Obsidian vs Poly

Agent access

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

   weight 2 · round to Poly
   Obsidian—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✓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
   Obsidian!disputedcontradicted4/10

   Vendor docs claim an Obsidian Sync 'headless client' explicitly designed for CI pipelines and automated agent workflows, but the independent runtime probe found Obsidian ships no official CLI or vendor automation interface, with only community-built (unofficial) tooling for programmatic access — directly contradicting the headless-CI claim. Missing for 10: independent confirmation the headless Sync client actually exists and works, official CLI documentation, and evidence of real CI usage.

   • [claimed-docs] “Obsidian Sync offers a headless client to sync vaults without using the desktop app. Useful for CI pipelines, agents, and automated workflow…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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 to Obsidian
   Obsidian~partialprobed3/10

   Obsidian has no first-party MCP client/server integration; the only evidence is a runtime probe noting that MCP support exists solely via unofficial community plugins, with no vendor-documented feature. missing for 10: official MCP client documentation, first-party plugin support, hands-on evidence of using MCP tools inside Obsidian.

   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   Obsidian is a note-taking platform (not itself an agent), so an official MCP server is a fair ecosystem question, but the evidence explicitly states Obsidian ships no official CLI or vendor MCP server, with MCP integrations existing only as community projects.

   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   Evidence explicitly confirms Obsidian ships no official CLI (the probe notes only community MCP servers exist, and no CLI is mentioned anywhere in docs). Missing for 10: any official CLI tool, documentation of CLI commands, or first-party automation interface for AI-native/agentic workflows.

   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   proof ↗⚑ 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
   Obsidian~partialprobed6/10

   Obsidian exposes a documented TypeScript Plugin API (obsidian-api on GitHub, e.g. the Vault interface) and a custom URI protocol for triggering actions like opening/creating notes, giving programmatic control over the app. However this requires building/compiling a plugin rather than calling a simple REST/HTTP API, and the probe explicitly notes Obsidian ships no official CLI or vendor MCP server, with MCP integrations being community-built. Missing for 10: a first-party REST/HTTP or MCP API surface for external agent control, and evidence of AI-native workflows actually driving Obsidian via the documented API.

   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [github] “`Vault`, the interface that lets you interact with files and folders in the vault.”
   • [claimed-docs] “Build plugins to extend the existing functionality in Obsidian using TypeScript.”
   • [claimed-docs] “Plugins let you extend Obsidian with your own features to create a custom note-taking experience.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   No evidence of scoped/least-privilege API credential issuance for agents; Obsidian has no official API/credential system, and community plugins run with full filesystem/network access rather than restricted permissions (obsidian-comm-10). No mention of any credentialing or permission-scoping mechanism anywhere in the docs.

   • [community] “Confirmed via Obsidian's own docs: there is no sandboxing at all for community plugins - every plugin has full access to your computer's fil…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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 Obsidian
   Obsidian~partialprobed6/10

   Obsidian ships an official, documented Plugin API/SDK (TypeScript) with a public GitHub repo (obsidian-api) and developer docs for building plugins, themes, and extensions, giving AI-native developers a real, first-party surface to build against. However, there is no official MCP server or AI-specific SDK/CLI (confirmed absent in the probe), plugins run with full filesystem/network access without sandboxing (community-verified), and Restricted Mode blocks third-party code by default — meaning agentic integration relies on community-built connectors rather than an official agent-facing SDK. Missing for 10: an official MCP server or AI/agent SDK, an official CLI, and evidence of first-party sandboxing suitable for autonomous agent code.

