “Chat Connectors let you connect AI chat apps, like ChatGPT, Claude, Cursor, or Le Chat, to your Capacities space.”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round drawn
   Anytype✓fullprobed8/10

   Anytype ships an official MCP server (npm @anyproto/anytype-mcp) documented at developers.anytype.io, confirmed via runtime probe to launch and connect to the local Anytype API, enabling AI assistants to read/search/modify Objects through natural language. missing for 10: independent third-party review of the MCP server in production use beyond the vendor's own probe/docs.

   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language”
   • [probe] “official MCP server documented at https://developers.anytype.io/docs/examples/featured/mcp/”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”

   proof ↗⚑ flag

   Capacities✓fullprobed8/10

   A runtime probe confirms a live, official hosted MCP server at https://api.capacities.io/mcp that responds with proper OAuth-protected-resource metadata and read/write scopes, and Capacities' developer docs explicitly document this MCP endpoint. This is genuine first-party server infrastructure an AI agent can connect to, not just a client-side integration guide. Missing for 10: independent/community confirmation of a successful agent connection in practice, and the docs text is inconsistently worded (framing it as building a 'custom MCP client' rather than clearly as 'our official server'), which adds minor ambiguity.

   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Anytype
   Anytype✓fullclaimed7/10

   Anytype explicitly ships an official CLI ('Anytype CLI is now available - run Anytype as a headless server for automation and scripting'), positioned for scripting/automation use cases relevant to AI-native/agentic workflows. However, evidence is limited to a single doc mention with no independent hands-on verification of the CLI itself (as opposed to the API/MCP server, which is separately corroborated). Missing for 10: independent/community confirmation of the CLI in use, detailed CLI command reference or examples.

   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”

   proof ↗⚑ flag

   Capacities—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

6. ai-native userDrive the product through a documented public API

   weight 3 · round to Capacities
   Anytype✓fullprobed8/10

   Anytype ships a documented local REST API (OpenAPI 3.1.0 spec, 22 paths, generated developer reference) plus an official MCP server package that fronts it, and a CLI/headless server mode for automation — all confirmed by both docs and runtime probes. missing for 10: independent third-party developer testimonials building against the API beyond the vendor's own probes, and no public hosted/remote API (localhost-only).

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [github] “Extensible through a gRPC API and AI "Agents" (see AGENTS.md).”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”

   proof ↗⚑ flag

   Capacities✓fullprobed9/10

   Capacities documents a REST API with Bearer-token OAuth authentication for accessing/creating/manipulating content, and this is independently verified by a runtime probe showing a live OpenAPI 3.1 spec at api.capacities.io and a correctly bearer-gated /spaces endpoint. It also exposes an official hosted MCP server (with OAuth-scoped read/write) confirmed live via probe, giving AI-native users multiple documented, working integration paths. Missing for 10: deeper endpoint-level documentation excerpts and independent third-party developer testimonials beyond the runtime probes.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750).”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to Capacities
   Anytype—none0/10

   Anytype's local API and MCP server require a key minted in the desktop app (anytype-probe-rt-1, anytype-docs-1), but nothing in the evidence describes scopes, permission levels, or least-privilege credential issuance for agents — the API/OpenAPI spec is just a flat set of endpoints (anytype-probe-rt-2) with no mention of restricting an agent's key to specific actions or Objects. missing for 10: any documentation of scoped/role-based API keys, per-agent permission restriction, or revocation/least-privilege credential model.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”

   proof ↗⚑ flag

   Capacities~partialprobed5/10

   Capacities' API and MCP server use Bearer/OAuth 2.0 authentication, and the live MCP endpoint exposes discrete 'mcp:read' and 'mcp:write' scopes, showing some notion of least-privilege access. However, there is no documented mechanism for a user to generate multiple distinct API keys per-agent, restrict a token to specific spaces/objects, or revoke individual credentials independently. Missing for 10: docs on issuing/managing multiple scoped tokens, per-agent key rotation/revocation, and fine-grained resource-level permissions beyond read/write.

   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750)”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750).”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Anytype
   Anytype✓fullprobed8/10

   Anytype ships an official local REST API (with a machine-readable OpenAPI 3.1.0 spec covering 22 paths) built into the desktop app, a CLI, and an official MCP server (@anyproto/anytype-mcp) verified at runtime to actually connect and mint keys from the app — giving AI-native developers multiple official, documented SDK-like surfaces. Missing for 10: independent third-party SDK wrappers or client libraries beyond the official API/CLI/MCP, and broader language-specific SDK docs (only OpenAPI + CLI + MCP confirmed).

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [probe] “official MCP server documented at https://developers.anytype.io/docs/examples/featured/mcp/”

   proof ↗⚑ flag

   Capacities~partialprobed7/10

   Capacities exposes a documented REST API with a verified live OpenAPI 3.1 spec and Bearer/OAuth authentication, plus an official hosted MCP server with live OAuth-gated endpoints — solid ground for building integrations. However, no dedicated client SDKs (e.g. Python/JS libraries) are evidenced, only the raw REST API and MCP protocol spec. Missing for 10: language-specific official SDK packages, code samples/quickstarts beyond raw API docs.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750)”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client using the Model Context Proto…”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Anytype—none0/10

   No evidence of webhook subscription support anywhere in Anytype's API/local-API docs; the local API is a localhost REST/gRPC surface with an MCP server for AI assistant access, but nothing indicates event-driven webhook callbacks. Missing for 10: any documentation of webhook registration, event subscription endpoints, or push-notification mechanism.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://doc.anytype.io/openapi.json, https://doc.anytype.io/swagger.json, https://doc.anytype.io/api…”

   proof ↗⚑ flag

   Capacities—none0/10

   Evidence shows Capacities has a REST API and MCP server for pull-based access, but no documentation or probe indicates any webhook subscription mechanism for event notifications.

   ⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Capacities
   Anytype~partialprobed5/10

   Anytype doesn't ship a native in-app AI-insights feature, but its local API + official MCP server + 'Agents Skill' let external AI assistants (Claude, Cursor, Gemini CLI, etc.) read, search, and run scripts against a user's Anytype data to generate insights/suggestions, and Queries provide auto-updating views of the knowledge base. This is enablement via integration rather than a built-in 'AI-generated insights' feature inside the product itself. Missing for 10: no evidence of a native, first-party AI panel/chat that autonomously surfaces insights without wiring up an external agent, and no independent hands-on account of the agent-generated insights actually working well.

   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”
   • [claimed-docs] “Rather than manually curating a list of things you're looking for, you define the criteria and the Query assembles the result for you as a V…”

   proof ↗⚑ flag

   Capacities~partialclaimed6/10

   Capacities offers concrete in-app AI features—AI Chats with context, AI Property Auto-Fill, and AI Image Analysis (OCR, categorization)—that provide AI-generated insights/suggestions on user data, and these are opt-in with privacy controls. However, these are fairly narrow (chat, auto-fill, image analysis) rather than broader proactive insight generation like automated summaries, trend detection, or knowledge-graph-driven suggestions. Missing for 10: evidence of proactive/automated insight surfacing (e.g., suggested connections, summaries across notes), independent hands-on reviews validating quality of AI suggestions, and broader coverage beyond the three documented AI features.

   • [claimed-docs] “AI Property Auto-Fill: Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to au…”
   • [claimed-docs] “AI Chats: Start a chat with AI from Explore, or with a keyboard shortcut. You can pass blocks or notes as context.”
   • [claimed-docs] “AI Image Analysis: Analyze any image with one click. The AI extracts a title, description, text (OCR, including handwritten text), a color p…”
   • [claimed-docs] “Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to auto-fill them for you.”
   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to Anytype
   Anytype~partialprobed4/10

   Anytype exposes a local API, CLI (headless server), and an official MCP server plus an 'agents-skill' that lets external AI agents (Claude Code, Cursor, etc.) run scripts against Anytype data, giving building blocks for automation. However there is no documented scheduler, trigger, or persistent background-running agent inside Anytype itself — all examples describe an external agent tool invoked on-demand, not autonomous background operation. Missing for 10: evidence of a built-in scheduler/trigger system, proof that agents can run unattended over time rather than per-invocation, and independent confirmation of autonomous background execution.

   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “official MCP server documented at https://developers.anytype.io/docs/examples/featured/mcp/”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”

   proof ↗⚑ flag

   Capacities—none0/10

   Evidence shows only a scheduled full-export feature and API/MCP integration points for external clients, but nothing indicating autonomous, self-triggering background automations (e.g., workflows/triggers acting on data changes) running inside Capacities.

   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Capacities
   Anytype—none0/10

   Evidence shows Anytype exposes a local API, CLI, and MCP server that let *external* AI assistants (Claude Code, Cursor, Gemini CLI, etc.) read/write Anytype data — this is Anytype acting as a data backend for outside agents, not a built-in AI assistant living inside the product that a user can delegate tasks to. No docs mention an in-app chat/assistant feature.

   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [github] “Extensible through a gRPC API and AI "Agents" (see AGENTS.md).”

   proof ↗⚑ flag

   Capacities~partialclaimed5/10

   Capacities ships a built-in AI assistant with AI Chats (pass blocks/notes as context), AI Property Auto-Fill, and AI Image Analysis, which are genuine in-app AI delegation features (opt-in, per capacities-docs-16/23/24/36). However, these are narrow, single-step assist functions rather than open-ended agentic task delegation (e.g., multi-step autonomous workflows or tool-use chains). Missing for 10: evidence of multi-step/autonomous task execution, any agent-like planning or tool invocation by the built-in assistant, and independent hands-on validation of these AI features' reliability.

