Logseq vs Poly

Agent access

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

   weight 2 · round to Poly
   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

   Poly✓fullprobed9/10

   Poly directly serves an llms.txt with a full agent-oriented documentation index, confirmed live via runtime probe (HTTP 200, structured docs list, companion llms-full.txt, /raw/*.md mirrors of every page), explicitly designed for agent consumption alongside CLI and MCP integration docs. Missing for 10: no independent third-party report of an agent actually using llms.txt to onboard, only first-party docs and probes.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.poly.app/llms.txt # docs.poly.app > Poly documentation ## Documentation Sets - [docs.poly.app](h…”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   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

   Poly~partialprobed4/10

   The `poly` CLI is explicitly described as 'scriptable from the terminal' (poly-docs-17) and supports commands like `poly search` (poly-docs-6), suggesting scriptable automation is possible, and the MCP server exists for programmatic agent access (poly-probe-rt-2). However, both the CLI and MCP server rely on browser-based OAuth authentication (poly-probe-rt-2), which is a significant barrier to headless/CI use, and there is no documentation of API keys, service accounts, or CI-specific setup for non-interactive automation. Missing for 10: documented headless/non-interactive auth method (API key or service token), explicit CI/automation examples or docs, evidence of running without a browser session.

   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”

   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

   Poly—none0/10

   All MCP-related evidence describes Poly exposing its own hosted MCP server (mcp.poly.app) for external AI assistants like Claude Code, Codex, ChatGPT, etc. to consume — i.e., Poly acting as the MCP *server* — not Poly acting as an MCP *client* that can plug in and use tools from third-party MCP servers. No documentation, CLI reference, or probe shows Poly's built-in agent connecting to or consuming external MCP servers.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   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

   Poly✓fullprobed9/10

   Poly documents and runtime-verifies an official hosted MCP server (mcp.poly.app/mcp) with OAuth auth, exposing search/fetch/CLI tools, and it's usable from Claude Code, ChatGPT, Codex, Gemini, and other MCP clients. missing for 10: independent third-party (non-vendor) confirmation of a successful end-to-end agent connection beyond the probe and docs.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Poly
   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

   Poly✓fullprobed8/10

   Poly ships a documented official CLI (`poly`) with 25+ commands for searching, reading, creating, and organizing files from the terminal, plus an agent-skill that composes CLI commands, confirmed by both docs and a runtime probe. missing for 10: independent/hands-on community verification of the CLI itself (community evidence discusses filesystem access concerns, not CLI usage) and no visible changelog/versioning depth for the CLI beyond docs.

   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “The [`poly-cli` agent skill] teaches an agent how to search, read, create, update, and organize your Poly files by composing `poly` commands…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   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

   Poly~partialprobed7/10

   Poly documents a CLI (`poly` with 25+ commands) and a hosted MCP server (https://mcp.poly.app/mcp with OAuth) that let AI agents and assistants drive file search, read, write, and organization programmatically, confirmed by both docs and a live runtime probe. However, there is no conventional public REST/OpenAPI API — probes for openapi.json/swagger.json all returned 404 — so agentic access is limited to MCP/CLI surfaces rather than a general-purpose documented API. missing for 10: a REST/OpenAPI-documented API, independent third-party corroboration of API usage beyond vendor docs.

   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Poly—none0/10

   Poly's MCP/agent integrations use a single OAuth login granting 'full access to your Poly files' (poly-docs-30, poly-docs-29) rather than any scoped or least-privilege credential/token mechanism; no docs mention granular permission scopes, read-only vs write tokens, or per-agent credential issuance. This axis is applicable (Poly ships agent/API integrations) but no evidence supports scoped credentialing — missing for 10: any documented scope/permission model, token-level restriction, or least-privilege API key issuance for agents.