   • [claimed-docs] “In this tutorial, you'll compile a sample plugin from source code and load it into Obsidian.”
   • [claimed-docs] “Build plugins to extend the existing functionality in Obsidian using TypeScript.”
   • [claimed-docs] “you'll compile a sample plugin from source code and load it into Obsidian.”
   • [claimed-docs] “Plugins let you extend Obsidian with your own features to create a custom note-taking experience.”
   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [github] “`Vault`, the interface that lets you interact with files and folders in the vault.”
   • [claimed-docs] “By default, Obsidian runs in Restricted Mode to prevent third-party code execution.”
   • [community] “Confirmed via Obsidian's own docs: there is no sandboxing at all for community plugins - every plugin has full access to your computer's fil…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   No evidence in the pack of Obsidian offering webhooks or an event-subscription API; the plugin system exposes in-app events (e.g., Vault interface) but nothing about outbound webhook subscriptions, and the probe explicitly notes no official MCP/CLI or webhook-style integration exists, only community projects.

   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   proof ↗⚑ 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
   Obsidian—none0/10

   Obsidian's core product has no first-party AI-generated insights or suggestions feature; the only AI capability comes from third-party community plugins (e.g., Text-Generator), and community evidence explicitly notes 'no decent RAG functionality among Obsidian AI plugins,' indicating this is not a native, reliable capability of the product itself.

   • [community] “There's no decent RAG functionality among Obsidian AI plugins, but the Text-Generator plugin with links/backlinks pulled into inference cont…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   The evidence pack shows Obsidian's plugin architecture, URI protocol for triggering actions, and a large community-plugin ecosystem, but nothing demonstrates autonomous background automation (e.g., scheduled/triggered agent-like workflows running without user interaction). The probe explicitly notes no official CLI or vendor MCP server, and Restricted Mode by default blocks third-party code execution unless manually enabled, further undercutting any 'runs autonomously in background' claim.

   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [claimed-docs] “By default, Obsidian runs in Restricted Mode to prevent third-party code execution.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   There is no evidence of a built-in AI assistant in Obsidian; all AI-related capability mentioned (e.g., Text-Generator plugin) is explicitly a third-party community plugin, not a native feature, and the probe confirms no official vendor MCP server or AI tooling. Community plugins requiring full filesystem access (obsidian-comm-10) are the only AI-adjacent route, but that's an ecosystem extension, not a delegated built-in assistant.

   • [community] “There's no decent RAG functionality among Obsidian AI plugins, but the Text-Generator plugin with links/backlinks pulled into inference cont…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”
   • [community] “Confirmed via Obsidian's own docs: there is no sandboxing at all for community plugins - every plugin has full access to your computer's fil…”

   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
   Obsidian—none0/10

   Obsidian's own docs describe a traditional Command Palette, keyboard shortcuts, and a plugin API, but there is no first-party natural-language command interface; the probe explicitly notes Obsidian ships no official CLI or vendor MCP server, with any LLM/NL functionality (e.g. Text-Generator plugin) coming from community plugins rather than the product itself.

   • [claimed-docs] “Tabs, Command Palette, plugins,”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”
   • [community] “There's no decent RAG functionality among Obsidian AI plugins, but the Text-Generator plugin with links/backlinks pulled into inference cont…”

   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
   Obsidian—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

   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
   Obsidian—none0/10

   Obsidian has a plugin API and developer docs (TypeScript API reference), but no evidence of a downloadable machine-readable spec like OpenAPI/Swagger for any REST or programmatic interface; the probe explicitly notes no official CLI or vendor MCP server, and no OpenAPI spec is mentioned anywhere in the evidence pack.

   • [claimed-docs] “Build plugins to extend the existing functionality in Obsidian using TypeScript.”
   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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 to Obsidian
   Obsidian!disputedcontradicted3/10

   Obsidian's docs claim a 'Restricted Mode' that prevents third-party code execution (obsidian-docs-27), which could be read as a sandbox safeguard, but hands-on community evidence directly contradicts this: 'there is no sandboxing at all for community plugins - every plugin has full access to your computer's filesystem and can make network requests' (obsidian-comm-10), and a third party built a separate sandboxed app specifically because Obsidian plugins run with full system access on sensitive data (obsidian-comm-11). There is no documented feature for spinning up an isolated test vault/sandbox distinct from a production vault for AI-agent testing. Missing for 10: an official sandbox/test-vault feature, evidence of isolated execution for agent actions, and resolution of the restricted-mode vs. no-sandboxing contradiction.