   • [claimed-docs] “AI Chats: Start a chat with AI from Explore, or with a keyboard shortcut. You can pass blocks or notes as context.”
   • [claimed-docs] “AI Image Analysis: Analyze any image with one click. The AI extracts a title, description, text (OCR, including handwritten text), a color p…”
   • [claimed-docs] “Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to auto-fill them for you.”
   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Anytype
   Anytype✓fullprobed8/10

   Anytype ships an official MCP server (npm @anyproto/anytype-mcp) that fronts its local API, explicitly documented as 'enabling AI assistants to seamlessly interact with Anytype's API through natural language,' verified working at runtime against the local app. Additionally an 'agents skill' lets agent-capable tools (Claude Code, Cursor, Gemini CLI, Copilot) run natural-language-driven scripts against Anytype data. missing for 10: independent third-party review of natural-language command accuracy/robustness beyond vendor docs and a single runtime probe.

   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “official MCP server documented at https://developers.anytype.io/docs/examples/featured/mcp/”

   proof ↗⚑ flag

   Capacities~partialprobed5/10

   Capacities supports AI chats with context, AI property auto-fill, and connects to external AI assistants (ChatGPT, Claude, Cursor) via chat connectors and a live MCP server with read/write scopes, letting AI act as an intermediary for natural-language commands. However, there is no evidence of a native in-app natural-language command palette/interface where a user directly types free-form commands to control the app itself (e.g., 'create a project page and link it to my meeting notes') — the NL interaction is mediated through external AI tools/chat rather than a first-party built-in command layer. missing for 10: first-party in-app natural-language command interface, hands-on evidence of NL commands controlling core app actions (creating/organizing objects) rather than just chat/auto-fill, independent user reports validating this workflow.

   • [claimed-docs] “Chat Connectors let you connect AI chat apps, like ChatGPT, Claude, Cursor, or Le Chat, to your Capacities space.”
   • [claimed-docs] “AI Chats: Start a chat with AI from Explore, or with a keyboard shortcut. You can pass blocks or notes as context.”
   • [claimed-docs] “Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to auto-fill them for you.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [claimed-docs] “AI Property Auto-Fill: Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to au…”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to Anytype
   Anytype~partialprobed5/10

   Anytype ships a genuine local REST API with a machine-readable OpenAPI 3.1 spec (22 paths) and a developer reference site (developers.anytype.io) generated from it, which documents endpoints like chat/messages with version tags — this is the backbone of an API reference. However, there's no direct evidence of an interactive 'try it out' console or runnable code examples embedded in the docs; probes only confirm the spec's existence and doc generation, not interactivity. Missing for 10: explicit evidence of a live 'try it' widget or runnable code snippets, independent confirmation of interactive testing within the docs UI.

   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [claimed-docs] “Create chats, send and stream messages, react, and search chat history (anytype-heart v0.50.7)”
   • [probe] “PROBE openapi: all candidate paths 404 (https://doc.anytype.io/openapi.json, https://doc.anytype.io/swagger.json, https://doc.anytype.io/api…”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”

   proof ↗⚑ flag

   Capacities—none0/10

   Evidence confirms a REST API and a machine-readable OpenAPI 3.1 spec exist, but there is no sign of an interactive reference (e.g., Swagger/Redoc UI, try-it-now console, runnable code snippets) — docs are plain markdown reference pages and the openapi.json is only a raw spec file, not an interactive explorer.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.capacities.io/openapi.json, https://docs.capacities.io/swagger.json, https://docs.capac…”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to Anytype
   Anytype✓fullprobed9/10

   A genuine machine-readable OpenAPI 3.1.0 spec (22 paths) for Anytype's local API is confirmed to exist and was fetched directly from the vendor's core repo, and developers.anytype.io's API reference is generated from this same spec — i.e. a real downloadable API spec exists and is used to power official docs. Missing for 10: the spec isn't hosted at a stable public URL on the main docs domain (doc.anytype.io openapi.json paths returned 404), so discovery requires knowing the GitHub repo path rather than a standard /openapi.json convention.

   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://doc.anytype.io/openapi.json, https://doc.anytype.io/swagger.json, https://doc.anytype.io/api…”
   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Create chats, send and stream messages, react, and search chat history (anytype-heart v0.50.7)”

   proof ↗⚑ flag

   Capacities✓fullprobed8/10

   A live runtime probe confirms Capacities serves a genuine machine-readable OpenAPI 3.1.0 spec at https://api.capacities.io/openapi.json, paired with a working bearer-gated REST API, directly satisfying the story; the docs also describe the REST API and Bearer auth. missing for 10: an explicit documentation page linking to/download-able copy of the spec (the docs subdomain's openapi.json paths 404) and independent/community confirmation of the spec's existence.

   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750).”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.capacities.io/openapi.json, https://docs.capacities.io/swagger.json, https://docs.capac…”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Anytype—none0/10

   Anytype's docs describe local-only mode, self-hosting, and a local API/MCP server that operates directly on the user's real Anytype data, but there is no mention of a dedicated sandbox/test space, staging environment, or mock-data mode that lets an AI agent test actions without touching production content. Evidence shows agents run scripts 'against your Anytype data' directly, with no isolation layer.

   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”

   proof ↗⚑ flag

   Capacities—none0/10

   Capacities' docs describe a production REST API and MCP server with bearer/OAuth auth, but there is no mention of a sandbox, staging, or test space that lets an AI-native developer experiment without touching real production data. Missing for 10: any documented sandbox/staging environment, test API keys, or a dedicated test space feature.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Anytype—none0/10

   Evidence confirms Anytype ships a local API with an OpenAPI spec that is date-versioned (2025-04-22), but nowhere in the docs or probes is there any documented deprecation policy, versioning guarantees, or migration/sunset process for API changes. Absence of evidence for this applicable axis (a real, documented, self-hosted API exists) means the story is not delivered.

   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://doc.anytype.io/openapi.json, https://doc.anytype.io/swagger.json, https://doc.anytype.io/api…”
   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”

   proof ↗⚑ flag

   Capacities—none0/10

   Evidence confirms Capacities ships a REST API and MCP server, but nothing documents API version numbers, a versioning scheme, or a deprecation policy — the OpenAPI spec is even labeled 'Beta' with no stability guarantees mentioned.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”

   proof ↗⚑ flag

Agent ops

1. ai-native userMy coding agent or assistant can read AND write my notes headlessly — through a documented local API, vendor API, or MCP server — without me touching the GUI

   weight 3 · round to Anytype
   Anytype✓fullprobed9/10

   Anytype documents a local API and an official MCP server (@anyproto/anytype-mcp) that fronts that API, allowing AI assistants like Claude Code, Cursor, etc. to read, search, and modify Objects entirely headlessly without touching the GUI, and this was verified at runtime to actually launch and connect. The OpenAPI spec (22 paths) confirms concrete read/write endpoints beyond marketing claims. Missing for 10: independent third-party (non-vendor) hands-on report confirming write operations succeed end-to-end via the MCP server.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “official MCP server documented at https://developers.anytype.io/docs/examples/featured/mcp/”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”

   proof ↗⚑ flag

   Capacities✓fullprobed8/10

   Capacities ships both a documented REST API (Bearer/OAuth authenticated, verified live with a 401 on keyless access) and an official hosted MCP server at api.capacities.io/mcp with confirmed read AND write scopes (mcp:read mcp:write), enabling headless agent read/write access without the GUI. missing for 10: independent third-party hands-on report of an agent actually using the MCP server end-to-end, and clearer documentation of write-operation specifics/limits in the API docs.

   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750).”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”

   proof ↗⚑ flag

Ai assist

1. ai-native userConnect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI plugins

   weight 2 · round to Capacities
   Anytype✓fullprobed8/10

   Anytype ships a first-party local API plus an official MCP server (npm @anyproto/anytype-mcp) confirmed working at runtime, enabling AI assistants like Claude, Cursor, Gemini CLI, GitHub Copilot to read/search/modify Objects, alongside an 'Agents Skill' toolkit for agent-capable tools. missing for 10: no broader third-party AI plugin marketplace/ecosystem beyond the official MCP server and agents-skill, and no independent community review of the MCP integration's real-world reliability.

   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [github] “Extensible through a gRPC API and AI "Agents" (see AGENTS.md).”

   proof ↗⚑ flag

   Capacities✓fullprobed9/10

   Capacities ships first-party AI connectors (Chat Connectors for ChatGPT/Claude/Cursor/Le Chat), a documented and runtime-verified hosted MCP server with OAuth scopes, and a REST API confirmed live via OpenAPI probe, giving multiple first-party paths to connect external LLMs/tools to notes. Missing for 10: independent hands-on user reports specifically testing these connectors/MCP server in practice, and evidence of a broader third-party plugin ecosystem beyond the officially listed chat apps.

   • [claimed-docs] “Chat Connectors let you connect AI chat apps, like ChatGPT, Claude, Cursor, or Le Chat, to your Capacities space.”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client using the Model Context Proto…”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”

   proof ↗⚑ flag

2. ai-native userA built-in AI assistant can answer questions, summarize, and draft grounded in my own notes — with clear controls over what data it sees

   weight 2 · round to Capacities
   Anytype—none0/10

   Anytype ships a local API and an MCP server that let external AI assistants (Claude, Cursor, etc.) read/search/modify Objects, but there is no evidence of a built-in in-app AI assistant that itself answers questions, summarizes, or drafts grounded in the user's notes with UI-level data-scope controls — the docs describe it as a toolkit for external agents, not a native assistant feature. Missing for 10 (or even partial credit): a first-party in-app assistant UI, summarization/drafting features, and explicit data-scope/consent controls within Anytype itself.