   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [claimed-docs] “Give Claude Code persistent context and full access to your Poly files.”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Logseq
   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

   Poly—none0/10

   Evidence shows a CLI and an MCP server integration, but no official SDK (Python/JS/etc.) or API client library is documented; the OpenAPI probe returned 404s across all candidate paths, indicating no formal API spec developers could build an SDK against.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”

   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

   Poly—none0/10

   No evidence of any webhook or event-subscription mechanism; Poly's integration surface is limited to MCP, CLI, and file sync, none of which describes outbound event notifications via webhooks.

   ⚑ flag

Agentic features

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

   weight 2 · round to Poly
   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

   Poly✓fullprobed7/10

   Poly's docs describe natural-language search, an automatic 'second brain' memory layer, and an agent that can summarize, explain, and generate insights from indexed files (docs-2, docs-3, docs-31, docs-14), directly matching the AI-generated insights/suggestions story. Missing for 10: independent/hands-on evidence of proactive insight generation (vs. just search/summarize-on-request) and no third-party validation of insight quality beyond vendor docs.

   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”
   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “It automatically parses, transcribes, and indexes your files that make it up to 20x faster for an agent to read and understand them. Use our…”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   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

   Poly~partialprobed5/10

   Poly's agent can perform multi-step file tasks, spawn subagents, and be invoked via CLI/MCP/plugins, but these are triggered interactively (chat requests, CLI commands, agent sessions) rather than described as scheduled or event-triggered background automations running autonomously without a user prompt. There's no documented scheduler, trigger system, or 'run this automatically every day/on file change' capability. missing for 10: explicit scheduling/trigger mechanism (cron-like, event-driven, or always-on background execution), evidence of automations persisting and running unattended over time, and independent confirmation of autonomous background operation.

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress. Moreover, agents/subagents can communicate with each ot…”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   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

   Poly✓fullprobed8/10

   Poly ships a built-in agent that can search, read, write, edit, and organize files across multiple steps (poly-docs-14, poly-docs-27, poly-docs-31), and can even spawn subagents to delegate subtasks (poly-docs-21, poly-docs-35), directly matching the story of delegating tasks to an in-product AI assistant. This is corroborated by runtime probes confirming a live agent/MCP infrastructure (poly-probe-rt-1, poly-probe-rt-2). Missing for 10: independent hands-on user reports specifically validating the agent's task execution (community commentary focuses on search/security concerns rather than confirming agentic task delegation in practice).

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress. Moreover, agents/subagents can communicate with each ot…”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   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

   Poly✓fullprobed8/10

   Poly's docs describe a built-in agent operable via natural language — searching, summarizing, editing, and organizing files with plain-language requests (poly-docs-2, poly-docs-31, poly-docs-14, poly-docs-27), plus a CLI and MCP-based integrations exposing the same commands to AI assistants. This directly matches the ai-native natural-language-command story. Missing for 10: independent/hands-on verification that NL commands work reliably in practice (community evidence only discusses trust/security concerns, not functional testing of NL command execution).

   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”

   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

   Poly—none0/10

   The probe explicitly found no OpenAPI/Swagger spec at any candidate path, and the evidence pack contains no mention of an interactive API reference or runnable examples anywhere in Poly's docs or CLI/MCP materials.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Poly—none0/10

   A direct probe for OpenAPI/Swagger specs at all standard paths returned 404s, and no evidence pack item mentions a downloadable API spec; Poly instead documents an MCP server and CLI, not a machine-readable REST API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”

   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

   Poly—none0/10

   Poly's docs describe direct agent read/write access to a user's real files, Drive/Dropbox imports, and MCP integrations, but nowhere mention a sandbox, staging, or test environment isolated from production data. Community comments even highlight anxiety about the agent having broad access to real files with no isolation layer. missing for 10: any documented sandbox/staging mode, test data set, or isolated environment separate from the user's live files.