   • [claimed-docs] “By default, Obsidian runs in Restricted Mode to prevent third-party code execution.”
   • [community] “Confirmed via Obsidian's own docs: there is no sandboxing at all for community plugins - every plugin has full access to your computer's fil…”
   • [community] “A company wrote a sandboxed alternative app because community plugins are too risky running with full system access when working on sensitiv…”

   proof ↗⚑ 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
   Obsidian—none0/10

   Evidence covers Obsidian's plugin API, developer docs, and file formats, but there is no mention of a versioning scheme or documented deprecation policy for the Obsidian API. The developer docs describe building plugins but do not address API version guarantees or backward-compatibility commitments. Missing for 10: any documentation of API versioning, semver policy, or deprecation timelines/announcements.

   ⚑ 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
   Obsidian~partialprobed4/10

   Obsidian stores notes as plain local Markdown files (obsidian-docs-20, obsidian-docs-23), which lets an agent read/write vault contents directly on disk without touching the GUI — but this is not a documented API or protocol, just an emergent property of the file format. The probe explicitly confirms Obsidian ships no official CLI or vendor MCP server, with MCP servers being community-only projects (obsidian-probe-rt-1), and the only documented headless integration (Obsidian URI, obsidian-docs-8) is for triggering GUI actions, not structured read/write. Missing for 10: an official vendor-documented local API or MCP server, first-party support for programmatic note read/write, and evidence of hands-on agent integration.

   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian~partialprobed5/10

   Obsidian has no first-party AI/LLM connector or vendor MCP server (confirmed by probe: 'no official CLI or vendor MCP server... MCP servers for Obsidian are community projects'), but its large community plugin ecosystem (7,275 plugins) does include AI tools like the Text-Generator plugin, cited by users as a productive LLM interface. This satisfies the 'ecosystem of AI plugins' half of the story but not the 'first-party connectors' half. Missing for 10: official first-party AI/LLM integration or vendor-maintained MCP server, broader documentation of AI plugin capabilities (e.g., RAG), and evidence these plugins are robust (community notes 'no decent RAG functionality among Obsidian AI plugins').

   • [community] “There's no decent RAG functionality among Obsidian AI plugins, but the Text-Generator plugin with links/backlinks pulled into inference cont…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”
   • [claimed-docs] “Use plugins to adapt Obsidian to fit your specific needs, such as support for additional file formats or integrating with a third-party serv…”
   • [claimed-docs] “Learn how to extend Obsidian with plugins built by the community.”

   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
   Obsidian—none0/10

   Obsidian's core product ships no built-in AI assistant; the only AI-related evidence describes third-party community plugins, and one commenter explicitly states 'there's no decent RAG functionality among Obsidian AI plugins,' undermining any grounded-in-notes assistant claim. There is no first-party documentation of an official AI feature with data-access controls.

   • [community] “There's no decent RAG functionality among Obsidian AI plugins, but the Text-Generator plugin with links/backlinks pulled into inference cont…”

   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
   Obsidian—none0/10

   The evidence pack shows Obsidian's file-based storage, plugin/API extensibility (Vault interface, community plugins), and Bases for database-like views, but nothing documents a bulk-operation capability (e.g., batch rename, bulk tag/metadata edit, multi-note transform) that an AI-native user could invoke across many items at once. The generic plugin API and 7,275-plugin ecosystem are extensibility building blocks, not evidence of a delivered bulk-operations feature.

   • [claimed-docs] “Bases is a core plugin that lets you create database-like views of your notes.”
   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [github] “`Vault`, the interface that lets you interact with files and folders in the vault.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   Obsidian's evidence shows a plugin API, a URI protocol for triggering actions, and a large community plugin ecosystem, but there is no documented built-in rule engine or automation system that fires actions automatically on events (e.g., note-created, tag-added triggers). Obsidian URI (obsidian-docs-8) requires an external caller, not an internal event-trigger rule system, and no plugin or first-party feature is cited that implements conditional automation.

