Rank #3 of 6 in Notes & Knowledge Bases
Install
gemini extensions install https://github.com/withpoly/polymcp
vs Obsidian
vs Logseq
vs Anytype
vs Capacities
vs ReflectTry itExperimental
See what an agent can do with Poly before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -sL https://docs.poly.app/llms.txt | head -3recorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Ai in notes — stories about ai in notes in this arenaAi in notesevidence →
Stories about ai in notes in this arena
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Capture editing — stories about capture editing in this arenaCapture editingevidence →
Stories about capture editing in this arena
Import export — stories about import export in this arenaImport exportevidence →
Stories about import export in this arena
Linking graph — stories about linking graph in this arenaLinking graphevidence →
Stories about linking graph in this arena
Local first ownership — stories about local first ownership in this arenaLocal first ownershipevidence →
Stories about local first ownership in this arena
Mobile capture — stories about mobile capture in this arenaMobile captureevidence →
Stories about mobile capture in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Organization retrieval — stories about organization retrieval in this arenaOrganization retrievalevidence →
Stories about organization retrieval in this arena
Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibilityevidence →
Stories about plugins extensibility in this arena
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Publish sharing — stories about publish sharing in this arenaPublish sharingevidence →
Stories about publish sharing in this arena
Sync collaboration — stories about sync collaboration in this arenaSync collaborationevidence →
Stories about sync collaboration in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Poly stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
~7/10
unlocks → Webhooks · Official SDKs · Scoped API keys · Machine-readable spec · Versioning policy · API sandbox · Browse and install from a large catalog of community plugins/extensions to add features the core app doesn't ship · Build my own plugins against a documented extension API/SDK with samples and developer docs
Subscribe to events via webhooks
—–
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
—0/10
Connect an agent via an official MCP server
✓9/10
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
—0/10
Explore an interactive API reference with runnable examples
—0/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓9/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
✓8/10
unlocks → MCP client
Operate the product with natural-language commands
✓8/10
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
✓7/10
Set up automations that run autonomously in the background
~5/10
Ai in notes — stories about ai in notes in this arenaAi in notes
Stories about ai in notes in this arena
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Capture editing — stories about capture editing in this arenaCapture editing
Stories about capture editing in this arena
Import export — stories about import export in this arenaImport export
Stories about import export in this arena
Linking graph — stories about linking graph in this arenaLinking graph
Stories about linking graph in this arena
Local first ownership — stories about local first ownership in this arenaLocal first ownership
Stories about local first ownership in this arena
Mobile capture — stories about mobile capture in this arenaMobile capture
Stories about mobile capture in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Organization retrieval — stories about organization retrieval in this arenaOrganization retrieval
Stories about organization retrieval in this arena
Attach typed properties and tags to notes and use them consistently for organization and retrieval
~4/10
Query my notes by their structured properties and render live database-style views (tables, boards, lists) from those queries
—0/10
Instantly search all my notes with full-text search plus filters on tags, properties, and paths — including offline
~4/10
Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility
Stories about plugins extensibility in this arena
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Publish sharing — stories about publish sharing in this arenaPublish sharing
Stories about publish sharing in this arena
Sync collaboration — stories about sync collaboration in this arenaSync collaboration
Stories about sync collaboration in this arena
Sorted by importance (agentic first) (high → low) · 55/55 stories · click a row’s chevron for the rationale and evidence
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 9/10 | Tprobed⚿ | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Tprobed⚿ | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 7/10 | Tprobed⚿ | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ⚿ | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Tprobed⚿ | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 4/10 | Tprobed⚿ | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ⚿ | |
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | none | 0/10 | ||
My 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 C Agent ops | ai-native user | Ai in notes — stories about ai in notes in this arenaAi in notes | 3 | full | 9/10 | Tprobed⚿ | |
Import my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preserved C Migration | switcher | Import export — stories about import export in this arenaImport export | 3 | partial | 5/10 | Cclaimed | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partial | 4/10 | Cclaimed | |
Instantly search all my notes with full-text search plus filters on tags, properties, and paths — including offline C Search | researcher | Organization retrieval — stories about organization retrieval in this arenaOrganization retrieval | 3 | partial | 4/10 | Cclaimed | |