   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [community] “Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   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

   Poly—none0/10

   No evidence of any versioned public API or documented deprecation policy — probes for OpenAPI/Swagger specs all returned 404, and docs only cover CLI/MCP/agent integrations, not API versioning or deprecation guarantees. missing for 10: versioned API reference, deprecation policy documentation, changelog/versioning scheme.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”

   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 Poly
   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

   Poly✓fullprobed9/10

   Poly ships a documented hosted MCP server (mcp.poly.app) with OAuth, exposing search, fetch, and CLI-equivalent tools, plus a CLI/agent-skill that lets agents read, write, create, and organize files headlessly, and a Claude Code plugin that loads Poly memory and connects the MCP server automatically — all confirmed live via runtime probes. missing for 10: independent (non-vendor) hands-on confirmation that write operations via MCP work reliably in practice, beyond docs and probes.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “The [`poly-cli` agent skill] teaches an agent how to search, read, create, update, and organize your Poly files by composing `poly` commands…”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   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 Poly
   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

   Poly✓fullprobed9/10

   Poly ships a first-party MCP server (mcp.poly.app) with OAuth, documented and runtime-verified as live, plus official plugins/integrations for Claude, ChatGPT, Claude Code, VS Code, and a CLI usable by agents, giving AI-native users multiple first-party ways to connect external LLMs to their notes/files. missing for 10: no independent hands-on confirmation of the plugin ecosystem working smoothly beyond docs/probe, and community feedback raises unresolved trust/security concerns rather than functional failures.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [claimed-docs] “Give Claude Code persistent context and full access to your Poly files.”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   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 Poly
   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

   Poly~partialcommunity5/10

   Poly's built-in agent clearly summarizes, explains, drafts, and edits notes grounded in the user's own files (poly-docs-31, poly-docs-14, poly-docs-27, poly-docs-3), and Mind/journaling gives a personal-notes corpus for it to draw on (poly-docs-12, poly-docs-26, poly-docs-32). However, evidence for granular controls over *what the assistant itself sees* is thin: docs describe the agent getting 'full access to your Poly files' (poly-docs-30) rather than scoped visibility, and the only access controls documented are sharing/revoke permissions for other people (poly-docs-9, poly-docs-33), not data-scoping for the AI itself — a gap community users flag as a trust concern (poly-comm-2, poly-comm-4). Missing for 10: explicit per-folder/file visibility toggles or exclusion settings for the assistant, and independent confirmation that such controls work as intended.

   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Give Claude Code persistent context and full access to your Poly files.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [community] “Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   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

   Poly~partialclaimed5/10

   Poly's CLI is described as 'scriptable from the terminal' (poly-docs-17) and the agent can chain multi-step tasks like 'organizing a folder' or spawning subagents to handle work in parallel (poly-docs-14, poly-docs-21, poly-docs-31, poly-docs-35), which implies some automation across sets of files, but there is no explicit documentation of a true bulk/batch operation (e.g., 'rename/tag/move N files at once') or a dedicated batch API/command. Missing for 10: an explicit bulk-operation example or batch command, evidence of scale (many items processed in one call), and independent/hands-on confirmation that automation reliably spans large item sets.

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress. Moreover, agents/subagents can communicate with each ot…”

   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

   Poly—none0/10

   Poly's docs describe on-demand agent actions (search, summarize, edit, organize) and multi-step task execution, but there is no evidence of a rules/trigger system that fires actions automatically on defined events (e.g., file-added, schedule, webhook-based automation). Automation is user-initiated per request, not event-driven.

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”

   proof ↗⚑ 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

   Poly—none0/10

   Poly's docs describe agent-driven task automation (multi-step tasks, subagents, organizing folders) but there is no mention of recurring/scheduled execution, cron-like triggers, or workflow scheduling anywhere in the evidence pack.

   ⚑ flag

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

   weight 1 · round to Poly
   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

   Poly~partialclaimed4/10

   Poly documents file-level version history and rollback (flashback mode, conflict-preserving recovery) that would cover changes made by its agent when it edits files, but there is no evidence of a first-class 'automation' object (e.g., saved workflows/skills) that can be versioned, reviewed, or rolled back as a unit — only raw file state is versioned. missing for 10: dedicated automation/workflow versioning UI, diff/review of agent actions before execution, rollback of multi-step agent tasks (not just files) as an atomic unit.

   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “Go into flashback mode at any time to see exactly what your files looked like at any point in the past, down to the millisecond.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”

   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

   Poly—none0/10

   Poly's docs describe importing from Drive/Dropbox/iCloud/local files and from note apps like Notion/Obsidian/Evernote, but there is no mention of a browser extension, web clipper, or capture flow for saving web pages/articles/highlights directly into Poly. This is a fair capability for a 'second brain' note tool, so absence of evidence means it is not delivered.

   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”

   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

   Poly~partialclaimed3/10

   Poly Mind's journaling feature provides a manual 'quiet place' to write daily thoughts and syncs entries as Markdown files, which loosely matches the capture/journaling theme, but there's no evidence of automatic daily note creation, template pre-fill, or it being the default landing screen. missing for 10: automatic daily note generation, template pre-fill mechanism, evidence of default-landing behavior on app open.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ flag

Editor

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

   weight 2 · round drawn
   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

   Poly—none0/10

   Poly's Mind/journaling docs describe creating markdown journal entries and importing notes, but there is no evidence of a reusable template system with variables (date, title) for recurring note types.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   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 Poly
   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

   Poly~partialclaimed3/10

   Poly supports Markdown-based journaling (auto-synced .md files in the Mind folder) and offers Vim keybindings for file editing, suggesting some keyboard-driven text editing capability, but there is no documentation of rich formatting elements like callouts, tables, code blocks, or embedded media in a dedicated note editor. Missing for 10: explicit support for headings/callouts/tables/code blocks, embedded media, and any description of a fast dedicated editor UI beyond basic Markdown journaling.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Vim keybindings (enable in Settings)”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ 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 Poly
   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

   Poly~partialclaimed4/10

   Poly stores files as real files that sync to a local Finder/Explorer folder (poly-docs-23) and journal entries are plain Markdown (poly-docs-12), implying your data always exists in accessible, mostly-original formats rather than a locked proprietary export. However, there is no explicit 'export my knowledge base' feature, bulk-export tool, or open-format guarantee for the indexed metadata/second-brain layer — only import pathways (poly-docs-1, poly-docs-22) are documented. Missing for 10: an explicit export/backup command or API, confirmation that indexed metadata (tags, memory, search index) can be exported, and any open-format guarantee beyond raw file sync.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   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

   Poly~partialclaimed5/10

   Poly's docs explicitly state you can 'bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more,' directly covering two of the four named sources, and general file import (Google Drive/Dropbox/local) plus native Markdown journal files supports plain Markdown ingestion. However, Roam is never explicitly named, and there is no documented detail on how structure, internal links, or attachments are preserved during the import process, nor any hands-on/community confirmation of import fidelity. Missing for 10: explicit Roam support, documented handling of internal links/structure/attachments during migration, independent corroboration of import fidelity.

   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”

   proof ↗⚑ flag

Graph

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

   weight 1 · round to Logseq
   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

   Poly—none0/10

   Poly's docs describe a 'second brain' with search, journaling, tagging, multiple folder views (Icon, Grid, Feed, Detail, Tree, etc.), and Notion/Obsidian import, but nowhere mention a graph visualization of notes/connections or filtering such a graph — this is a plausible axis for a notes/second-brain product but no evidence supports it.

   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “Eight ways to look at a folder — Icon, Grid, Feed, Detail, Tree, C”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”

   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

   Poly—none0/10

   Poly's 'Mind' feature supports journaling, importing notes from other PKM tools, and semantic search, but nothing in the evidence pack mentions [[wiki-style]] linking, backlink panels, or unlinked-mention detection — core PKM/wiki-linking features. Since Poly Mind explicitly targets note-taking/second-brain use cases, this axis is a fair question for the product, but no evidence shows it delivers wiki-links or backlinks.

   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ flag

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

   weight 2 · round to Logseq
   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

   Poly—none0/10

   Poly's docs describe file search, an agent, a CLI/MCP integration, and a Markdown-based Mind/journal folder, but nothing in the evidence describes block- or section-level transclusion between notes that stays synced (no backlinks, embeds, or live-sync block references are mentioned anywhere in the docs pack).

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   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

   Poly!disputedcontradicted4/10

   Docs describe files/journal entries as real local files (synced Finder folder, Markdown notes in a 'Mind' folder), suggesting some local-first storage, but the core search/indexing/agent stack is cloud-hosted (remote MCP server at mcp.poly.app, OAuth-gated, server-side parsing/transcribing/indexing) — and a hands-on community reviewer explicitly notes 'your service, by nature, is reading and analyzing all of my files using a remote server,' directly contradicting a fully offline, locally-owned workflow. Missing for 10: no documentation of an offline mode, no evidence local files remain fully functional/searchable without the cloud service, and no rebuttal to the community's remote-dependency observation.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “It automatically parses, transcribes, and indexes your files that make it up to 20x faster for an agent to read and understand them.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”
   • [community] “It feels like an LLM wrapper in search of a problem. Cloud search plus already exists... I do not find the idea of bringing my data to your …”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   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 Poly
   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

   Poly~partialclaimed5/10

   Poly's Mind journal entries are explicitly stored as plain Markdown files synced to a folder (poly-docs-12), and the desktop client exposes all Poly files as a real Finder/Explorer folder that syncs back automatically (poly-docs-23), so notes aren't locked in a proprietary blob. However there is no documented bulk-export feature, no JSON export format, and no explicit statement about long-term archival or vendor-independence beyond this folder-sync mechanism; import from other note apps (poly-docs-22) is one-way and does not evidence export-out portability. Missing for 10: explicit JSON/structured export option, a documented full-archive export or backup mechanism, and any statement guaranteeing data portability/format stability if the vendor shuts down.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   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

   Poly—none0/10

   All evidence points to Poly being a cloud-backed service (hosted MCP server at mcp.poly.app requiring OAuth login to Poly's cloud, cloud-based indexing/search) with no documented local-only mode or self-hosted sync backend option; community comments even complain that files/data must go through Poly's remote servers rather than staying local.

   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”
   • [community] “It feels like an LLM wrapper in search of a problem. Cloud search plus already exists... I do not find the idea of bringing my data to your …”

   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

   Poly—none0/10

   Evidence pack extensively documents desktop, CLI, web/MCP, and Finder/Explorer integration, but contains no mention whatsoever of iOS or Android apps, mobile capture, or mobile search/linking capability. missing for 10: any evidence of iOS app, Android app, or mobile-specific capture/search/linking features.

   ⚑ flag

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

   weight 2 · round to Poly
   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

   Poly~partialprobed5/10

   Poly ships a scriptable CLI (25+ commands) and a hosted MCP server exposing search, fetch, and a virtual `poly` CLI as tools, giving programmatic access to core file search/read/write/organize workflows that mirror the UI's agent capabilities (poly-docs-17, poly-probe-rt-2, poly-probe-4). However there is no documented REST/OpenAPI API (openapi probes all 404'd), and no evidence that UI-only features like sharing/permissions management, the eight folder views, flashback/version history, or journaling are exposed programmatically. Missing for 10: a general-purpose REST/OpenAPI surface, API parity for sharing/permissions, version history, and Mind/journaling features.

   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The [`poly-cli` agent skill] teaches an agent how to search, read, create, update, and organize your Poly files by composing `poly` commands…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Go into flashback mode at any time to see exactly what your files looked like at any point in the past, down to the millisecond.”

   proof ↗⚑ flag

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

   weight 3 · round to Logseq
   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

   Poly~partialclaimed4/10

   Poly's desktop sync exposes files as a real folder in Finder/Explorer with files kept in their original formats and synced back automatically (poly-docs-23), and journal entries are stored as plain Markdown files (poly-docs-12), which implies some natural portability rather than lock-in. However, there is no explicit documentation of a bulk 'export all data' feature, data-export API, or guarantee that a user can fully extract their indexed memory/context in open formats and leave — missing for 10: an explicit export/data-portability feature, documentation of exporting the 'second brain'/index data, and any mention of account deletion/data takeout.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”

   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

   Poly—none0/10

   No evidence of any open-source license or public source repository for Poly; it appears to be a closed, proprietary SaaS/desktop product with only documentation and API/MCP endpoints disclosed. Missing for 10: any open-source license file, public code repository, or statement of source availability.