   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [claimed-docs] “Use plugins to adapt Obsidian to fit your specific needs, such as support for additional file formats or integrating with a third-party serv…”
   • [claimed-docs] “Plugins let you extend Obsidian with your own features to create a custom note-taking experience.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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
   Obsidian—none0/10

   No evidence describes any Obsidian feature for scheduling recurring jobs or workflows; core plugins (daily notes, templates, bases) and the URI protocol are for triggering/creating notes, not for time-based recurring automation. The plugin ecosystem is large but no specific scheduling/automation plugin or native scheduler is documented.

   • [claimed-docs] “Daily notes is a core plugin that opens a note based on today's date, or creates it if it doesn't exist.”
   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [claimed-docs] “Use plugins to adapt Obsidian to fit your specific needs, such as support for additional file formats or integrating with a third-party serv…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   proof ↗⚑ 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
   Obsidian—none0/10

   Obsidian offers file version history for notes (obsidian-docs-28) and third-party Git sync for backups (obsidian-comm-8), but there is no evidence of any built-in mechanism to version, review, or roll back 'automations' (e.g., plugin configs, Templater/QuickAdd scripts, or workflow definitions) — Obsidian has no native automation/workflow builder at all, only community plugins that could theoretically be automation-like but aren't documented with any versioning/rollback tooling. Missing for 10: any documented automation-specific versioning system, review/diff tooling for automation changes, or rollback mechanism tied to plugin/script configurations.

   • [claimed-docs] “Version history - View or restore previous versions of a note.”
   • [community] “The Git plugin is great for single-device backup but not great for device sync or collaboration; a real-time collaboration plugin using CRDT…”

   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 Obsidian
   Obsidian✓fullclaimed9/10

   Obsidian ships an official free browser extension, the Web Clipper, explicitly documented to let users highlight pages and save web content directly into their vault, covering pages, articles, and highlights as described in the story. missing for 10: independent hands-on user reports specifically confirming the Web Clipper's reliability/quality beyond the vendor docs.

   • [claimed-docs] “Obsidian Web Clipper is a free browser extension that lets you highlight pages and save web content to your vault.”

   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 Obsidian
   Obsidian✓fullcommunity8/10

   Obsidian's core Daily Notes plugin opens/creates a note for today's date and can be paired with the Templates core plugin to pre-fill content, directly matching the story [obsidian-docs-4][obsidian-docs-5]. Community evidence corroborates daily notes as a common power-user workflow (mixed freely with folders/Zettelkasten) [obsidian-comm-4][obsidian-comm-17]. Missing for 10: explicit first-party documentation confirming daily note as the literal 'default landing/startup' page, and independent confirmation of template auto-fill reliability at scale.

   • [claimed-docs] “Daily notes is a core plugin that opens a note based on today's date, or creates it if it doesn't exist.”
   • [claimed-docs] “Templates is a core plugin that lets you insert pre-defined snippets of text into your active note.”
   • [community] “As an outliner, Logseq is too opinionated about usage; Obsidian is less strict, allowing mixing Zettelkasten, daily notes, and folder struct…”
   • [community] “Used Obsidian for organizing and running tabletop RPG sessions with folders of monsters, encounters, and world notes; also good enough to re…”

   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 to Obsidian
   Obsidian✓fullclaimed8/10

   Obsidian ships a first-party Templates core plugin for inserting reusable text snippets, and a Daily notes core plugin that creates date-based notes automatically, together covering variable-driven, recurring note templates (date/title insertion is a documented core feature of these plugins). Missing for 10: no explicit doc snippet showing custom variable syntax beyond date/title, and no independent hands-on report confirming template variable behavior in practice.

   • [claimed-docs] “Templates is a core plugin that lets you insert pre-defined snippets of text into your active note.”
   • [claimed-docs] “Daily notes is a core plugin that opens a note based on today's date, or creates it if it doesn't exist.”

   proof ↗⚑ 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 Obsidian
   Obsidian~partialclaimed5/10

   Evidence confirms Obsidian is a plain-text Markdown editor with linking, templates, mobile editing toolbar, and command palette (keyboard-driven), supporting the general shape of the story, but the pack never explicitly documents callouts, tables, code-block rendering, or embedded media handling. Missing for 10: explicit documentation/citations on callout syntax, table support, code block rendering, and media embedding, plus any performance/speed benchmarking of the editor.

   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “By linking notes, you can create a network of knowledge.”
   • [claimed-docs] “Templates is a core plugin that lets you insert pre-defined snippets of text into your active note.”
   • [claimed-docs] “Mobile toolbar is a customization toolbar for editing notes.”
   • [claimed-docs] “Tabs, Command Palette, plugins,”

   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 Obsidian
   Obsidian✓fullcommunity9/10

   Obsidian stores all notes as local, non-proprietary plain-text Markdown files (not a proprietary database or cloud lock-in), so a user's entire vault is always exportable/portable by simply copying the folder, and this is explicitly marketed as a future-proofing/anti-lock-in feature ('apps come and go, but your data should last'). Community testimonials corroborate this in practice (users migrated to/from Roam, Notion, Google Docs citing plain-text ownership as the reason switching was easy). Missing for 10: no independent hands-on verification of a bulk 'export' action for non-Markdown assets (attachments, plugin data) or edge cases in migration fidelity.

   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [community] “Moved from Google Docs to Obsidian for de-Googling; notes stored only locally and via storage sync, files are just text so notes can outlive…”
   • [community] “Migrated from Roam to Obsidian and it's really awesome - ownership of files, constant updates with new features and bug fixes, and a really …”

   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 Obsidian
   Obsidian✓fullcommunity8/10

   Obsidian ships dedicated first-party importers for Notion, Evernote, Roam-style Markdown, and Airtable/OneNote (obsidian-docs-1, 24, 29, 30), converting content to durable local Markdown files with links/attachments/structure preserved, and Notion databases even convert to Bases. Community evidence (obsidian-comm-20) confirms a real-world Roam→Obsidian migration went well. Missing for 10: no independent hands-on verification of attachment/link fidelity across all four sources (Notion, Evernote, Roam, plain Markdown) in one report, and no detail on edge-case fidelity issues during import.

   • [claimed-docs] “Obsidian lets you easily migrate your data from Notion using the Importer plugin.”
   • [claimed-docs] “Obsidian lets you easily migrate your data from Notion using the Importer plugin. This converts your Notion workspace to durable Markdown fi…”
   • [claimed-docs] “Notion account (recommended) connects directly to your workspace and lets you preserve Databases and formulas which are converted to Bases.”
   • [claimed-docs] “Import from Notion|Notion - Import from Airtable|Airtable - Import from Microsoft OneNote|Microsoft OneNote - Import from Evernote|Evernote”
   • [community] “Migrated from Roam to Obsidian and it's really awesome - ownership of files, constant updates with new features and bug fixes, and a really …”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”

   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 Obsidian
   Obsidian✓fullcommunity8/10

   Graph view is a documented core plugin that visualizes note relationships built from internal links, and Obsidian's linking system explicitly creates a 'network of knowledge' that the graph renders; Graph view also supports filters (though filtering specifics aren't detailed in this pack). Community evidence confirms users actively rely on the linking/graph model for organizing knowledge (e.g., RPG notes, dev notes). Missing for 10: no evidence of advanced graph filtering UI details (tags/colors/query filters) or independent hands-on praise/critique specifically of graph view's filtering usability.

   • [claimed-docs] “Graph view is a core plugin that lets you visualize the relationships between the notes in your vault.”
   • [claimed-docs] “By linking notes, you can create a network of knowledge.”
   • [community] “Used Obsidian for organizing and running tabletop RPG sessions with folders of monsters, encounters, and world notes; also good enough to re…”

   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 Obsidian
   Obsidian✓fullcommunity8/10

   Obsidian's core feature set is wiki-style [[linking]] and a network of knowledge (obsidian-docs-18), backed by Graph view for visualizing note relationships (obsidian-docs-3), and this is corroborated by independent community usage reports praising Obsidian's linking/organization model (obsidian-comm-17, obsidian-comm-20). Missing for 10: explicit documentation snippet describing the 'unlinked mentions' panel/backlinks pane in context (only inferred from linking/graph docs, not directly quoted) and no independent hands-on confirmation of backlink-in-context UI specifically.