My 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 C Ownership | power-user | Local first ownership — stories about local first ownership in this arenaLocal first ownership | 3 | disputed | 4/10 | Dcontradicted⚿ | |
I get an automatic daily note for each day, pre-filled from a template, as the default landing place for journaling and capture C Daily notes | power-user | Capture editing — stories about capture editing in this arenaCapture editing | 3 | partial | 3/10 | Cclaimed | |
An official sync service keeps my notes updated across all my devices with end-to-end encryption the vendor can't read C Sync | power-user | Sync collaboration — stories about sync collaboration in this arenaSync collaboration | 3 | none | 0/10 | ⚿ | |
Browse and install from a large catalog of community plugins/extensions to add features the core app doesn't ship C Plugins | power-user | Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility | 3 | none | 0/10 | ||
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | none | 0/10 | ||
Link notes with [[wiki-style]] links and see every backlink and unlinked mention of a note in context C Links | researcher | Linking graph — stories about linking graph in this arenaLinking graph | 3 | none | 0/10 | ||
Query my notes by their structured properties and render live database-style views (tables, boards, lists) from those queries C Queries | power-user | Organization retrieval — stories about organization retrieval in this arenaOrganization retrieval | 3 | none | 0/10 | ||
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ⚿ | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Connect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI plugins C Ai assist | ai-native user | Ai in notes — stories about ai in notes in this arenaAi in notes | 2 | full | 9/10 | Tprobed⚿ | |
View a note's version history and restore earlier versions or recover deleted notes C Sync | power-user | Sync collaboration — stories about sync collaboration in this arenaSync collaboration | 2 | full | 7/10 | Cclaimed | |
Drive 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 C Automation hooks | developer | Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility | 2 | partial | 6/10 | Tprobed⚿ | |
A built-in AI assistant can answer questions, summarize, and draft grounded in my own notes — with clear controls over what data it sees C Ai assist | ai-native user | Ai in notes — stories about ai in notes in this arenaAi in notes | 2 | partial | 5/10 | Xcommunity | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed⚿ | |
My notes are stored or exportable in open, documented formats (Markdown, JSON) so my archive outlives the vendor C Ownership | researcher | Local first ownership — stories about local first ownership in this arenaLocal first ownership | 2 | partial | 5/10 | Cclaimed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 5/10 | Cclaimed | |
Share a vault or space with collaborators and edit notes together without stepping on each other's changes C Collaboration | researcher | Sync collaboration — stories about sync collaboration in this arenaSync collaboration | 2 | partial | 5/10 | Cclaimed | |
Attach typed properties and tags to notes and use them consistently for organization and retrieval C Metadata | power-user | Organization retrieval — stories about organization retrieval in this arenaOrganization retrieval | 2 | partial | 4/10 | Cclaimed | |
Export my entire knowledge base at any time in open formats, so leaving is as easy as arriving C Migration | switcher | Import export — stories about import export in this arenaImport export | 2 | partial | 4/10 | Cclaimed | |
Write and format notes with headings, callouts, tables, code blocks, and embedded media in a fast keyboard-driven editor C Editor | power-user | Capture editing — stories about capture editing in this arenaCapture editing | 2 | partial | 3/10 | Cclaimed | |
Build my own plugins against a documented extension API/SDK with samples and developer docs C Plugins | developer | Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility | 2 | none | 0/10 | ||
Clip web pages, articles, and highlights from my browser straight into my notes with an official clipper or capture flow C Capture | researcher | Capture editing — stories about capture editing in this arenaCapture editing | 2 | none | 0/10 | ||
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | 0/10 | ||
Define reusable templates (with variables like date and title) and apply them when creating recurring kinds of notes C Editor | power-user | Capture editing — stories about capture editing in this arenaCapture editing | 2 | none | 0/10 | ||
Publish selected notes as a browsable website — a digital garden with working links — without leaving the app C Publish | researcher | Publish sharing — stories about publish sharing in this arenaPublish sharing | 2 | none | 0/10 | ||
Reference or transclude an individual block or section of one note inside another and have it stay in sync C Links | power-user | Linking graph — stories about linking graph in this arenaLinking graph | 2 | none | 0/10 | ||
Run the whole system without the vendor's cloud — local-only mode or a self-hosted sync backend I operate myself C Self host | developer | Local first ownership — stories about local first ownership in this arenaLocal first ownership | 2 | none | 0/10 | ⚿ | |
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Full-featured iOS and Android apps give me my whole knowledge base — capture, search, and linking — not a stripped-down companion C Mobile | power-user | Mobile capture — stories about mobile capture in this arenaMobile capture | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 4/10 | Cclaimed | |
Explore my knowledge base as an interactive graph of notes and connections, filtered to what I care about C Graph | researcher | Linking graph — stories about linking graph in this arenaLinking graph | 1 | none | 0/10 |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 45 stories with headroom
What would move Poly’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
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.
Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events
nonemoves PA Scoreimpact 30
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).
Linking graph — stories about linking graph in this arenaLink notes with [[wiki-style]] links and see every backlink and unlinked mention of a note in context
nonemoves PA Scoreimpact 30
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.
Plugins extensibility — stories about plugins extensibility in this arenaBrowse and install from a large catalog of community plugins/extensions to add features the core app doesn't ship
nonemoves PA Scoreimpact 30
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.
Sync collaboration — stories about sync collaboration in this arenaAn official sync service keeps my notes updated across all my devices with end-to-end encryption the vendor can't read
nonemoves PA Scoreimpact 30
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.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
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.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
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.
Organization retrieval — stories about organization retrieval in this arenaQuery my notes by their structured properties and render live database-style views (tables, boards, lists) from those queries
nonemoves PA Scoreimpact 30
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.
Showing the top 8 of 45 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map7 surfaces · 27 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
Raw docs26 stories
- Run the product headlessly / in CI for automation
- Connect an agent via an official MCP server
- Use an official CLI
- Drive the product through a documented public API
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- My 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
- Connect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI plugins
- A built-in AI assistant can answer questions, summarize, and draft grounded in my own notes — with clear controls over what data it sees
- Perform bulk operations across many items at once
- Version, review, and roll back my automations
- I get an automatic daily note for each day, pre-filled from a template, as the default landing place for journaling and capture
- Write and format notes with headings, callouts, tables, code blocks, and embedded media in a fast keyboard-driven editor
- Export my entire knowledge base at any time in open formats, so leaving is as easy as arriving
- Import my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preserved
- My 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
- My notes are stored or exportable in open, documented formats (Markdown, JSON) so my archive outlives the vendor
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
- Attach typed properties and tags to notes and use them consistently for organization and retrieval
- Instantly search all my notes with full-text search plus filters on tags, properties, and paths — including offline
- Drive 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
- Share a vault or space with collaborators and edit notes together without stepping on each other's changes
- View a note's version history and restore earlier versions or recover deleted notes
llms.txt10 stories
- Point an agent at llms.txt or agent-oriented docs
- Use an official CLI
- Drive the product through a documented public API
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Connect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI plugins
- Export my entire knowledge base at any time in open formats, so leaving is as easy as arriving
- Import my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preserved
- Attach typed properties and tags to notes and use them consistently for organization and retrieval
docs.poly.app6 stories
- Get AI-generated insights and suggestions from my data inside the product
- Operate the product with natural-language commands
- A built-in AI assistant can answer questions, summarize, and draft grounded in my own notes — with clear controls over what data it sees
- My 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
- Attach typed properties and tags to notes and use them consistently for organization and retrieval
- Instantly search all my notes with full-text search plus filters on tags, properties, and paths — including offline
CLI docs4 stories
Integrations docs4 stories
- Connect an agent via an official MCP server
- Drive the product through a documented public API
- My 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
- Connect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI plugins
OpenAPI spec2 stories
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -sL https://docs.poly.app/llms.txt | head -3reproduced$ curl -sL https://docs.poly.app/llms.txt | head -3 # docs.poly.app > Poly documentation
$curl -si -X POST https://mcp.poly.app/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced$ curl -si -X POST https://mcp.poly.app/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>' HTTP/2 401 date: Mon, 14 Sep 2026 23:16:09 GMT content-type: text/plain; charset=utf-8 content-length: 26 www-authenticate: Bearer resource_metadata="https://mcp.poly.app/.well-known/oauth-protected-resource/mcp" vary: origin, access-control-request-method, access-control-request-headers access-control-allow-origin: * access-control-expose-headers: www-authenticate 4001: Access [redacted] missing
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
8 of 16 testable claims verified · 1 contradicted → integrity 38/100
27 distinct capability claims found in Poly’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