   ⚑ 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

   Poly—none0/10

   All evidence describes Poly as a hosted SaaS (cloud sync, hosted MCP endpoint at mcp.poly.app requiring OAuth, subscription-based) with no mention of a self-hosted or on-prem deployment option anywhere in the docs or probes.

   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [community] “This is really cool! I suck at organizing my filesystem and I've lost track of how many times I had to find that ONE PDF which I KNOW I have…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

Metadata

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

   weight 2 · round to Logseq
   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

   Poly~partialclaimed4/10

   Poly documents tag support that syncs bidirectionally with Finder tags and colors, and search/retrieval features (natural language, visual similarity), but there is no evidence of 'typed properties' (structured metadata fields/schemas) or of consistent, structured tag-based retrieval workflows beyond basic color/tag sync. missing for 10: typed/structured property fields, evidence of consistent tag-based filtering or retrieval UI, cross-file property schemas.

   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [claimed-docs] “Eight ways to look at a folder — Icon, Grid, Feed, Detail, Tree, C”
   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”

   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 Logseq
   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

   Poly—none0/10

   Poly's docs describe file search, tagging, journaling, and multiple folder 'views' (Icon, Grid, Feed, Detail, Tree, etc.) but there is no evidence of structured/custom properties on notes nor of live query-driven database views like tables or boards built from property filters — the 'eight ways to look at a folder' are display modes, not queryable schema-based views.

   • [claimed-docs] “Eight ways to look at a folder — Icon, Grid, Feed, Detail, Tree, C”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”

   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 Poly
   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

   Poly~partialclaimed4/10

   Poly documents natural-language full-text search (down to timestamp/page/paragraph), a CLI 'poly search' command, visual similarity search, and Finder-tag syncing, but nowhere combines these into documented filter syntax on tags/properties/paths, nor claims search works offline (files instead 'download on demand' and sync back, implying online-first indexing). missing for 10: explicit support for combined tag/property/path filters in search queries, explicit documentation of offline full-text search capability.

   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “Visual similarity — find images that look like a reference image you provide”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”

   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

   Poly~partialprobed6/10

   Poly ships a scriptable `poly` CLI (poly-docs-6, poly-docs-17, poly-probe-4) and a local/hosted MCP endpoint (poly-docs-29, poly-probe-rt-2) that let external scripts search, read, and create/edit files including Mind journal notes, satisfying the 'local endpoint for workflows' part of the story. However there is no documented URI scheme or OS-level deep-link mechanism for opening/creating notes, only CLI/MCP paths. Missing for 10: URI scheme/deep-link support, explicit CLI subcommand for creating a note by title/URI, independent confirmation of CLI scripting reliability.

   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   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

   Poly—none0/10

   Evidence shows Poly ships its own integrations (CLI, MCP server, plugins for Claude/ChatGPT/VS Code) that let Poly connect into other tools, but there is no mention of a marketplace or catalog of third-party/community-built plugins that extend Poly itself with new features.

   • [claimed-docs] “Use our plugin with leading agents like Claude, ChatGPT, and VS Code and make your file workflows insanely fast.”
   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”

   proof ↗⚑ 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

   Poly—none0/10

   Evidence shows Poly ships an MCP server, a CLI, and an agent-skill file for its own CLI, but nothing documents a first-party extension API/SDK for developers to build their own Poly plugins — the 'plugin' references are about installing Poly's plugin into other agents (Claude, ChatGPT, VS Code), not the reverse. A direct probe for an OpenAPI/Swagger spec returned 404 on all candidate paths, and no developer SDK, plugin manifest format, or extension samples are mentioned anywhere in the docs pack.