   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “an open-source toolkit that gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”

   proof ↗⚑ flag

   Capacities~partialclaimed7/10

   Docs confirm a built-in AI Chat that can be grounded on selected notes/blocks as context (capacities-docs-23), AI property auto-fill and image analysis (capacities-docs-24, docs-36), and explicit opt-in/data-sharing controls for AI features (capacities-docs-16). This covers Q&A and grounding-with-control well, but explicit 'summarize' and 'draft' capabilities aren't directly documented, only implied via chat/context features. missing for 10: explicit documentation of summarization/drafting workflows, independent/hands-on user validation of AI answer quality or grounding accuracy.

   • [claimed-docs] “AI Chats: Start a chat with AI from Explore, or with a keyboard shortcut. You can pass blocks or notes as context.”
   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”
   • [claimed-docs] “AI Image Analysis: Analyze any image with one click. The AI extracts a title, description, text (OCR, including handwritten text), a color p…”
   • [claimed-docs] “Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to auto-fill them for you.”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Anytype
   Anytype~partialprobed6/10

   Anytype documents an agent skill where an AI agent can run scripts against Anytype data to handle bulk edits transformations and repetitive tasks using the local API and MCP server plus a CLI for headless automation. However this relies entirely on external scripting and agent tooling rather than a native bulk edit UI and a community report flags friction with bulk CSV merges into databases. missing for 10: native in-app bulk edit selection tools, independent hands-on verification of large-scale bulk script runs, resolution of the community reported CSV merge gap

   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [community] “I consistently find myself in need of a 'merge feature' when re-importing cleaned CSV data into Anytype database objects - the larger the da…”

   proof ↗⚑ flag

   Capacities—none0/10

   The evidence shows a REST API and MCP server for programmatic access, plus scheduled full exports and selective exports, but nothing documents a bulk/batch operation capability (e.g., batch API endpoints, multi-select bulk edit/tag/delete across many items) that an AI agent could invoke at scale.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “Export selected content as Markdown + CSV... In Capacities, go to Settings > Import Content, open the Notion guide in Migration guides, then…”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   Anytype—none0/10

   Evidence shows Queries (auto-updating saved views) and an 'Agents skill' letting an external AI agent run scripts against Anytype data on request, plus an MCP/local API for AI assistants to read/write objects — but none of this describes user-defined rules that automatically trigger actions on events (e.g. 'when X happens, do Y'). There is no workflow/automation-rule engine, webhook trigger, or event-based action system documented anywhere in the pack.

   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”
   • [claimed-docs] “Rather than manually curating a list of things you're looking for, you define the criteria and the Query assembles the result for you as a V…”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”

   proof ↗⚑ flag

   Capacities—none0/10

   Capacities offers an API, MCP server, and AI assistant features, but no evidence of a rules/trigger engine (event-based automation like 'when X happens, do Y') exists in the docs pack—only manual actions, scheduled exports, and AI-assisted fill-in features are documented.

   ⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Anytype—none0/10

   Evidence shows Anytype exposes a local API, MCP server, and an 'agents skill' letting external agents run one-off scripts against Anytype data, but nothing describes any built-in scheduler, cron-like trigger, or recurring/automated workflow execution within Anytype itself. Automation-depth is a fair axis for an AI-native knowledge tool, so absence of evidence yields 'none' rather than 'na'.

   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”

   proof ↗⚑ flag

   Capacities—none0/10

   No evidence of any scheduling, cron-style triggers, or recurring workflow/automation capability aside from a manual 'automated full export' schedule which is not a general job/workflow scheduler; the API, MCP server, and AI features shown are all synchronous/manual, not recurring triggers for workflows.

   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   Anytype—none0/10

   Anytype documents AI agent scripting/automation capabilities (agents running scripts against Anytype data) and general object version history is not mentioned anywhere in the evidence, nor is any mechanism to version, review, or roll back automations/scripts themselves. Since Anytype does support automation via its agents-skill and API, this axis is applicable, but no evidence shows versioning, review workflows, or rollback for those automations.

   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [claimed-docs] “gives AI assistants a safe way to read, search, and modify Objects in your Anytype Channels”

   proof ↗⚑ flag

   Capacities—none0/10

   Capacities documents templates, an API, and an MCP server for integrations, but nothing in the evidence describes an automation-building feature (workflows/triggers/actions) let alone version history, review, or rollback for such automations.

   • [claimed-docs] “Templates allow you to prefill the content of an object- you can prefill properties and blocks in your objects.”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

Capture

1. researcherClip web pages, articles, and highlights from my browser straight into my notes with an official clipper or capture flow

   weight 2 · round drawn
   Anytype—none0/10

   No evidence of a browser clipper extension or web-capture flow for Anytype; import features cover Markdown/Any-Block/Obsidian migration, not web page/article clipping. Missing for 10: official browser extension, article/highlight capture flow, bookmarklet or share-to-Anytype integration.

   ⚑ flag

   Capacities—none0/10

   No evidence pack item mentions a browser extension, web clipper, or article/highlight capture flow for Capacities; the closest features are generic content-type ingestion and a mobile app for 'capture on the go', not a browser clipper. This is a reasonable axis for a note-taking/knowledge-base app (competitors ship clippers), so absence of evidence means 'none' rather than 'na'.

   • [claimed-docs] “The mobile app is a companion to desktop for day-to-day work in your space: search and capture on the go.”
   • [claimed-docs] “Any image you input into Capacities becomes an image object, that can be reused anywhere in your space.”
   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself. The first group is what we call Basic Object T…”

   proof ↗⚑ flag

Daily notes

1. power-userI get an automatic daily note for each day, pre-filled from a template, as the default landing place for journaling and capture

   weight 3 · round to Capacities
   Anytype—none0/10

   Anytype documents general Templates and Types (docs-13, docs-22, docs-32) but nowhere describes an automatic daily/journal note feature that auto-creates a dated entry pre-filled from a template as a default landing page — no evidence of a 'Daily Note' or journaling automation feature exists in the pack.

   • [claimed-docs] “A Template is a saved layout for a page that you can reuse.”
   • [claimed-docs] “you define what a good starting point looks like once and it'll form the base for every new Object you create afterwards”
   • [claimed-docs] “Anytype comes with built-in Types, but you can create your own custom Types to match your needs.”

   proof ↗⚑ flag

   Capacities~partialclaimed6/10

   Capacities docs confirm a native daily-note concept uniquely linked to each day for quick capture (capacities-docs-21) and a general templates feature that can pre-fill properties and blocks in objects (capacities-docs-9), and daily notes surface backlinked references automatically (capacities-docs-8). However, the docs never explicitly confirm that a template is auto-applied to the daily note by default or that the daily note is the default landing page/capture surface on app open. Missing for 10: explicit documentation of template-to-daily-note binding, and confirmation that the daily note is the default landing view.

   • [claimed-docs] “A daily note is a note that is uniquely linked to one day. It often serves as a quick and simple way to write down ideas or things to rememb…”
   • [claimed-docs] “Templates allow you to prefill the content of an object- you can prefill properties and blocks in your objects.”
   • [claimed-docs] “The next section shows all references of that day, including objects with properties to that day and mentions of the day in your writing.”

   proof ↗⚑ flag

Editor

1. power-userDefine reusable templates (with variables like date and title) and apply them when creating recurring kinds of notes

   weight 2 · round drawn
   Anytype~partialclaimed6/10

   Anytype's docs clearly describe reusable Templates ('a saved layout for a page that you can reuse' and 'define what a good starting point looks like once... base for every new Object') including customizable cover/icon, which supports recurring note types via Types+Templates. However, there's no evidence of dynamic variable substitution (e.g., auto-filled date, title placeholders) within templates—only static layout/property definitions are documented. missing for 10: explicit variable/placeholder support (auto-date, auto-title fill), independent hands-on confirmation of template variable behavior.

   • [claimed-docs] “A Template is a saved layout for a page that you can reuse.”
   • [claimed-docs] “you define what a good starting point looks like once and it'll form the base for every new Object you create afterwards”
   • [claimed-docs] “Choose an image from the gallery or upload your own image.”
   • [claimed-docs] “Anytype comes with built-in Types, but you can create your own custom Types to match your needs.”

   proof ↗⚑ flag

   Capacities~partialclaimed6/10

   Capacities docs confirm a template system that lets you prefill properties and blocks of an object type, which supports reusable templates for recurring note kinds (e.g., Meetings, Projects) as suggested by the object-type-first workflow. However, no evidence describes dynamic variable insertion (e.g., auto-filled current date or title placeholders) within templates. Missing for 10: explicit documentation of variable/placeholder support (date, title, etc.) in templates and independent hands-on confirmation of this behavior.

   • [claimed-docs] “Templates allow you to prefill the content of an object- you can prefill properties and blocks in your objects.”
   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself. The first group is what we call Basic Object T…”
   • [claimed-docs] “Capacities is object-type-first. Define key object types early (`People`, `Projects`, `Meetings`, etc.) and add core properties.”

   proof ↗⚑ flag

2. power-userWrite and format notes with headings, callouts, tables, code blocks, and embedded media in a fast keyboard-driven editor

   weight 2 · round to Anytype
   Anytype~partialcommunity5/10

   Docs and GitHub confirm a block-based editor (text, databases, kanban, calendar, custom Types) and community reports confirm tables exist (though 'simple, no formulas'), plus templates and page icons/covers. However there is no explicit evidence for headings, callouts, or code blocks as first-class formatting elements, nor any documentation of keyboard shortcuts or 'fast keyboard-driven' editing speed, and embedded media support is only implied via cover images. missing for 10: explicit callout/heading/code-block support, documented keyboard-shortcut system, and evidence of rich embedded media (video/audio/files) in the editor.

   • [github] “Composable blocks: text, databases, kanban, calendar & custom Types.”
   • [community] “Anytype has tables now, simple, no formulas yet. Plan to add formulas to databases - it's one of the top requested features on our forum (co…”
   • [claimed-docs] “A Template is a saved layout for a page that you can reuse.”
   • [claimed-docs] “Anytype comes with built-in Types, but you can create your own custom Types to match your needs.”
   • [community] “I've been using this for about a year. It's very polished and been stable for me. The Apple and Android apps work well too... I'm using it a…”

   proof ↗⚑ flag

   Capacities—none0/10

   The evidence pack covers linking, templates, object types, and AI features but never documents core editor formatting elements (headings, callouts, tables, code blocks) or keyboard-driven editing speed/shortcuts, so this applicable power-user capability has no supporting evidence.

   ⚑ flag

Migration

1. switcherExport my entire knowledge base at any time in open formats, so leaving is as easy as arriving

   weight 2 · round to Anytype
   Anytype✓fullclaimed8/10

   Docs explicitly state you can import content and export it at any time, with Markdown or Any-Block format choices, plus dedicated import from Obsidian and self-host backup/export of channels for migrating identities — covering the core switcher promise of open-format export/import at will. missing for 10: independent hands-on verification of export fidelity/completeness and no explicit mention of bulk/full-space export beyond channel-level export.

   • [claimed-docs] “Choose your preferred format: Markdown or Any-Block.”
   • [claimed-docs] “You can import content into your spaces and export it at any time.”
   • [claimed-docs] “Anytype will process the contents and automatically create a separate object for each Markdown file.”
   • [claimed-docs] “Open Channel Settings → Import → Obsidian and click on Import files.”
   • [claimed-docs] “export all your channels, and import them into a new identity after switching the network mode”
   • [claimed-docs] “To back up your channels and data to a self-hosted network, you need to have a network configuration.”

   proof ↗⚑ flag

   Capacities✓fullclaimed7/10

   Capacities documents a native Full Export feature (Settings > Full Export) that can be run on demand or scheduled automatically, exporting content as Markdown with properties as front matter and collections as CSV files explicitly 'to reuse your content in other apps or work with it programmatically' — both open, portable formats satisfying a switcher's exit needs. Missing for 10: independent/hands-on verification of export completeness (media, attachments, block-references, backlinks fidelity) and confirmation this covers the entire space rather than only selected content in the documented flows.

   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”
   • [claimed-docs] “Export selected content as Markdown + CSV... In Capacities, go to Settings > Import Content, open the Notion guide in Migration guides, then…”
   • [claimed-docs] “Export only the selected content you intend to migrate. Use Markdown + CSV as your default format for this flow.”

   proof ↗⚑ flag

2. switcherImport my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preserved

   weight 3 · round to Anytype
   Anytype~partialcommunity5/10

   Anytype documents Markdown import (choose Markdown or Any-Block format) and a dedicated Obsidian migration path that creates a separate object per Markdown file, preserving structure to some degree, plus general import/export at any time. However, there is no evidence of dedicated Notion, Evernote, or Roam importers preserving links/attachments as the story specifies — only generic Markdown ingestion is documented, and a community comment even flags gaps in re-importing structured data (CSV) cleanly. Missing for 10: dedicated Notion/Evernote/Roam import tooling, evidence that links and attachments survive import from these specific sources, and independent hands-on confirmation of fidelity.

   • [claimed-docs] “Choose your preferred format: Markdown or Any-Block.”
   • [claimed-docs] “Anytype will process the contents and automatically create a separate object for each Markdown file.”
   • [claimed-docs] “Open Channel Settings → Import → Obsidian and click on Import files.”
   • [claimed-docs] “You can import content into your spaces and export it at any time.”
   • [community] “I consistently find myself in need of a 'merge feature' when re-importing cleaned CSV data into Anytype database objects - the larger the da…”

   proof ↗⚑ flag

   Capacities~partialclaimed4/10

   Docs provide a detailed Notion-to-Capacities migration guide (curate structure, export as Markdown+CSV, define object types before import) which covers the Notion import path, but there is no evidence at all for importing from Evernote or Roam, and no confirmation that links/attachments are preserved on import (the export docs describe front matter/CSV output going out of Capacities, not import fidelity). missing for 10: Evernote import support, Roam import support, plain Markdown import instructions, explicit evidence that internal links/backlinks and attachments survive the import process, independent/hands-on reports confirming fidelity.

   • [claimed-docs] “Migrate from Notion by curating structure before export.”
   • [claimed-docs] “Export selected content as Markdown + CSV... In Capacities, go to Settings > Import Content, open the Notion guide in Migration guides, then…”
   • [claimed-docs] “Capacities is object-type-first. Define key object types early (`People`, `Projects`, `Meetings`, etc.) and add core properties.”
   • [claimed-docs] “Export only the selected content you intend to migrate. Use Markdown + CSV as your default format for this flow.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”

   proof ↗⚑ flag

Graph

1. researcherExplore my knowledge base as an interactive graph of notes and connections, filtered to what I care about

   weight 1 · round to Anytype
   Anytype✓fullclaimed8/10

   Anytype's Graph is explicitly documented as 'a live, visual map of every Object in your Channel and how they connect to each other,' directly matching the interactive knowledge graph story, and linking is described as core to turning notes into a connected knowledge base. Filtering/querying is supported via the Query feature, which lets users define criteria to assemble filtered Views, though docs don't explicitly confirm Query filters apply directly to the Graph visualization itself. Missing for 10: explicit documentation or hands-on evidence that Graph view can be filtered by Query/View criteria, and independent user corroboration of the graph exploration experience.

   • [claimed-docs] “The Graph is a live, visual map of every Object in your Channel and how they connect to each other.”
   • [claimed-docs] “These connections become incredibly valuable. You can trace how ideas relate, see what's connected to a project”
   • [claimed-docs] “Linking on Anytype is what turns a bunch of separate notes into a connected knowledge base.”
   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”
   • [claimed-docs] “Rather than manually curating a list of things you're looking for, you define the criteria and the Query assembles the result for you as a V…”

   proof ↗⚑ flag

   Capacities~partialclaimed5/10

   Capacities has a documented Graph View that visualizes an object's links as a network showing the 'local neighbourhood' around the open note, which supports interactive graph exploration of the knowledge base. However, the evidence never describes any filtering mechanism (by tag, type, date, or search term) within the graph view itself, so the 'filtered to what I care about' part of the story is unevidenced. missing for 10: documented graph filtering/faceting by object type, tag, or search query, and any independent hands-on account of using filters in graph view.

   • [claimed-docs] “Graph view shows how one object connects to others. Each link between notes becomes a line in the graph”
   • [claimed-docs] “Graph view shows how one object connects to others. Each link between notes becomes a line in the graph, so you can see the local neighbourh…”
   • [claimed-docs] “All backlinks are grouped together at the bottom of your object in a section titled "Backlinks".”
   • [claimed-docs] “Capacities lets you link to individual blocks inside of an object, and reference them in other pages. We call this concept block-based linki…”

   proof ↗⚑ flag

Links

1. researcherLink notes with [[wiki-style]] links and see every backlink and unlinked mention of a note in context

   weight 3 · round to Anytype
   Anytype~partialclaimed6/10

   Docs confirm bidirectional-style linking ('Linking on Anytype is what turns a bunch of separate notes into a connected knowledge base', 'trace how ideas relate, see what's connected') and a live Graph view showing every Object's connections, which covers wiki-links and a form of backlink visualization. However, the evidence never explicitly documents a dedicated 'Backlinks' panel or an 'unlinked mentions' detection feature (text mentioning a note's title without a link), so the researcher's specific in-context backlink/unlinked-mention workflow is only partly evidenced. Missing for 10: explicit backlinks list UI, unlinked-mentions detection, independent/hands-on confirmation of these specific sub-features.

   • [claimed-docs] “Linking on Anytype is what turns a bunch of separate notes into a connected knowledge base.”
   • [claimed-docs] “These connections become incredibly valuable. You can trace how ideas relate, see what's connected to a project”
   • [claimed-docs] “The Graph is a live, visual map of every Object in your Channel and how they connect to each other.”

   proof ↗⚑ flag

   Capacities~partialclaimed5/10

   Docs confirm backlinks are grouped in a dedicated 'Backlinks' section on each object and graph view shows links between notes, and daily notes show 'mentions of the day in your writing,' but there is no explicit mention of [[wiki-style]] link syntax or a general unlinked-mention detection feature across regular notes (only for daily notes). missing for 10: explicit [[wiki-link]] syntax documentation, a general unlinked-mentions panel for all object types, and independent/hands-on confirmation of in-context backlink previews.

   • [claimed-docs] “All backlinks are grouped together at the bottom of your object in a section titled "Backlinks".”
   • [claimed-docs] “Graph view shows how one object connects to others. Each link between notes becomes a line in the graph”
   • [claimed-docs] “The next section shows all references of that day, including objects with properties to that day and mentions of the day in your writing.”
   • [claimed-docs] “Graph view shows how one object connects to others. Each link between notes becomes a line in the graph, so you can see the local neighbourh…”
   • [claimed-docs] “A daily note is a note that is uniquely linked to one day. It often serves as a quick and simple way to write down ideas or things to rememb…”

   proof ↗⚑ flag

2. power-userReference or transclude an individual block or section of one note inside another and have it stay in sync

   weight 2 · round to Capacities
   Anytype—none0/10

   Evidence documents only object-level linking and backlinks (docs-40, docs-28) and a live Graph of Object connections (docs-9), but nowhere describes block- or section-level transclusion/embedding that stays synced across notes — a distinct feature from whole-object linking. No mention of synced blocks, block references, or embed-with-sync exists in the pack.

   • [claimed-docs] “Linking on Anytype is what turns a bunch of separate notes into a connected knowledge base.”
   • [claimed-docs] “These connections become incredibly valuable. You can trace how ideas relate, see what's connected to a project”
   • [claimed-docs] “The Graph is a live, visual map of every Object in your Channel and how they connect to each other.”

   proof ↗⚑ flag

   Capacities✓fullclaimed8/10

   Capacities explicitly supports block-based linking/embedding (block references) where an embedded block is identical to the original and edits propagate everywhere it's used, plus backlinks and graph view to surface these connections — directly matching the transclusion-stays-in-sync story. Missing for 10: independent hands-on verification of sync behavior across notes and any documented limits (e.g., section-level vs single-block granularity).

   • [claimed-docs] “Capacities lets you link to individual blocks inside of an object, and reference them in other pages.”
   • [claimed-docs] “Capacities lets you link to individual blocks inside of an object, and reference them in other pages. We call this concept block-based linki…”
   • [claimed-docs] “An embedded block is identical to the original. This means that any edits will occur in all places where this block is used.”
   • [claimed-docs] “All backlinks are grouped together at the bottom of your object in a section titled "Backlinks".”
   • [claimed-docs] “Graph view shows how one object connects to others. Each link between notes becomes a line in the graph, so you can see the local neighbourh…”

   proof ↗⚑ flag

Ownership

1. power-userMy notes live in local files or a local-first store that I own and can read without the app, and everything keeps working fully offline

   weight 3 · round to Anytype
   Anytype~partialcommunity6/10

   Anytype clearly delivers offline-first, locally-owned storage: docs state all content is stored locally, the app 'always works without an internet connection', data is encrypted at rest in a self-owned Vault, and a local-only sync mode exists that disables any external node entirely (anytype-docs-29, anytype-docs-30, anytype-docs-44, anytype-docs-31/43, anytype-docs-24). However, the underlying store is a proprietary local database/CRDT format, not plain files you can read without the app — the only path to human-readable local files is manual Markdown export/import (anytype-docs-11, anytype-docs-20), and a community report notes data 'lives unencrypted on-disk' at the index level despite vendor's encryption claims (anytype-comm-8, anytype-comm-9), showing some tension around the ownership/transparency claim. missing for 10: evidence that the live working store itself (not just exports) is human-readable outside the app, and independent confirmation that full offline use has no hidden network dependency beyond vendor docs.

   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”
   • [claimed-docs] “A Vault is an encrypted container in Anytype that you own. Everything you create lives inside your Vault, stored directly on your device.”
   • [claimed-docs] “Only you can access your spaces and grant access to others — not even Anytype can see your content.”
   • [claimed-docs] “You control access. Only you can access your spaces and grant access to others — not even Anytype can see your content.”
   • [claimed-docs] “you can enable local-only mode. This mode disables Anytype's backup node entirely”
   • [claimed-docs] “Choose your preferred format: Markdown or Any-Block.”
   • [claimed-docs] “You can import content into your spaces and export it at any time.”
   • [community] “I found Anytype a few months ago and thought 'wow maybe I can ditch Turtl and just use this.' A few things bugged me: it's source-available …”
   • [community] “(Anytype team) All your data in Anytype is encrypted at rest; only the indexes are not encrypted currently. We have plans to also encrypt th…”

   proof ↗⚑ flag

   Capacities~partialclaimed5/10

   Capacities documents offline-first behavior (work offline, sync when back online, offline search) and a full/scheduled export to Markdown+CSV/front-matter that is 'easy to reuse... work with programmatically,' giving some data ownership. However, there is no evidence the primary store is plain local files usable without the app day-to-day — the live working format is the app's own sync/cloud store, and export is a periodic snapshot rather than the native storage format. Missing for 10: evidence of a genuine local-first primary file format (e.g. markdown files on disk that the app just syncs), and confirmation that full functionality (not just search) works offline without any cloud dependency.

   • [claimed-docs] “Capacities is an offline-first application. You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “Search in Capacities is great for navigation, finding, and connecting your content. It works offline on all devices, giving you quick search…”
   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”
   • [claimed-docs] “Export selected content as Markdown + CSV... In Capacities, go to Settings > Import Content, open the Notion guide in Migration guides, then…”
   • [claimed-docs] “Export only the selected content you intend to migrate. Use Markdown + CSV as your default format for this flow.”

   proof ↗⚑ flag

2. researcherMy notes are stored or exportable in open, documented formats (Markdown, JSON) so my archive outlives the vendor

   weight 2 · round drawn
   Anytype✓fullprobed7/10

   Anytype explicitly documents Markdown export/import (choose Markdown or Any-Block format) and lets you import/export content at any time, plus Obsidian-style markdown migration, giving researchers a documented open-format path out of the vendor lock-in. The local API also exposes data via JSON over a documented OpenAPI spec, reinforcing programmatic, non-proprietary access to notes. missing for 10: explicit full-space JSON export/archival documentation and independent verification that exported Markdown preserves all object metadata/relations.

   • [claimed-docs] “Choose your preferred format: Markdown or Any-Block.”
   • [claimed-docs] “You can import content into your spaces and export it at any time.”
   • [claimed-docs] “Anytype will process the contents and automatically create a separate object for each Markdown file.”
   • [claimed-docs] “Open Channel Settings → Import → Obsidian and click on Import files.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”

   proof ↗⚑ flag

   Capacities✓fullclaimed7/10

   Capacities documents a full, schedulable export to Markdown (with front matter) plus CSV for collections, explicitly stated to make content reusable in other apps or programmatically ('capacities-docs-11','capacities-docs-31'), alongside a REST API for direct data access ('capacities-docs-33'). This gives researchers a genuine open-format escape hatch beyond vendor lock-in. Missing for 10: independent/hands-on verification of export completeness and fidelity (e.g., whether all object types and block-links survive the export), and confirmation that the 'Full Export' truly captures the entire space rather than only selected/migration content.

   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”
   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “Export selected content as Markdown + CSV... In Capacities, go to Settings > Import Content, open the Notion guide in Migration guides, then…”
   • [claimed-docs] “Migrate from Notion by curating structure before export.”

   proof ↗⚑ flag

Self host

1. developerRun the whole system without the vendor's cloud — local-only mode or a self-hosted sync backend I operate myself

   weight 2 · round to Anytype
   Anytype✓fullcommunity8/10

   Anytype documents local-only mode (disables the backup node entirely, data stays on-device with offline-first storage) plus a self-hosted network backend option including a team-maintained Docker image for backing up/syncing without vendor cloud, and this is corroborated by the team's own community statements about p2p sync working without a central server. Some nuance remains around multi-device sync limitations in local-only mode and encryption caveats raised in community threads (indexes not encrypted, source-available license). Missing for 10: independent hands-on verification of a full self-hosted sync-server deployment (vs. docs-only description) and more detail on operational maturity of the self-host path.

   • [claimed-docs] “To back up your channels and data to a self-hosted network, you need to have a network configuration.”
   • [claimed-docs] “This mode disables Anytype's backup node entirely—meaning multi-device syncing will only work over the same local network”
   • [claimed-docs] “There's also a docker image that's maintained by the team.”
   • [claimed-docs] “you can enable local-only mode. This mode disables Anytype's backup node entirely”
   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”
   • [claimed-docs] “You can even collaborate directly with others using peer-to-peer sync or self-host on your own network.”
   • [community] “(Anytype team) All your data in Anytype is encrypted at rest; only the indexes are not encrypted currently. We have plans to also encrypt th…”

   proof ↗⚑ flag

   Capacities—none0/10

   Capacities is offline-first (local caching with sync) but all evidence shows sync and API/MCP endpoints run through the vendor's own cloud (api.capacities.io); there is no documented self-hosted sync backend or fully local-only mode without vendor infrastructure. Missing for 10: any option to self-host sync server, any documented local-only deployment mode, independent confirmation of running without vendor cloud.

   • [claimed-docs] “Capacities is an offline-first application. You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “You can work offline and your changes will get synchronized as soon as you're back online.”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”

   proof ↗⚑ flag

Mobile

1. power-userFull-featured iOS and Android apps give me my whole knowledge base — capture, search, and linking — not a stripped-down companion

   weight 2 · round to Anytype
   Anytype~partialcommunity4/10

   Evidence confirms native iOS and Android apps exist and are described as polished and functional (comm-3, comm-7), and cross-device sync/offline-first architecture (anytype-docs-29, anytype-docs-30) implies capture/linking works across devices, but no documentation explicitly details mobile-specific feature parity for capture, search, and linking, and one long-term user characterizes their mobile use as 'a very basic note system,' hinting at reduced functionality vs desktop. Missing for 10: explicit docs on mobile app feature set (Queries, Graph, Types, Templates) confirming parity with desktop, and independent hands-on reviews of mobile power-user workflows beyond basic notes.

   • [community] “I've been using this for about a year. It's very polished and been stable for me. The Apple and Android apps work well too... I'm using it a…”
   • [community] “We don't offer a browser version. Instead, we have an Electron-based cross-platform app for Windows, Linux, macOS, plus native iOS and Andro…”
   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”

   proof ↗⚑ flag

   Capacities—none0/10

   The only description of the mobile app in the evidence pack is Capacities' own docs stating it is 'a companion to desktop for day-to-day work... search and capture on the go' — this explicitly frames mobile as a stripped-down companion, not a full-featured app with linking/graph/backlinks parity, and no evidence shows block-based linking, graph view, or full object-type editing on iOS/Android. missing for 10: any documentation or reports of full linking/graph/template features on mobile, evidence that mobile isn't limited to search+capture, independent hands-on confirmation of mobile feature parity.

   • [claimed-docs] “The mobile app is a companion to desktop for day-to-day work in your space: search and capture on the go.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Anytype
   Anytype~partialprobed6/10

   Anytype ships a real local REST API (OpenAPI spec, 22 paths, confirmed by runtime probe) plus a CLI headless server and an official MCP server that let AI agents create/search/modify objects and chats — solid API-driven access. However, the API surface (22 endpoints) is far narrower than the full UI feature set (Queries/Views, Templates, Web Publishing, Graph, Types customization, import/export flows), and no evidence confirms full parity between API and UI capabilities. Missing for 10: explicit documentation or confirmation that templates, publishing, graph, and query/view creation are all API-accessible, and independent hands-on verification of parity beyond basic CRUD/chat operations.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “Create chats, send and stream messages, react, and search chat history (anytype-heart v0.50.7)”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [claimed-docs] “The Graph is a live, visual map of every Object in your Channel and how they connect to each other.”
   • [claimed-docs] “Web Publishing lets you turn any Object into a public webpage at a URL anyone can visit.”
   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”

   proof ↗⚑ flag

   Capacities~partialprobed5/10

   Capacities ships a documented REST API (with a live OpenAPI spec) and an official hosted MCP server with both read and write scopes, letting programmatic clients create/manipulate content and integrate agents — a real API-driven workflow, not just a UI. However, no evidence shows the API/MCP exposes UI-only features like AI property auto-fill, AI image analysis, chat connectors, graph view, or templates, so full UI-API parity is not demonstrated. Missing for 10: confirmation that AI assistant features, graph view, templates, and chat connector functionality are all reachable via API/MCP, and independent hands-on verification of API completeness.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client using the Model Context Proto…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   Anytype✓fullclaimed8/10

   Anytype docs explicitly support exporting content in open formats (Markdown or Any-Block) at any time, plus local-first storage, self-hosting (including a maintained Docker image), local-only mode, and exporting/importing channels into a new identity when switching network modes — giving AI-native users a documented path to export data and leave to their own infrastructure. Missing for 10: independent/hands-on verification of export completeness and fidelity, and no detailed account of exactly what metadata/relations survive export.

   • [claimed-docs] “Choose your preferred format: Markdown or Any-Block.”
   • [claimed-docs] “You can import content into your spaces and export it at any time.”
   • [claimed-docs] “export all your channels, and import them into a new identity after switching the network mode”
   • [claimed-docs] “There's also a docker image that's maintained by the team.”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”
   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”

   proof ↗⚑ flag

   Capacities✓fullclaimed8/10

   Capacities offers full/selective export to open Markdown+CSV formats (front matter, CSV collections) explicitly designed for reuse in other apps or programmatic work, plus scheduled automated full exports, giving users a genuine 'export and leave' path. missing for 10: no independent/hands-on verification that exported data is fully lossless (e.g., all block references, embeds, graph links preserved) and no evidence of bulk data deletion/account closure workflow alongside export.

   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”
   • [claimed-docs] “Export only the selected content you intend to migrate. Use Markdown + CSV as your default format for this flow.”
   • [claimed-docs] “Export selected content as Markdown + CSV... In Capacities, go to Settings > Import Content, open the Notion guide in Migration guides, then…”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Anytype
   Anytype!disputedcontradicted4/10

   Anytype's client code is publicly visible on GitHub (anytype-ts, anytype-heart) and even labels some AI-agent tooling 'open-source', suggesting readable source; however a hands-on community report explicitly states Anytype ships under a 'source-available license' rather than a true open license, directly contradicting an open-license claim for the core product. missing for 10: an explicit OSI-approved license file/statement for the main app repos, and resolution of the source-available vs open-source discrepancy.

   • [github] “Composable blocks: text, databases, kanban, calendar & custom Types.”
   • [github] “Extensible through a gRPC API and AI "Agents" (see AGENTS.md).”
   • [community] “I found Anytype a few months ago and thought 'wow maybe I can ditch Turtl and just use this.' A few things bugged me: it's source-available …”

   proof ↗⚑ flag

   Capacities—none0/10

   No evidence of Capacities' source code being open-licensed or publicly available; it is a closed, proprietary SaaS/app with a documented API and MCP server, but no open-source repository or license is mentioned anywhere in the evidence.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Anytype
   Anytype✓fullcommunity8/10

   Anytype ships a self-hostable network node (Docker image maintained by the team) for backup/sync, plus a local-only mode that removes any dependency on Anytype's backup node entirely, and the core client itself is offline-first storing all data locally. Community input corroborates the p2p/no-central-server architecture actually working in practice. Missing for 10: independent hands-on validation of running the official self-host Docker image end-to-end, and more detail on feature parity/limits of self-hosted vs managed network.

   • [claimed-docs] “To back up your channels and data to a self-hosted network, you need to have a network configuration.”
   • [claimed-docs] “There's also a docker image that's maintained by the team.”
   • [claimed-docs] “export all your channels, and import them into a new identity after switching the network mode”
   • [claimed-docs] “This mode disables Anytype's backup node entirely—meaning multi-device syncing will only work over the same local network”
   • [claimed-docs] “you can enable local-only mode. This mode disables Anytype's backup node entirely”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”
   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”
   • [community] “(Anytype team) All your data in Anytype is encrypted at rest; only the indexes are not encrypted currently. We have plans to also encrypt th…”

   proof ↗⚑ flag

   Capacities—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

Metadata

1. power-userAttach typed properties and tags to notes and use them consistently for organization and retrieval

   weight 2 · round to Capacities
   Anytype✓fullcommunity7/10

   Anytype's documented object model lets users create custom Types and attach structured properties, then retrieve them via Queries that assemble results by defined criteria (docs-32/38, docs-8/21), which is the core of typed, consistent organization and retrieval; Templates further support consistent object creation (docs-13/22). Missing for 10: explicit documentation of a dedicated 'tag' property type (only 'Types'/relations are described) and independent verification that large-scale tagging stays consistent (one community report flags friction reconciling bulk/CSV data at scale, comm-10).

   • [claimed-docs] “Anytype comes with built-in Types, but you can create your own custom Types to match your needs.”
   • [claimed-docs] “you can create your own custom Types to match your needs.”
   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”
   • [claimed-docs] “Rather than manually curating a list of things you're looking for, you define the criteria and the Query assembles the result for you as a V…”
   • [claimed-docs] “A Template is a saved layout for a page that you can reuse.”
   • [claimed-docs] “you define what a good starting point looks like once and it'll form the base for every new Object you create afterwards”
   • [community] “I consistently find myself in need of a 'merge feature' when re-importing cleaned CSV data into Anytype database objects - the larger the da…”

   proof ↗⚑ flag

   Capacities✓fullcommunity8/10

   Capacities is explicitly object-type-first, letting users define custom object types with typed properties (front-matter on export) and tags, with AI auto-fill for properties, and search/graph/backlinks for retrieval; a HN commenter corroborates that all content becomes taggable, reusable entities in a network of notes. missing for 10: independent hands-on validation of complex multi-property queries/filtering at scale and more detailed docs on tag hierarchies or property types beyond basic examples.

   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself. The first group is what we call Basic Object T…”
   • [claimed-docs] “Capacities is object-type-first. Define key object types early (`People`, `Projects`, `Meetings`, etc.) and add core properties.”
   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself.”
   • [claimed-docs] “AI Property Auto-Fill: Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to au…”
   • [claimed-docs] “Rather than manually filling in the properties of your custom objects, you can rely on the AI model's knowledge to auto-fill them for you.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”
   • [claimed-docs] “Search in Capacities is designed to return useful results even when your wording is not exact.”
   • [claimed-docs] “Search in Capacities is great for navigation, finding, and connecting your content. It works offline on all devices, giving you quick search…”
   • [community] “Have been using it for a while now, there are really some cool new concepts... all media is automatically treated as an entity that can be r…”

   proof ↗⚑ flag

Queries

1. power-userQuery my notes by their structured properties and render live database-style views (tables, boards, lists) from those queries

   weight 3 · round to Anytype
   Anytype~partialcommunity6/10

   Anytype supports structured Types/properties and Queries that assemble live, auto-updating Views (docs describe defining criteria and getting results as a View), plus tables/kanban/calendar-style database views per the GitHub description. However, formulas are explicitly still missing per a co-founder community comment, and there's no independent hands-on evidence confirming board/list view richness or complex cross-property querying at scale. missing for 10: independent/hands-on verification of multi-view query rendering (table/board/list) beyond docs claims, confirmation of formula/aggregation support, and evidence of performance/robustness with large structured datasets.

   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”
   • [claimed-docs] “Rather than manually curating a list of things you're looking for, you define the criteria and the Query assembles the result for you as a V…”
   • [claimed-docs] “Anytype comes with built-in Types, but you can create your own custom Types to match your needs.”
   • [github] “Composable blocks: text, databases, kanban, calendar & custom Types.”
   • [community] “Anytype has tables now, simple, no formulas yet. Plan to add formulas to databases - it's one of the top requested features on our forum (co…”

   proof ↗⚑ flag

   Capacities~partialclaimed4/10

   Capacities clearly supports structured object types with custom properties (docs-26, docs-29, docs-35) and lists 'Smart queries' as a paid feature (docs-27), implying some query capability over properties, but there is no documentation describing table/board/list view rendering, filtering/sorting UI, or database-style views comparable to Notion databases. missing for 10: explicit documentation of query views (table/board/list), filter/sort UI, examples of rendering query results as live views.