8
Verified
7
Unverified
1
Contradicted
11
Undersold
Verified (13)
“Automatically remembers key details across files, forming a 'second brain' of your data”
Get AI-generated insights and suggestions from my data inside the productfullproof ↗
“Official plugin works with Claude, ChatGPT, and VS Code for fast file workflows”
Connect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI pluginsfullproof ↗
“Automatic parsing, transcription, and indexing make files up to 20x faster for agents to read”
My 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 GUIfullproof ↗
“Official CLI lets you search and script against your files from the terminal”
“MCP lets compatible AI assistants connect to Poly via a hosted OAuth-secured MCP endpoint”
“Gives Claude Code persistent context and full access to your Poly files”
My 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 GUIfullproof ↗
“Agent can perform multi-step tasks (read, search, write, organize) in a single request”
Operate the product with natural-language commandsfullproof ↗
“Official plugin loads Poly memory at session start, teaches Claude to use Poly, and connects the MCP server”
Connect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI pluginsfullproof ↗
“poly-cli agent skill teaches agents to search, read, create, update, and organize files via poly commands”
My 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 GUIfullproof ↗
“Agents can spawn subagents, assign them tasks, track progress, and share learnings with each other”
Set up automations that run autonomously in the backgroundpartialproof ↗
“Poly agent can write and edit files directly in your storage”
My 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 GUIfullproof ↗
“Agent can summarize, explain, or edit files, and automate tasks like organizing a folder”
A built-in AI assistant can answer questions, summarize, and draft grounded in my own notes — with clear controls over what data it seespartialproof ↗
“Connect Poly to AI assistants and code editors first via local CLI, then via MCP integration”
Unverified (11)
“Import existing files from Google Drive, Dropbox, iCloud, or a local machine”
Import my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preservedpartialproof ↗
“Natural language search finds results down to the exact timestamp, page, paragraph, or frame”
Instantly search all my notes with full-text search plus filters on tags, properties, and paths — including offlinepartialproof ↗
“Flashback mode shows exactly what files looked like at any past point, down to the millisecond”
View a note's version history and restore earlier versions or recover deleted notesfullproof ↗
“Finder tags sync bidirectionally with Poly tags, including colors”
Attach typed properties and tags to notes and use them consistently for organization and retrievalpartialproof ↗
“Share files or folders with specific people or a link while retaining ownership and revoke access anytime”
Share a vault or space with collaborators and edit notes together without stepping on each other's changespartialproof ↗
“Conflicting edits are preserved so any version of any file can be recovered at any time”
View a note's version history and restore earlier versions or recover deleted notesfullproof ↗
“Journal entries are saved as Markdown files synced to a dedicated Mind folder”
I get an automatic daily note for each day, pre-filled from a template, as the default landing place for journaling and capturepartialproof ↗
“Vim keybindings can be enabled in settings for keyboard-driven editing”
Write and format notes with headings, callouts, tables, code blocks, and embedded media in a fast keyboard-driven editorpartialproof ↗
“Import existing notes and memory archives from Notion, Obsidian, Evernote, Bear, and more”
Import my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preservedpartialproof ↗
“Journaling lets you write thoughts, attach files, and add broader project context day-to-day”
I get an automatic daily note for each day, pre-filled from a template, as the default landing place for journaling and capturepartialproof ↗
“Create a Shared Drive as a team's own storage space with its own members, roles, and archive”
Share a vault or space with collaborators and edit notes together without stepping on each other's changespartialproof ↗
Contradicted (1)
“Poly files appear as a real folder in Finder/Explorer, downloading on demand and syncing back automatically”
My notes live in local files or a local-first store that I own and can read without the app, and everything keeps working fully offlinedisputedproof ↗
Undersold (11)
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Run the product headlessly / in CI for automationpartialproof ↗
Drive the product through a documented public APIpartialproof ↗
Delegate tasks to a built-in AI assistant inside the productfullproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Export my entire knowledge base at any time in open formats, so leaving is as easy as arrivingpartialproof ↗
My notes are stored or exportable in open, documented formats (Markdown, JSON) so my archive outlives the vendorpartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Export all of my data in open formats and leavepartialproof ↗
Drive 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 workflowspartialproof ↗
Claims outside our story set (2)
Real capability claims found in Poly’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Visual similarity search finds images that look like a reference image you provide”
source ↗“Folders can be viewed eight different ways (Icon, Grid, Feed, Detail, Tree, etc.)”
source ↗
Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents