Logseq vs Capacities

Agent access

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

   weight 2 · round to Capacities
   Logseq—none0/10

   There is no llms.txt file (probe returned 404) and no evidence of agent-oriented docs formatted for LLM consumption; the docs are standard human-facing markdown/wiki pages.

   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”

   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 Capacities
   Logseq—none0/10

   Logseq is a desktop/mobile Electron app with a local HTTP API and plugin system, but nothing in the evidence describes a headless mode, CLI, or CI-runnable binary for automation — the HTTP API requires the desktop app to be running interactively. Missing for 10: any documented headless/CLI mode, CI examples, or automation-oriented server mode.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”

   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
   Logseq—none0/10

   Logseq documents a plugin system, HTTP API, and URL protocol for third-party integration, but nothing in the evidence pack mentions MCP servers or any mechanism for Logseq to consume MCP tools. Community comments even lament that AI tools like Claude/Codex can't be used to update pages, reinforcing the absence of MCP support.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   proof ↗⚑ 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 to Capacities
   Logseq—none0/10

   Logseq documents a local HTTP API and a plugin ecosystem for third-party integrations, but there is no mention anywhere in the evidence of an official Model Context Protocol (MCP) server or endpoint. Since Logseq is a knowledge-base platform (not itself an AI agent), shipping an official MCP server is a fair axis to ask about, but no such capability is evidenced.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”

   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 drawn
   Logseq—none0/10

   No evidence of an official Logseq CLI; the product exposes a local HTTP API, a URL protocol scheme, and plugins, but nothing about a command-line interface for AI-native automation. Missing for 10: any mention of an official CLI tool, its command set, or installation/usage docs.

   ⚑ 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
   Logseq~partialprobed6/10

   Logseq documents a local HTTP APIs server explicitly for 'external access to the database through authorization' and a separate community-maintained plugin API reference, plus a logseq:// protocol for third-party invocation — all documented, public interfaces for programmatic control. However, there's no formal machine-readable spec (probes show 404s for openapi.json/llms.txt) and a community report explicitly states losing the ability to use Claude/codex to write/update pages after a version change, indicating real-world friction for AI-driven API use. Missing for 10: a formal OpenAPI/machine spec, first-party confirmation of AI-agent compatibility, and independent corroboration that the HTTP API reliably supports agentic write workflows.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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
   Logseq—none0/10

   Logseq's local HTTP API server requires a single authorization token for full graph access, but there is no evidence of scoped or least-privilege credential issuance (e.g., read-only vs write, per-agent scopes, or permission granularity) for AI agents.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “local HTTP server to access logseq's graph”

   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 Capacities
   Logseq~partialprobed6/10

   Logseq exposes a genuine plugin API/SDK (marketplace with hundreds of packages, load-unpacked plugin support) plus a local HTTP APIs server and a logseq:// URL protocol for third-party integration, giving AI-native builders real programmatic surfaces. However, the plugin API documentation is explicitly community-driven rather than official, and probes found no OpenAPI/machine-readable spec or llms.txt for these APIs. Missing for 10: official (not community-maintained) SDK documentation, an OpenAPI/schema spec, and evidence of first-party AI-agent integration guidance.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [probe] “PROBE runtime (recorded 2026-09-05): Logseq's official plugin marketplace registry (logseq/marketplace, one directory per package) counted 6…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”

   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
   Logseq—none0/10

   Logseq offers a local HTTP API and a plugin system, but the evidence pack shows no webhook subscription mechanism (outbound event notifications) — only a local HTTP server for pull-based access and a custom URI protocol for inbound invocation. No documentation or community evidence describes subscribing to events via webhooks.

   ⚑ 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
   Logseq—none0/10

   Logseq's docs describe queries, plugins, journaling, sync, and export, but nowhere document a native AI-generated insights or suggestion feature. The only AI-adjacent mention is a community complaint that a user could no longer use Claude/codex to write/update pages, which points to third-party integration loss, not a first-party AI feature.

   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”
   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”

   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 drawn
   Logseq—none0/10

   Evidence shows Logseq has a plugin system, local HTTP API, and a custom URL protocol for third-party integration, but nothing describes autonomous, unattended background automations (e.g., schedulers, triggers, agent workflows) running without user action.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”

   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
   Logseq—none0/10

   No evidence in the docs or community pack of a built-in AI assistant inside Logseq; only third-party plugins, HTTP API, and protocol integrations exist, and one community comment references using external tools like Claude/Codex to edit pages, not a native assistant.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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 Capacities
   Logseq—none0/10

   No evidence of a native natural-language command interface, chat-based control, or AI assistant in Logseq's docs; the product is described as a block/outline-based knowledge base with query syntax and plugin APIs, not NL commands. One community comment (logseq-comm-11) references losing the ability to use Claude/Codex to edit pages, implying such capability existed only via third-party plugin integration, not a first-party feature, and it's now broken in the new DB version.