   • [claimed-docs] “Task management, AI assistant, Calendar integrations, Smart queries, Task actions”
   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself. The first group is what we call Basic Object T…”
   • [claimed-docs] “Capacities is object-type-first. Define key object types early (`People`, `Projects`, `Meetings`, etc.) and add core properties.”
   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself.”

   proof ↗⚑ flag

Search

1. researcherInstantly search all my notes with full-text search plus filters on tags, properties, and paths — including offline

   weight 3 · round to Capacities
   Anytype~partialclaimed5/10

   Anytype's Queries let users filter by Type, tag, and other properties, and all data is stored locally for a genuine offline-first experience, which supports the filtering and offline parts of this story. However, the evidence never documents a full-text search feature, path-based filtering, or how these Query filters combine with a search index — missing for 10: explicit full-text search documentation, filtering by file/object 'paths', and any performance/scale claims for search across large note collections.

   • [claimed-docs] “A Query is a question you ask your knowledge base—answered instantly and kept up to date automatically.”
   • [claimed-docs] “Rather than manually curating a list of things you're looking for, you define the criteria and the Query assembles the result for you as a V…”
   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”
   • [claimed-docs] “Anytype comes with built-in Types, but you can create your own custom Types to match your needs.”
   • [claimed-docs] “you can create your own custom Types to match your needs.”

   proof ↗⚑ flag

   Capacities~partialclaimed6/10

   Docs confirm full-text search that works offline and tolerates inexact wording (capacities-docs-10, capacities-docs-22, capacities-docs-13, capacities-docs-37), and object types/tags/properties exist as structural concepts (capacities-docs-26, capacities-docs-35). However, no evidence documents explicit search filters/query syntax for tags, properties, or paths specifically. Missing for 10: documented filter syntax or UI for narrowing search by tag/property/path, independent hands-on confirmation of filtered search results.

   • [claimed-docs] “Search in Capacities is designed to return useful results even when your wording is not exact.”
   • [claimed-docs] “Search in Capacities is great for navigation, finding, and connecting your content. It works offline on all devices, giving you quick search…”
   • [claimed-docs] “Capacities is an offline-first application. You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “Object types are either created automatically by Capacities, or you can create them yourself. The first group is what we call Basic Object T…”

   proof ↗⚑ flag

Automation hooks

1. developerDrive the app from outside — create or open notes via a URI scheme, deep links, or a local endpoint — to wire it into my scripts and workflows

   weight 2 · round to Anytype
   Anytype✓fullprobed8/10

   Anytype ships a local-API (localhost, offline) with a documented OpenAPI spec (22 paths) that developers can call directly from scripts, plus a CLI/headless server mode and an official MCP server that fronts this API for automation — all confirmed by both docs and runtime probes. This covers programmatic create/open/search of Objects for scripting and workflow integration, though it's a REST/gRPC local API rather than a classic OS-level URI scheme/deep-link handler. Missing for 10: explicit documentation of an os-level 'anytype://' URI scheme or deep-link handler, and independent third-party corroboration beyond vendor docs/probes.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”

   proof ↗⚑ flag

   Capacities~partialprobed6/10

   Capacities exposes a documented REST API (Bearer-auth, OpenAPI spec verified live) that lets developers create and manipulate content programmatically, which satisfies the 'local endpoint' part of the story for scripting/automation. However, there is no evidence of a URI scheme or deep-link mechanism for opening/creating notes from other apps, only a hosted (not local) API and MCP server. Missing for 10: documented URI scheme or deep-link support, evidence of a local (non-cloud) endpoint, and independent confirmation of scripting workflows beyond the API docs.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750).”
   • [claimed-docs] “The Capacities API uses Bearer authentication (token-based authentication, OAuth 2.0 RFC 6750)”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”

   proof ↗⚑ flag

Plugins

1. power-userBrowse and install from a large catalog of community plugins/extensions to add features the core app doesn't ship

   weight 3 · round drawn
   Anytype—none0/10

   Anytype documents an API, CLI, MCP server, and 'Agent Skill' for scripting/AI integration, but nothing in the evidence describes a community plugin/extension marketplace or catalog that users can browse and install to add features — these integrations are developer/API surfaces, not an installable plugin ecosystem.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [github] “Extensible through a gRPC API and AI "Agents" (see AGENTS.md).”
   • [probe] “official MCP server documented at https://developers.anytype.io/docs/examples/featured/mcp/”

   proof ↗⚑ flag

   Capacities—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

2. developerBuild my own plugins against a documented extension API/SDK with samples and developer docs

   weight 2 · round to Anytype
   Anytype~partialprobed6/10

   Anytype documents a local REST API (with a real OpenAPI 3.1 spec, 22 paths) plus a CLI, an official MCP server, and an 'agents skill' example showing scripts run against Anytype data — this gives developers a documented, sample-backed way to build integrations. However there's no evidence of an actual in-app plugin/extension SDK (e.g., UI extension points, a plugin marketplace, or a formal SDK package) — the API is more integration/automation-oriented than a plugin framework. Missing for 10: an official plugin SDK/framework for extending the app itself, a plugin marketplace or registry, and broader third-party plugin examples beyond MCP/agent scripts.

   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [claimed-docs] “Anytype CLI is now available - run Anytype as a headless server for automation and scripting.”
   • [claimed-docs] “enabling AI assistants to seamlessly interact with Anytype's API through natural language.”
   • [claimed-docs] “the agent can run scripts against your Anytype data — programmatically — to handle bulk edits, transformations, and repetitive tasks”
   • [claimed-docs] “Drop it into Claude Code, Cursor, Gemini CLI, GitHub Copilot, or any other agent-capable tool, and the agent can run scripts against your An…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Anytype MCP server (npm @anyproto/anytype-mcp 1.2.10) launched keylessly via `npx -y @anyp…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the local API's machine-readable OpenAPI 3.1.0 spec (22 paths) was fetched keylessly from the vendor's …”
   • [github] “Extensible through a gRPC API and AI "Agents" (see AGENTS.md).”

   proof ↗⚑ flag

   Capacities~partialprobed5/10

   Capacities exposes a documented REST API (with OpenAPI spec, verified live) and an MCP integration standard for building external agents/bots/clients, which covers part of the 'extend Capacities programmatically' story, but there is no evidence of a true in-app plugin architecture/SDK, plugin samples, or a plugin marketplace — the docs describe API/MCP client integration rather than installable plugins running inside the product. missing for 10: dedicated plugin SDK/framework, code samples for building in-app plugins, plugin distribution/marketplace docs.

   • [claimed-docs] “The Capacities API is a REST API that allows you access, create and manipulate your content.”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client”
   • [claimed-docs] “Build your own app, agent, or bot and integrate it with a Capacities space by implementing a custom MCP client using the Model Context Proto…”
   • [probe] “PROBE runtime (recorded 2026-09-05): https://api.capacities.io/openapi.json served a machine-readable OpenAPI 3.1.0 spec ('Capacities API (B…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.capacities.io/mcp return…”
   • [probe] “official MCP server documented at https://docs.capacities.io/developer/model-context-protocol”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round to Anytype
   Anytype~partialcommunity6/10

   Anytype is local-first (data stored on-device) and offers a self-hosted network / local-only mode, giving users control over where their data physically lives rather than a fixed vendor cloud region — this indirectly satisfies data-residency concerns. However, there's no explicit multi-region cloud selection feature or documented compliance framework (e.g., EU-only hosting) — missing for 10: explicit region/residency selection UI, documented compliance certifications, and independent verification of self-host deployment satisfying legal residency requirements.

   • [claimed-docs] “To back up your channels and data to a self-hosted network, you need to have a network configuration.”
   • [claimed-docs] “There's also a docker image that's maintained by the team.”
   • [claimed-docs] “you can enable local-only mode. This mode disables Anytype's backup node entirely”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”
   • [claimed-docs] “Our infrastructure handles background syncing and backups automatically, so you retain full ownership of your data without compromising your…”
   • [community] “As a teacher I just can't use Notion or any other US-service due to GDPR concerns. I hope AnyType copies as many good Notion features so I c…”

   proof ↗⚑ flag

   Capacities—none0/10

   No evidence anywhere in the pack mentions data residency, region selection, or where user data is physically stored; docs cover offline-first sync and AI opt-in privacy but never data location choice. Missing for 10: any documentation of region/residency selection, server location options, or data hosting jurisdiction controls.

   • [claimed-docs] “Capacities is an offline-first application. You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”

   proof ↗⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round to Capacities
   Anytype~partialcommunity6/10

   Anytype's local-first, encrypted architecture ('not even Anytype can see your content', all data stored locally, offline-first) strongly implies the vendor has no access to user data and thus cannot use it for AI training, and this is reinforced by the fact that AI integrations (MCP, local API) run entirely on localhost rather than sending data to a cloud AI service. However, there is no explicit vendor statement or ToS clause addressing AI-training use of data, and community evidence notes that index data is not yet encrypted at rest, a caveat to the 'we can't see your data' claim. Missing for 10: an explicit no-AI-training policy/ToS clause, and confirmation that even metadata/indexes are excluded from any vendor-side processing.

   • [claimed-docs] “Only you can access your spaces and grant access to others — not even Anytype can see your content.”
   • [claimed-docs] “You control access. Only you can access your spaces and grant access to others — not even Anytype can see your content.”
   • [claimed-docs] “All your content is stored locally on your device... This means an offline-first experience: the app always works without an internet connec…”
   • [claimed-docs] “Our API is now available and directly included with the desktop app, running entirely on localhost. It operates fully offline”
   • [community] “(Anytype team) All your data in Anytype is encrypted at rest; only the indexes are not encrypted currently. We have plans to also encrypt th…”

   proof ↗⚑ flag

   Capacities✓fullclaimed8/10

   Capacities explicitly documents that AI features are opt-in and that no data is shared with third-party AI services unless a user activates AI features, directly addressing the training-data-prevention story. missing for 10: no independent/third-party audit or hands-on verification of the no-training-data claim beyond vendor documentation.