   • [claimed-docs] “By linking notes, you can create a network of knowledge.”
   • [claimed-docs] “Graph view is a core plugin that lets you visualize the relationships between the notes in your vault.”
   • [community] “Used Obsidian for organizing and running tabletop RPG sessions with folders of monsters, encounters, and world notes; also good enough to re…”
   • [community] “Migrated from Roam to Obsidian and it's really awesome - ownership of files, constant updates with new features and bug fixes, and a really …”

   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 drawn
   Obsidian—none0/10

   The evidence pack only shows generic internal linking ('By linking notes, you can create a network of knowledge' — obsidian-docs-18) and graph view for whole-note relationships, but contains no documentation or community evidence of block/section-level embedding (transclusion) syntax or behavior. Missing for 10: any docs on block references (^blockid), section embeds, or confirmation that embedded content stays live-synced with the source note.

   • [claimed-docs] “By linking notes, you can create a network of knowledge.”

   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 Obsidian
   Obsidian✓fullcommunity9/10

   Obsidian's core design stores notes as plain-text Markdown files locally in a user-owned vault, explicitly marketed for offline use and future-proofing/app independence, corroborated by independent community reports of migrating away from cloud apps because files are local text that outlive the app. Minor caveat is Canvas's JSON format (still local, but less human-readable than Markdown), and mobile has a save-timing quirk under sync; missing for 10: independent long-term audit of full offline reliability across all core plugins and confirmation Canvas/Bases data remain equally portable as plain Markdown.

   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [community] “Moved from Google Docs to Obsidian for de-Googling; notes stored only locally and via storage sync, files are just text so notes can outlive…”
   • [community] “Obsidian Canvas uses a new JSON-based file format, open-sourced under MIT license; canvas files remain local and still link to your own futu…”
   • [community] “The Obsidian Android app does not save files to storage until the note unloads, which can break things if you sync/pull mid-edit, sometimes …”

   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 Obsidian
   Obsidian✓fullcommunity9/10

   Obsidian core storage is plain-text Markdown files on local disk with no proprietary lock-in, explicitly marketed as future-proof so notes 'outlive the app,' and this is corroborated by independent user reports of migrating away and still having usable text files. missing for 10: independent long-term archival/format-stability audit and clarity on the newer Canvas JSON format's durability (community notes flag it as less readable than Markdown, a minor caveat).

   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [community] “Moved from Google Docs to Obsidian for de-Googling; notes stored only locally and via storage sync, files are just text so notes can outlive…”
   • [community] “Obsidian is less opinionated on the file format and folders, making it more future-proof than Logseq, though Logseq's sync is too asynchrono…”
   • [community] “Obsidian Canvas uses a new JSON-based file format, open-sourced under MIT license; canvas files remain local and still link to your own futu…”
   • [community] “This looks like Obsidian's first move away from markdown - the .canvas JSON files are readable but not as readable as markdown; hope this is…”

   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 Obsidian
   Obsidian~partialcommunity7/10

   Obsidian is fundamentally local-first: notes are plain Markdown files stored on-device, fully usable offline with no vendor cloud dependency (obsidian-docs-2, obsidian-docs-20, obsidian-docs-23), and users can sync via Dropbox, iCloud, OneDrive, or Git instead of Obsidian's paid Sync service (obsidian-docs-19), confirmed by a community user who runs it fully local plus storage sync (obsidian-comm-19). However, self-hosting a sync backend is imperfect in practice — community reports note the Git plugin works for single-device backup but is 'not great for device sync or collaboration,' requiring third-party CRDT plugins to fill the gap (obsidian-comm-8). Missing for 10: an officially documented/first-party self-hosted sync backend with real-time multi-device guarantees (vs. community workarounds), and confirmation that Git/cloud-drive sync avoids conflict issues.