   • [claimed-docs] “Use our plugin with leading agents like Claude, ChatGPT, and VS Code and make your file workflows insanely fast.”
   • [claimed-docs] “It automatically parses, transcribes, and indexes your files that make it up to 20x faster for an agent to read and understand them. Use our…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”

   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

   Poly—none0/10

   No evidence in the pack addresses data residency, region selection, or storage location choice for Poly's cloud-hosted service; documentation focuses on features, sync, and MCP/CLI integrations without any regional/residency controls. Missing for 10: any mention of data center regions, residency options, or compliance-driven storage location settings.

   ⚑ flag

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

   weight 3 · round to Logseq
   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

   Poly—none0/10

   No evidence in the pack of any data-training opt-out, privacy policy, or model-training exclusion commitment from Poly; docs focus on file search/agent features, not data-usage privacy controls. Community comments raise general trust/security concerns but don't confirm or deny a training-opt-out policy, so this is an unaddressed gap rather than a dispute.

   ⚑ 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

   Poly—none0/10

   The evidence pack covers file import, search, sharing, versioning, and MCP/CLI integrations, but contains no documentation on data retention policies, permanent deletion, or export/purge controls for an AI-native privacy-conscious user. Community comments raise general trust/security concerns but don't confirm or deny specific retention/deletion mechanisms. missing for 10: retention policy docs, account/file deletion controls, data export or purge guarantees, any first-party statement on how long data is kept or how to fully erase it.

   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Poly—none0/10

   No evidence in the pack addresses telemetry, analytics, or usage-tracking opt-out settings for Poly; the docs and community discussion cover file syncing, search, MCP integrations, and general privacy/security concerns about filesystem access, not telemetry controls.

   ⚑ 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

   Poly—none0/10

   Poly's evidence covers sharing individual files/folders via links or team drives (poly-docs-9, poly-docs-24, poly-docs-33) and journaling/Mind notes storage, but there is no mention of publishing a collection of notes as a browsable, interlinked website (digital garden) with working cross-links. Sharing appears to be file/folder link-based, not a rendered site with navigable note-to-note links.

   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Share individual files with a link, or give a team its own storage space.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   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 Poly
   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

   Poly~partialclaimed5/10

   Poly supports sharing files/folders and creating team Shared Drives with members and roles, and it preserves conflicting edits so any version can be recovered, which addresses collaborative access and non-destructive conflict handling. However, this is file-versioning-based (conflicts are preserved as separate recoverable versions, not merged live), with no evidence of real-time co-editing, presence awareness, or seamless merge like a true multiplayer notes app. Missing for 10: real-time simultaneous editing support, live presence/cursor indicators, and conflict-free merge (vs. version preservation) for concurrent note edits.

   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [claimed-docs] “Create a Shared Drive when the content belongs to a team rather than to a person. A Shared Drive is its own storage space with its own membe…”
   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “Share individual files with a link, or give a team its own storage space.”

   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

   Poly—none0/10

   Poly's docs describe file sync (desktop folder sync, Finder tag sync, sharing, MCP/CLI integrations) but nowhere claim end-to-end encryption that the vendor itself cannot read; in fact the architecture explicitly routes files through Poly's servers for indexing/search, and community comments explicitly worry that Poly's remote servers read and analyze all files, contradicting the premise of vendor-blind E2EE. No evidence of an E2EE sync mechanism exists in the pack.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [community] “Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   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

   Poly✓fullclaimed7/10

   Poly's docs explicitly describe file-level version history and recovery: 'flashback mode' lets you see exactly what files looked like at any past point, and edits/conflicts are preserved so 'you can recover any version of any file at any time' (poly-docs-5, poly-docs-10). Since notes (journal entries, Mind files) are just files synced in Poly, this recovery/versioning applies to them too. Missing for 10: no independent/hands-on verification of the restore UX specifically for notes, and no explicit mention of undeleting a note versus just reverting content.

   • [claimed-docs] “Go into flashback mode at any time to see exactly what your files looked like at any point in the past, down to the millisecond.”
   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”

   proof ↗⚑ flag