   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”
   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”

   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 drawn
   Logseq—none0/10

   There is a plugin API doc site and a local HTTP API, but no evidence of an interactive API reference with runnable examples; probes explicitly show no OpenAPI/swagger spec and no llms.txt found at the plugin docs site.

   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”

   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 Capacities
   Logseq—none0/10

   Logseq documents a local HTTP API server and a plugin API, but there is no evidence of a downloadable machine-readable spec (OpenAPI/Swagger) for either; explicit probes for openapi.json/swagger.json at the plugin docs site returned 404s.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”

   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
   Logseq—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

   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
   Logseq—none0/10

   Logseq documents a local HTTP API and a plugin API, but there is no evidence of API versioning or a documented deprecation policy anywhere in the docs; probes for openapi/llms.txt specs return 404s, and community comments (e.g., DB-version migration breaking AI tool integrations) suggest breaking changes without clear versioning guarantees.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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 Capacities
   Logseq!disputedcontradicted5/10

   Logseq documents a local HTTP APIs server explicitly built 'to support external access to the database through authorization,' which would let an agent read/write notes headlessly, plus a plugin API and logseq:// protocol for third-party invocation. However, a hands-on community report directly contradicts this working capability, stating 'Not being able to use Claude or codex anymore to write or update pages is a real deal breaker for me' — indicating the API-based read/write access broke (likely in the newer DB version). Missing for 10: confirmation the HTTP API still supports write access post-DB-migration, an official MCP server, and independent corroboration that agent read/write works reliably today.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “local HTTP server to access logseq's graph”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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
   Logseq~partialprobed5/10

   Logseq has no documented first-party AI/LLM connector, but its open plugin marketplace (617 registered packages), local HTTP API for external graph access, and logseq:// protocol for third-party app integration provide an ecosystem pathway for AI plugins/tools to connect to notes. Community evidence confirms some users did integrate LLMs like Claude/codex to write/update pages, but also that this broke in the newer DB version, showing fragility rather than a robust first-party AI integration story. Missing for 10: an official AI/LLM connector or documented AI plugin category, first-party docs mentioning LLM integration, and confirmation that AI plugin workflows are stable across versions.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [probe] “PROBE runtime (recorded 2026-09-05): Logseq's official plugin marketplace registry (logseq/marketplace, one directory per package) counted 6…”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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
   Logseq—none0/10

   Logseq's own docs describe journals, queries, plugins, HTTP API, and sync, but there is no evidence of a built-in first-party AI assistant that answers/summarizes/drafts grounded in notes with data-visibility controls. A community comment even references losing the ability to use Claude/Codex on notes after a version change, implying any AI usage was via external plugins/tools rather than a native assistant.

   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”
   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”

   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 Logseq
   Logseq~partialclaimed4/10

   Logseq exposes a local HTTP API and plugin system that could be used to script bulk edits across many blocks/pages, and its query language ({{query}}) can surface many items at once, but there is no documented native bulk-operation feature (e.g., mass rename, bulk tag, batch move) demonstrated in the evidence pack. missing for 10: explicit bulk-edit/bulk-update API or UI feature, evidence of an AI agent actually performing bulk operations via the HTTP API, independent hands-on confirmation of scale.

   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “Simple queries by using `{{query }}`... You can type `/query` to create a simple query.”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”

   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
   Logseq—none0/10

   Logseq's docs describe journaling, queries, plugins, HTTP APIs, and protocol handlers, but nowhere document a rules/trigger system where user-defined events automatically fire actions (e.g., 'when block tagged X, do Y'). The plugin API and marketplace could theoretically enable such automation, but no evidence shows a first-party or documented feature for event-triggered rules.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”

   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
   Logseq—none0/10

   No evidence of any scheduling, cron-like, or recurring workflow/automation capability in Logseq's docs or community discussion; the docs cover journaling, queries, plugins, HTTP API, and sync but nothing about triggering recurring jobs or automated workflows.

   ⚑ 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
   Logseq—none0/10

   Logseq's evidence covers notes, queries, plugins, HTTP API, and sync, but there is no mention of any 'automation' construct (workflows, macros, agent actions) that could be versioned, reviewed, or rolled back — plugins are installed/updated/removed, not versioned as automations, and markdown files aren't presented as an automation history mechanism.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “From this dashboard, third-party plugins from the [[Marketplace]], can be searched, installed, updated and removed.”
   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the [[Marketplace]], can be searched, installed, upd…”
   • [claimed-docs] “third-party plugins from the [[Marketplace]], can be searched, installed, updated and removed.”

   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 to Logseq
   Logseq~partialclaimed4/10

   Logseq documents a 'Quick capture' feature via the logseq:// protocol that can be added as a browser bookmarklet or invoked from command line, letting users capture short text and links into notes (logseq-docs-11, logseq-docs-17, logseq-docs-27, logseq-docs-22). However, this is a lightweight bookmarklet, not a dedicated official browser-extension web clipper capable of capturing full articles, page content, or highlights as many competing tools offer. Missing for 10: an official browser extension/clipper product, support for capturing full article content or highlighted text with metadata, and any independent/hands-on evidence of researchers using this capture flow for web clipping.

   • [claimed-docs] “logseq://x-callback-url/quickCapture? ... Quick capture for short text and links. Can be added as a bookmark link to modern browser”
   • [claimed-docs] “logseq://x-callback-url/quickCapture? - Quick capture for short text and links.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [claimed-docs] “Quick capture for short text and links. Can be added as a bookmark link to modern browser or opened from command line shell”

   proof ↗⚑ 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 Logseq
   Logseq✓fullclaimed8/10

   Docs confirm Logseq opens to the Journals page every time you launch it ([logseq-docs-24]), that a new dated journal page is auto-created daily at midnight ([logseq-docs-2]), and that this page serves as the equivalent of a daily-notes capture landing page ([logseq-docs-1]). Missing for 10: explicit documentation of a customizable 'journal template' pre-fill mechanism and independent/hands-on confirmation that templates apply automatically to new daily notes.

   • [claimed-docs] “Every time you open Logseq, you start on the Journals page.”
   • [claimed-docs] “Every day at midnight a new Journals page is created with that day's date, making it easy to see when you've added what information.”
   • [claimed-docs] “For people familiar with Roam Research: the Journals page in Logseq is the same as the Daily Notes Page in Roam.”

   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 to Capacities
   Logseq—none0/10

   The evidence pack contains no documentation or community mentions of Logseq's template feature (e.g. `template::` property, `/template` command, or variable substitution like date/title) — only journals, page/block references, queries, plugins, sync, and publishing are covered. Since template creation is a plausible and well-known capability for a note-taking tool, its complete absence from the evidence means this axis cannot be credited as delivered.

   ⚑ 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 Logseq
   Logseq!disputedcontradicted4/10

   The evidence pack lacks any first-party documentation specifically describing headings, callouts, tables, code blocks, or media-embedding support, and instead shows only adjacent editor features (page/block references, journals) that imply block-based markdown editing. Concrete hands-on reports contradict the 'fast, keyboard-driven' claim: pasting multi-paragraph text broke formatting into unwanted lists and even crashed on longer pastes, and users report severe UI lag once graphs grow, undermining the 'fast' editing experience for power users. Missing for 10: explicit docs on headings/callouts/tables/code-block syntax, embedded media handling, and independent confirmation that these specific formatting features perform well at scale.

   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”
   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [community] “I used Logseq for a while but the big problem I had with it is how strongly it is focused on bullet points. Posting long form text is cumber…”
   • [community] “Admittedly poor performance has been my primary gripe in the 7mos I've been using LogSeq on a near-daily basis... I'd gladly pay for a subsc…”
   • [community] “Indexing and general responsiveness slows down massively once you have a few million words stored, and you have to break up your data into m…”

   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 Capacities
   Logseq!disputedcontradicted5/10

   Logseq documents a genuine multi-format Export feature (Markdown, HTML, OPML, JSON, EDN, PNG) and historically stores data as local plain Markdown files, supporting easy exit at any time [logseq-docs-8]. However, hands-on community reports contradict the 'open, portable' framing: exported Markdown adds non-standard formatting that breaks compatibility with other Markdown apps like Obsidian [logseq-comm-19], and the newer Logseq DB version reportedly moves away from storing everything as plain markdown files, alarming users who relied on that for portability [logseq-comm-14, logseq-comm-9]. Missing for 10: independent verification that exports are lossless/round-trippable, clarity on whether DB-version graphs can still export to plain markdown, and confirmation the export covers all data (assets, whiteboards, plugins config).

   • [claimed-docs] “The Logseq Export feature allows users to export their data in various formats, including text, HTML, OPML, PNG, EDN, JSON, and standard Mar…”
   • [community] “The MarkDown files it generates aren't compatible with other similar programs (Obsidian for instance). It adds 2 spaces which makes things i…”
   • [community] “Logseq remained a buggy mess, is now on an unmaintained (thus insecure) version of electron. And now after several years of complete stagnat…”
   • [community] “Yeah I felt the same about the decision when they decided to move to database structure. If it had this structure from the start it could've…”

   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 Capacities
   Logseq—none0/10

   The evidence pack documents Logseq's export formats and journal/page structure comparisons to Roam, but contains no mention of an import feature for Notion, Evernote, Roam exports, or Markdown migration with links/attachments preserved. Community comments mention switching from Roam via GitHub sync, not a structured import tool. Since import tooling is a plausible feature for a PKM app, absence of evidence means 'none' rather than 'na'.

   • [claimed-docs] “The Logseq Export feature allows users to export their data in various formats, including text, HTML, OPML, PNG, EDN, JSON, and standard Mar…”
   • [claimed-docs] “For people familiar with Roam Research: the Journals page in Logseq is the same as the Daily Notes Page in Roam.”
   • [community] “I switched over to LogSeq from Roam Research, and I'm using Github for syncing and backup.”

   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 drawn
   Logseq~partialcommunity5/10

   Logseq's documented linking primitives — page/block references ([[ ]], (( ))) and simple queries ({{query}}) — provide the backbone for connecting and filtering notes, and the Whiteboard feature offers a spatial canvas with connectors for arranging knowledge visually, but no evidence explicitly documents a dedicated interactive 'graph view' with node-link visualization or filtering controls. Community reports also note serious performance degradation ('indexing and general responsiveness slows down massively once you have a few million words') which would hamper exploring a large graph. missing for 10: explicit documentation of the graph-view visualization UI and its filtering options, and independent confirmation that graph exploration performs well at scale.

   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”
   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “Simple queries by using `{{query }}`... You can type `/query` to create a simple query.”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”
   • [claimed-docs] “Put thoughts from your knowledge base as well as new ones next to each other on a spatial canvas together with shapes, drawings, website emb…”
   • [community] “Indexing and general responsiveness slows down massively once you have a few million words stored, and you have to break up your data into m…”

   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 Logseq
   Logseq~partialcommunity7/10

   Docs confirm core wiki-linking mechanics ([[ ]] page references, (( )) block references, journals as the default landing page) and queries for surfacing related content, which underpins backlinking functionality core to Logseq's outliner design. However, the evidence pack never explicitly documents a dedicated 'Linked References' or 'unlinked references' UI panel showing backlinks-in-context, which is a well-known Logseq feature but unevidenced here; community notes instead focus on performance/sync issues rather than confirming backlink display quality. Missing for 10: explicit docs/evidence on the Linked References and Unlinked References panels, independent hands-on confirmation of backlink context display working well at scale.

   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”
   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “Simple queries by using `{{query }}`... You can type `/query` to create a simple query.”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”
   • [claimed-docs] “Every time you open Logseq, you start on the Journals page.”
   • [community] “Indexing and general responsiveness slows down massively once you have a few million words stored, and you have to break up your data into m…”

   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 drawn
   Logseq✓fullclaimed8/10

   Logseq's block reference syntax `(())` embeds/transcludes an individual block from any page into another, and page references `[[]]` do the same at page level; since Logseq's block-based architecture keeps a single canonical block that references simply render/link to, edits propagate automatically, keeping transclusions in sync. Docs explicitly describe both block and page referencing as core features. Missing for 10: no explicit doc quote confirming live-sync behavior on edit (implied by architecture, not directly demonstrated) and no independent hands-on confirmation of transclusion sync specifically.

   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”
   • [claimed-docs] “Blocks that have a page as a parent i.e. usually top-level blocks can be converted to a page and back to a block easily. To convert this blo…”

   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 Logseq
   Logseq~partialcommunity6/10

   Logseq's classic (file) mode stores notes as plain Markdown on local disk, exports to multiple open formats, and only publishes pages explicitly (docs-8, docs-7, docs-23), supporting the 'own your files, work offline' story; community users confirm they read/back up the raw Markdown files themselves (comm-1, comm-19, comm-7). However, the newer DB-based version raises real doubts: a user explicitly states 'I can no longer keep all my data as markdown files' with the new format (comm-14), and others cite years of stagnation, sync bugs, and performance/data-loss concerns (comm-3, comm-5, comm-6, comm-8) that undercut confidence in durable, app-independent local ownership going forward. missing for 10: clear first-party confirmation that the DB version still exposes plain-text/local files, independent verification of offline reliability at scale, and resolution of the data-loss/performance complaints.

   • [claimed-docs] “The Logseq Export feature allows users to export their data in various formats, including text, HTML, OPML, PNG, EDN, JSON, and standard Mar…”
   • [claimed-docs] “By default no pages are public. Individual pages can be marked as public with the property `publish:: true`.”
   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [community] “I switched over to LogSeq from Roam Research, and I'm using Github for syncing and backup.”
   • [community] “The MarkDown files it generates aren't compatible with other similar programs (Obsidian for instance). It adds 2 spaces which makes things i…”
   • [community] “I use Logseq personally and for work almost daily since a year ago or so. It's pretty nice and the 'least bad' PKM platform I'm aware of (no…”
   • [community] “Logseq remained a buggy mess, is now on an unmaintained (thus insecure) version of electron. And now after several years of complete stagnat…”
   • [community] “I had two main problems with LogSeq: 1. Not designed from the ground-up to prevent data loss. Has had data-loss issues in the past.”
   • [community] “Admittedly poor performance has been my primary gripe in the 7mos I've been using LogSeq on a near-daily basis... I'd gladly pay for a subsc…”

   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 to Capacities
   Logseq!disputedcontradicted5/10

   Logseq's docs confirm export to open, documented formats (Markdown, JSON, EDN, OPML) and its journal-based local storage model, supporting archive portability (logseq-docs-8). However, hands-on community reports contradict full open-format durability: users note the generated Markdown isn't standard-compliant/interoperable with other tools due to extra indentation (logseq-comm-19), and the newer DB-based version reportedly abandons plain Markdown as the storage format entirely, forcing users into a proprietary DB structure (logseq-comm-14). Missing for 10: confirmation that the current/default file storage (not just export) remains plain Markdown across versions, and independent verification that exported files are lossless/interoperable.

   • [claimed-docs] “The Logseq Export feature allows users to export their data in various formats, including text, HTML, OPML, PNG, EDN, JSON, and standard Mar…”
   • [community] “The MarkDown files it generates aren't compatible with other similar programs (Obsidian for instance). It adds 2 spaces which makes things i…”
   • [community] “Logseq remained a buggy mess, is now on an unmaintained (thus insecure) version of electron. And now after several years of complete stagnat…”

   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 Logseq
   Logseq✓fullcommunity7/10

   Logseq stores data as local Markdown/EDN files by default with no cloud requirement, and is documented as 'privacy-first' — users confirm they run it fully local or pair it with self-managed sync like GitHub instead of vendor cloud. The official Logseq Sync exists only as an optional paid vendor-hosted add-on, not a self-hosted backend, and one user explicitly notes there's no built-in way to self-host it as a server despite an open feature request. missing for 10: an officially supported self-hosted sync backend (only vendor-cloud Sync or DIY git workflows exist), and independent verification that local mode has no offline degradation.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”
   • [community] “I switched over to LogSeq from Roam Research, and I'm using Github for syncing and backup.”
   • [community] “I use Logseq personally and for work almost daily since a year ago or so. It's pretty nice and the 'least bad' PKM platform I'm aware of (no…”
   • [community] “I know Logseq is intended as an offline-first solution, but I really wish I could self-host it as a website and have all notes saved on my s…”

   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 drawn
   Logseq—none0/10

   Evidence confirms Logseq has mobile apps (iOS/Android sync up to 10 graphs, end-to-end encrypted) but contains no evidence about the actual feature set of the mobile apps themselves — no mention of whether search, linking, queries, or full editing capabilities are present on mobile versus a stripped-down capture-only experience. Community commentary focuses on desktop performance/sync bugs, not mobile app completeness.

   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”

   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 Capacities
   Logseq!disputedcontradicted4/10

   Logseq docs describe a local HTTP APIs server for external access to the graph, a community-documented plugin API, and a logseq:// protocol for third-party invocation, suggesting programmatic access beyond the UI (logseq-docs-6, logseq-docs-21, logseq-docs-12, logseq-docs-22). However, there's no documentation showing this API surface covers 'everything' the UI can do (queries, whiteboards, publishing, sync are UI-first features with no documented API equivalents), and a hands-on user reports that after the move to the new DB version, 'Not being able to use Claude or codex anymore to write or update pages is a real deal breaker' — a concrete failure of AI-driven read/write parity (logseq-comm-11). missing for 10: full API coverage of queries/whiteboard/publish/sync, evidence of AI tools reliably reading+writing via API in the current version, independent confirmation the HTTP API matches UI capability breadth.

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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 to Capacities
   Logseq~partialcommunity6/10

   Logseq's docs describe a native local-markdown storage model plus an explicit Export feature covering text, HTML, OPML, PNG, EDN, JSON and standard Markdown, which supports data portability and offline 'leave anytime' use (logseq-docs-8). However, community reports note markdown output isn't cleanly interoperable with other markdown apps due to formatting quirks (logseq-comm-19), and the newer DB-based version is criticized for moving away from plain markdown files as the source of truth, undermining the 'leave in open formats' guarantee for that version (logseq-comm-14). Missing for 10: independent verification that exported formats round-trip cleanly into other tools, and clarity on export fidelity in the new DB architecture.

   • [claimed-docs] “The Logseq Export feature allows users to export their data in various formats, including text, HTML, OPML, PNG, EDN, JSON, and standard Mar…”
   • [community] “The MarkDown files it generates aren't compatible with other similar programs (Obsidian for instance). It adds 2 spaces which makes things i…”
   • [community] “Logseq remained a buggy mess, is now on an unmaintained (thus insecure) version of electron. And now after several years of complete stagnat…”

   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 Logseq
   Logseq✓fullcommunity8/10

   Logseq is explicitly described as "open-source" (logseq-docs-23), and its docs, plugin ecosystem, and marketplace are hosted publicly on GitHub, implying the source is inspectable and openly licensed; community comments corroborate "local data and source availability are important factors" (logseq-comm-7). missing for 10: explicit citation of the actual license name/terms (e.g., AGPL) and any independent audit or discussion of license compliance.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [community] “I use Logseq personally and for work almost daily since a year ago or so. It's pretty nice and the 'least bad' PKM platform I'm aware of (no…”

   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 Logseq
   Logseq~partialcommunity5/10

   Logseq is open-source and stores data locally as markdown files (docs-23), and offers a local HTTP API for accessing your own graph (logseq-docs-6, logseq-docs-21), which supports a 'run entirely on your own machine' notion of self-hosting. However, there is no official self-hosted server/web deployment: a community member explicitly wished they could self-host Logseq as a website with notes on their own server, noting this remains an open, unresolved GitHub feature request among 1.8k open issues (logseq-comm-20), and official Sync is a paid, vendor-hosted cloud service rather than a self-hostable component (logseq-docs-10, logseq-comm-2). Missing for 10: an official self-hosted server/backend deployment option, first-party documentation for hosting the app as a service, and confirmation that the open feature request has been resolved.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [community] “I know Logseq is intended as an offline-first solution, but I really wish I could self-host it as a website and have all notes saved on my s…”
   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [community] “Logseq's own sync is now in testing and you can access it if you're a sponsor ($15/month tier)... It works fine but has enough bugs that I w…”

   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
   Logseq~partialclaimed6/10

   Docs confirm block/page tagging (`#Page`) and properties (e.g., `publish:: true`), plus page/block references and query blocks (`{{query}}`) that can retrieve content by tags/properties. However, the evidence pack lacks dedicated documentation on Logseq's typed-property system (property schemas, value types, advanced query filtering by property) and no independent confirmation of consistent power-user workflows using properties for retrieval. Missing for 10: explicit docs on property types/schema, advanced query examples filtering by properties, and hands-on validation of consistent tagging/property retrieval at scale.

   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”
   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “By default no pages are public. Individual pages can be marked as public with the property `publish:: true`.”
   • [claimed-docs] “Simple queries by using `{{query }}`... You can type `/query` to create a simple query.”
   • [claimed-docs] “Blocks that have a page as a parent i.e. usually top-level blocks can be converted to a page and back to a block easily. To convert this blo…”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”

   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 Capacities
   Logseq~partialclaimed3/10

   Docs confirm a core query feature ({{query}} / /query) for asking questions of the knowledge base, and structured page/block references exist, but the pack never documents property-based structured queries or dynamic table/board/list rendering views (advanced query mode, query views like {{table}}) that power users need. missing for 10: documentation of advanced/structured-property queries, table/board/list view rendering from queries, and any hands-on confirmation of these views working.

   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “Simple queries by using `{{query }}`... You can type `/query` to create a simple query.”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”
   • [claimed-docs] “Blocks that have a page as a parent i.e. usually top-level blocks can be converted to a page and back to a block easily. To convert this blo…”

   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
   Logseq!disputedcontradicted5/10

   Logseq's docs describe a query system ({{query}}) for searching the knowledge base and page/block references and tags for organization (logseq-docs-4, -16, -19, -3), and it markets itself as privacy-first/local/offline (logseq-docs-23). However, hands-on community reports directly contradict the 'instant' part of the story: users report that 'indexing and general responsiveness slows down massively once you have a few million words stored' and describe persistent lag navigating pages even after months of daily use (logseq-comm-5, logseq-comm-6). Missing for 10: explicit documentation of a dedicated full-text search UI with tag/property/path filters (only generic query syntax is shown), and no independent benchmark confirming fast search at scale to offset the reported slowdowns.

   • [claimed-docs] “Simple queries by using `{{query }}`, the format is something like this: {{query Something you're looking for}}”
   • [claimed-docs] “Simple queries by using `{{query }}`... You can type `/query` to create a simple query.”
   • [claimed-docs] “Queries are for asking questions from your knowledge base and the outside world (in the future).”
   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”
   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [community] “Admittedly poor performance has been my primary gripe in the 7mos I've been using LogSeq on a near-daily basis... I'd gladly pay for a subsc…”
   • [community] “Indexing and general responsiveness slows down massively once you have a few million words stored, and you have to break up your data into m…”

   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 Logseq
   Logseq✓fullprobed8/10

   Logseq documents both a URI scheme (logseq://x-callback-url/quickCapture) that can be triggered from browser bookmarks or command line to capture/open notes, and a local HTTP APIs server enabling authorized external programmatic access to the graph — directly matching the story's ask for deep links and a local endpoint for scripting. Missing for 10: independent/hands-on confirmation of the HTTP API's request/response schema or third-party integration examples, and no evidence of a broader public REST API spec (openapi probes returned 404).

   • [claimed-docs] “local HTTP server to access logseq's graph ... Enable HTTP APIs server in `Features > HTTP APIs server`”
   • [claimed-docs] “logseq://x-callback-url/quickCapture? ... Quick capture for short text and links. Can be added as a bookmark link to modern browser”
   • [claimed-docs] “logseq://x-callback-url/quickCapture? - Quick capture for short text and links.”
   • [claimed-docs] “we developed the local HTTP server to support external access to the database through authorization.”
   • [claimed-docs] “Logseq provides a protocol `logseq://` to allow third party applications to invoke actions within Logseq.”
   • [claimed-docs] “Quick capture for short text and links. Can be added as a bookmark link to modern browser or opened from command line shell”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”

   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 to Logseq
   Logseq✓fullprobed8/10

   Logseq ships an in-app Marketplace dashboard to search/install/update/remove third-party plugins, plus a documented plugin API and community docs site, and a runtime probe confirms 617 published plugin packages in the official registry. Community commentary notes Logseq's ecosystem is smaller/less mature than Obsidian's, but doesn't dispute that a working plugin catalog exists. Missing for 10: independent hands-on account of browsing/installing a plugin, and quantification of catalog quality/curation vs. just count.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “From this dashboard, third-party plugins from the [[Marketplace]], can be searched, installed, updated and removed.”
   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the [[Marketplace]], can be searched, installed, upd…”
   • [claimed-docs] “Click on `Load unpacked plugin` to load plugins that are distributed outside the marketplace.”
   • [claimed-docs] “third-party plugins from the [[Marketplace]], can be searched, installed, updated and removed.”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [probe] “PROBE runtime (recorded 2026-09-05): Logseq's official plugin marketplace registry (logseq/marketplace, one directory per package) counted 6…”
   • [community] “Yeah I felt the same about the decision when they decided to move to database structure. If it had this structure from the start it could've…”

   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 Logseq
   Logseq~partialprobed6/10

   Logseq has a documented plugin API (plugins-doc.logseq.com, described as community-driven documentation for the SDK) plus in-app tooling for loading unpacked/dev plugins and a marketplace with 617 published packages showing a real developer ecosystem. However, the core API docs are explicitly community-maintained rather than official first-party reference docs with samples, and probes show no llms.txt/openapi spec, suggesting thinner formal SDK documentation than top competitors. Missing for 10: official first-party API reference with code samples/tutorials, and machine-readable API spec (openapi/llms.txt) confirming documented completeness.

   • [claimed-docs] “Extends the functionality of logseq with third party tools ... third-party plugins from the Marketplace, can be searched, installed, updated…”
   • [claimed-docs] “This is a community-driven documentation for Logseq plugin APIs.”
   • [claimed-docs] “Click on `Load unpacked plugin` to load plugins that are distributed outside the marketplace.”
   • [probe] “PROBE runtime (recorded 2026-09-05): Logseq's official plugin marketplace registry (logseq/marketplace, one directory per package) counted 6…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://plugins-doc.logseq.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plugins-doc.logseq.com/openapi.json, https://plugins-doc.logseq.com/swagger.json, https://pl…”

   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 Logseq
   Logseq~partialcommunity6/10

   Logseq stores data as local markdown/EDN files by default, giving users full control over where their data physically resides (their own device, self-hosted git repos, etc.), and its optional Sync service is end-to-end encrypted, which aligns with a privacy-first, local-first posture. However, there is no documented feature letting users select a specific data-center region for the Sync service, and community reports note sync reliability issues and no self-hosting option for a hosted graph. Missing for 10: explicit region/residency selection controls for the cloud Sync product, first-party documentation on where Sync servers are physically located, and confirmation that self-hosting/regional choice is officially supported rather than just achievable via local storage or third-party git.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”
   • [community] “I switched over to LogSeq from Roam Research, and I'm using Github for syncing and backup.”
   • [community] “Logseq's own sync is now in testing and you can access it if you're a sponsor ($15/month tier)... It works fine but has enough bugs that I w…”
   • [community] “I know Logseq is intended as an offline-first solution, but I really wish I could self-host it as a website and have all notes saved on my s…”

   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
   Logseq~partialcommunity3/10

   Logseq positions itself as a 'privacy-first, open-source knowledge base' with local-first storage and end-to-end encrypted sync, which implies user data isn't funneled to a cloud AI training pipeline by default, but no evidence explicitly states a policy on AI model training use of user data. Missing for 10: explicit statement addressing AI training data usage, any opt-out/consent controls for AI features, and confirmation that plugins or integrations (e.g., Claude/Codex mentioned in community posts) don't send data to third-party AI services.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”
   • [community] “I've got so much already in logseq though, and I really like the model. Right now I'm thinking I'll just stay on version one as long as poss…”