   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Anytype
   Anytype~partialcommunity6/10

   Anytype's local-first architecture gives strong implicit control over retention: data lives encrypted at rest on-device (anytype-docs-44, anytype-comm-9), can be exported/imported at any time (anytype-docs-20), and local-only mode lets users disable all cloud/backup-node sync entirely (anytype-docs-24, anytype-docs-30), plus self-hosting for full network control (anytype-docs-6, anytype-docs-19). However there's no explicit documented 'delete my data/account' feature, data-retention policy statement, or purge/right-to-erasure mechanism in the evidence — only inferred control via local file ownership and export. Missing for 10: explicit deletion/erasure feature or policy docs, retention period controls, and confirmation of what happens to synced/self-hosted copies upon deletion request.

   • [claimed-docs] “A Vault is an encrypted container in Anytype that you own. Everything you create lives inside your Vault, stored directly on your device.”
   • [claimed-docs] “You can import content into your spaces and export it at any time.”
   • [claimed-docs] “you can enable local-only mode. This mode disables Anytype's backup node entirely”
   • [claimed-docs] “If you prefer to fully keep your data on your device without any server to sync between your desktop and mobile, you can enable local-only m…”
   • [claimed-docs] “To back up your channels and data to a self-hosted network, you need to have a network configuration.”
   • [community] “(Anytype team) All your data in Anytype is encrypted at rest; only the indexes are not encrypted currently. We have plans to also encrypt th…”
   • [claimed-docs] “Our infrastructure handles background syncing and backups automatically, so you retain full ownership of your data without compromising your…”

   proof ↗⚑ flag

   Capacities—none0/10

   Evidence covers AI opt-in privacy (docs-16), offline/export features, and API auth, but there is no documentation of data retention policies, deletion controls, or account/data-deletion mechanisms specific to AI usage.

   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”
   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round to Capacities
   Anytype—none0/10

   The evidence pack details Anytype's local-first storage, encryption, and offline-first architecture (anytype-docs-29, anytype-docs-31, anytype-docs-43), but none of it mentions a telemetry/usage-analytics toggle or opt-out setting specifically. Privacy-by-architecture claims don't substitute for documented telemetry controls, so this applicable axis has no direct supporting evidence.

   ⚑ flag

   Capacities~partialclaimed4/10

   Capacities docs state that AI features are fully opt-in and no space data is shared with third-party AI services unless activated, which gives users control over AI-related data sharing, but there is no evidence of a general telemetry/usage-analytics opt-out setting for the app itself. Missing for 10: explicit documentation of a general telemetry/analytics opt-out toggle, independent confirmation that the app collects no usage data when opted out.

   • [claimed-docs] “AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services”

   proof ↗⚑ flag

Publish

1. researcherPublish selected notes as a browsable website — a digital garden with working links — without leaving the app

   weight 2 · round to Anytype
   Anytype✓fullclaimed8/10

   Anytype's Web Publishing feature lets users pick any Object and click Publish to generate a static HTML page on a personal subdomain (.any.org), including custom icon/cover, directly from within the app — matching the digital-garden use case with working links via the app's native linking/backlinking system. Missing for 10: no independent/community confirmation of link-following behavior between published pages or customization depth, and no evidence on bulk/multi-page publishing workflows.

   • [claimed-docs] “Web Publishing lets you turn any Object into a public webpage at a URL anyone can visit.”
   • [claimed-docs] “Pick an Object, click Publish, and Anytype generates a static HTML page hosted on your personal subdomain at .any.org/”
   • [claimed-docs] “Custom Object icon and cover — appears at the top of the page”
   • [claimed-docs] “Include a custom ANY ID — your unique handle, used for web publishing URLs”
   • [claimed-docs] “Linking on Anytype is what turns a bunch of separate notes into a connected knowledge base.”
   • [claimed-docs] “These connections become incredibly valuable. You can trace how ideas relate, see what's connected to a project”

   proof ↗⚑ flag

   Capacities—none0/10

   No evidence of any public-publishing or website/digital-garden export feature; Capacities offers only view-only sharing access, local export to Markdown/CSV, and APIs/MCP for integrations, none of which produce a browsable public website with working links.

   • [claimed-docs] “Grant others view-only access to notes”
   • [claimed-docs] “All your properties are transformed into front matter values, all collections are stored as CSV files, making it easy to reuse your content …”
   • [claimed-docs] “You can schedule automatic exports by going to Settings > Full Export > Automated Full Export > Add Schedule.”

   proof ↗⚑ flag

Collaboration

1. researcherShare a vault or space with collaborators and edit notes together without stepping on each other's changes

   weight 2 · round to Capacities
   Anytype!disputedcontradicted4/10

   Anytype's docs claim you can share a Vault/space and collaborate without sacrificing privacy, with peer-to-peer sync or self-hosting for shared editing (anytype-docs-12, anytype-docs-33, anytype-docs-39), but independent community evidence directly contradicts this: a Notion employee notes Anytype 'still lacking collaboration' and another user reports 'you can't share with others yet' as of their hands-on testing (anytype-comm-5, anytype-comm-8), and another user flags the need for a 'merge feature' when re-importing data, suggesting conflict handling for concurrent edits is immature (anytype-comm-10). Missing for 10: documented conflict-resolution/CRDT mechanics for simultaneous multi-user edits, and recent independent confirmation that sharing/collaboration works reliably today.

   • [claimed-docs] “Anytype lets you collaborate with others without sacrificing your privacy.”
   • [claimed-docs] “Collaborators don't need to provide an email address, buy a subscription, or ask anyone for permission.”
   • [claimed-docs] “You can even collaborate directly with others using peer-to-peer sync or self-host on your own network.”
   • [community] “(Notion employee) The Anytype model is really cool - they've rebuilt Lotus Notes with 21st century E2E encrypted protocols... However they a…”
   • [community] “I found Anytype a few months ago and thought 'wow maybe I can ditch Turtl and just use this.' A few things bugged me: it's source-available …”
   • [community] “I consistently find myself in need of a 'merge feature' when re-importing cleaned CSV data into Anytype database objects - the larger the da…”

   proof ↗⚑ flag

   Capacities~partialclaimed3/10

   The only sharing capability documented is view-only access to notes for others (capacities-docs-28), not true multi-user collaborative editing or conflict-free simultaneous editing of a shared vault/space. There is no evidence of real-time co-editing, presence indicators, or conflict resolution mechanisms that would let collaborators edit together without stepping on each other's changes. Missing for 10: real-time collaborative editing support, multi-editor conflict resolution, shared-space edit permissions beyond view-only, and any community/hands-on corroboration of team editing.

   • [claimed-docs] “Grant others view-only access to notes”

   proof ↗⚑ flag

Sync

1. power-userAn official sync service keeps my notes updated across all my devices with end-to-end encryption the vendor can't read

   weight 3 · round to Anytype
   Anytype!disputedcontradicted6/10

   Anytype ships an official multi-device sync via its backup-node infrastructure with claims of full E2E encryption where 'not even Anytype can see your content' (anytype-docs-31, anytype-docs-42, anytype-docs-43), and sync reportedly works well across devices (anytype-comm-9). However, a hands-on user and the vendor's own team response concretely contradict the blanket E2E claim: data is not fully encrypted on disk and 'only the indexes are not encrypted currently' (anytype-comm-8, anytype-comm-9), meaning the vendor itself confirms a gap in the encryption story it markets. missing for 10: independent security audit confirming full E2E coverage, resolution of the unencrypted-index gap, and clearer docs distinguishing at-rest vs. index encryption.

   • [claimed-docs] “Only you can access your spaces and grant access to others — not even Anytype can see your content.”
   • [claimed-docs] “Our infrastructure handles background syncing and backups automatically, so you retain full ownership of your data without compromising your…”
   • [claimed-docs] “You control access. Only you can access your spaces and grant access to others — not even Anytype can see your content.”
   • [community] “I found Anytype a few months ago and thought 'wow maybe I can ditch Turtl and just use this.' A few things bugged me: it's source-available …”
   • [community] “(Anytype team) All your data in Anytype is encrypted at rest; only the indexes are not encrypted currently. We have plans to also encrypt th…”

   proof ↗⚑ flag

   Capacities—none0/10

   There is evidence of offline-first sync ('changes get synchronized as soon as you're back online') but no mention anywhere of end-to-end encryption of sync data or a vendor-can't-read architecture; encryption claims are absent from docs, pricing, or community sources.

   • [claimed-docs] “Capacities is an offline-first application. You can work offline and your changes will get synchronized as soon as you're back online.”
   • [claimed-docs] “You can work offline and your changes will get synchronized as soon as you're back online.”

   proof ↗⚑ flag

2. power-userView a note's version history and restore earlier versions or recover deleted notes

   weight 2 · round drawn
   Anytype—none0/10

   No evidence in the pack mentions version history, restoring earlier versions, or recovering deleted notes; documentation covers sync, backup, encryption, import/export, and API/MCP integrations but never a version-history or undo/trash-recovery feature.

   ⚑ flag

   Capacities—none0/10

   No evidence anywhere in the pack of a version history feature or a way to recover deleted notes; documentation covers export, offline sync, linking, AI, and API but never mentions version history or trash/recovery.

   ⚑ flag