   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 Logseq
   Logseq~partialclaimed5/10

   Logseq stores graphs as local Markdown files and is marketed as 'privacy-first,' implying users can delete or retain data simply by managing local files, and Export lets users extract data in multiple formats; optional Sync is end-to-end encrypted. However, there is no explicit documentation on deletion mechanics for synced/cloud data, data-retention policies, or how to purge synced copies across devices. Missing for 10: documented data-retention/deletion policy, explicit instructions for deleting synced cloud data, and independent verification that deletion is complete and irreversible.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”
   • [claimed-docs] “The Logseq Export feature allows users to export their data in various formats, including text, HTML, OPML, PNG, EDN, JSON, and standard Mar…”
   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”

   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
   Logseq—none0/10

   The evidence describes Logseq as 'privacy-first, open-source' and local-first, implying no telemetry infrastructure exists, but there is no explicit documentation of a telemetry/usage-tracking feature or an opt-out setting for it. Absence of concrete evidence of an actual telemetry toggle means this cannot be confirmed as full/partial delivery. Missing for 10: explicit telemetry/analytics policy documentation, evidence of an opt-out setting or confirmation that no tracking occurs at all.

   • [claimed-docs] “Logseq: A privacy-first, open-source knowledge base”

   proof ↗⚑ 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 Logseq
   Logseq✓fullclaimed7/10

   Logseq's Publishing docs confirm per-page publish:: true flags to selectively expose notes, and the Publish feature generates a browsable static SPA site with working page/block references intact, matching the digital-garden use case entirely within the app. missing for 10: no independent/hands-on report confirming the exported site's link integrity or ease of workflow, and no detail on hosting/deployment specifics or custom domain support.

   • [claimed-docs] “By default no pages are public. Individual pages can be marked as public with the property `publish:: true`.”
   • [claimed-docs] “This feature publishes a graph as a [[Publish Web]], single page application (SPA).”
   • [claimed-docs] “Type `[[]]` to create or reference any other page. You can also make a new page in the search bar. - Type `(())` to reference a block on any…”

   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
   Logseq—none0/10

   Logseq's Sync feature is described as syncing a user's own graphs across their own devices (desktop/Android/iOS), not as multi-user real-time collaborative editing with conflict resolution; community reports describe using GitHub for personal sync/backup and note Logseq's own sync was still buggy/beta, with no evidence of concurrent multi-collaborator editing safeguards.

   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”
   • [community] “I switched over to LogSeq from Roam Research, and I'm using Github for syncing and backup.”
   • [community] “Logseq's own sync is now in testing and you can access it if you're a sponsor ($15/month tier)... It works fine but has enough bugs that I w…”
   • [community] “I still use Logseq and conceptually it's still a great method for building a second brain. But it has been dormant for years and early attem…”

   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 Logseq
   Logseq!disputedcontradicted5/10

   Docs confirm an official Logseq Sync service across Desktop/Android/iOS with explicit end-to-end encryption ('Yes, your graph is end-to-end encrypted'), fitting the story's claim. However, community reports directly contradict reliable delivery: one user in 2022 found the paid sync beta 'has enough bugs that I wouldn't rely on it yet,' and another in 2025 stated 'early attempts at syncing didn't work well... I paid to support the sync effort but we saw nothing for years,' indicating the sync feature has a documented history of not working as promised despite payment. Missing for 10: independent verification that sync is now stable/production-ready, technical detail on the E2EE key model, and resolution of the multi-year reliability complaints.

   • [claimed-docs] “Syncs up to 10 graphs between Logseq Desktop, Android, and iOS.”
   • [claimed-docs] “Yes, your graph is end-to-end encrypted.”
   • [community] “Logseq's own sync is now in testing and you can access it if you're a sponsor ($15/month tier)... It works fine but has enough bugs that I w…”
   • [community] “I still use Logseq and conceptually it's still a great method for building a second brain. But it has been dormant for years and early attem…”
   • [community] “I loved what Logseq had to offer, and setup monthly donations for a while, but after the long period of apparent stagnation I lost faith and…”

   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
   Logseq—none0/10

   The evidence pack contains no documentation of a native version-history or restore/undo-delete feature in Logseq; users instead rely on external tools like Git for backup (logseq-comm-1), and there are reports of past data-loss issues (logseq-comm-3), but no built-in mechanism to view or restore prior versions of a note is described.

   • [community] “I switched over to LogSeq from Roam Research, and I'm using Github for syncing and backup.”
   • [community] “I had two main problems with LogSeq: 1. Not designed from the ground-up to prevent data loss. Has had data-loss issues in the past.”

   proof ↗⚑ 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