   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [claimed-docs] “Obsidian syncs with Obsidian Sync, Dropbox, iCloud, OneDrive, Git, and many other third-party services.”
   • [community] “Moved from Google Docs to Obsidian for de-Googling; notes stored only locally and via storage sync, files are just text so notes can outlive…”
   • [community] “The Git plugin is great for single-device backup but not great for device sync or collaboration; a real-time collaboration plugin using CRDT…”

   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 to Obsidian
   Obsidian~partialcommunity6/10

   Docs confirm the mobile app supports tabs, command palette, and full plugin support (docs-34) plus a customizable editing toolar (docs-14/25), indicating feature parity with desktop rather than a stripped companion, and the same Markdown vault format underlies both platforms enabling linking (docs-18, docs-20). However, community evidence surfaces a concrete reliability issue specific to the Android app (files not saved to storage until note unloads, causing lost content on sync) and general dissatisfaction with mobile UX/Electron design relative to native apps, undercutting a fully polished power-user experience. Missing for 10: explicit documentation of mobile search functionality, mobile graph view parity, and independent confirmation the Android save bug has been resolved.

   • [claimed-docs] “Tabs, Command Palette, plugins,”
   • [claimed-docs] “Mobile toolbar is a customization toolbar for editing notes.”
   • [claimed-docs] “Mobile toolbar is a customization toolbar for editing notes. When editing a note, you will notice a row of icons at the bottom of the app.”
   • [claimed-docs] “By linking notes, you can create a network of knowledge.”
   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [community] “The Obsidian Android app does not save files to storage until the note unloads, which can break things if you sync/pull mid-edit, sometimes …”
   • [community] “I dislike the aesthetics and wouldn't use Obsidian because of Electron; spoiled by native note apps like Bear and Noteplan on macOS with nic…”

   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
   Obsidian~partialprobed4/10

   Obsidian exposes some programmatic surfaces — the Obsidian URI protocol for triggering actions like opening/creating notes, and a plugin API (Vault interface) for reading/writing files — but these fall short of full UI parity. There is no official CLI or vendor-provided REST/MCP API; the probe explicitly confirms no official CLI or MCP server exists, with third-party community plugins filling that gap instead. missing for 10: comprehensive first-party API/CLI covering all UI actions, official REST or MCP server, evidence of parity for non-file operations (e.g., graph view, canvas, settings) via API.

   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [github] “`Vault`, the interface that lets you interact with files and folders in the vault.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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 Obsidian
   Obsidian✓fullcommunity9/10

   Obsidian stores all data as local plain-text Markdown files with no proprietary lock-in, explicitly marketed as future-proof so users 'can use Obsidian offline and switch to another app easily,' and this is corroborated by independent community accounts of notes outliving the app and easy migration away. Even newer formats like Canvas are open JSON under MIT license, reinforcing the open-export/leave-anytime story. Missing for 10: no independent audit of full fidelity export for all plugin-generated data (e.g., Bases, Sync metadata) beyond core notes.

   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [community] “Moved from Google Docs to Obsidian for de-Googling; notes stored only locally and via storage sync, files are just text so notes can outlive…”
   • [community] “Obsidian Canvas uses a new JSON-based file format, open-sourced under MIT license; canvas files remain local and still link to your own futu…”

   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 drawn
   Obsidian—none0/10

   Obsidian is explicitly noted as closed-source (obsidian-comm-12), and no evidence pack item shows any open-license source availability; only the Canvas file format is MIT-licensed (obsidian-comm-14), not the app's source code itself.

   • [community] “Obsidian being closed-source makes it harder to verify their security model compared to note-taking systems where all plugin code is visible…”
   • [community] “Obsidian Canvas uses a new JSON-based file format, open-sourced under MIT license; canvas files remain local and still link to your own futu…”

   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 drawn
   Obsidian—none0/10

   Obsidian's core app is closed-source (obsidian-comm-12) and Sync/Publish are proprietary paid cloud services with no documented self-hosted server alternative; the only 'local' aspect is that vault files live on-device, which is not the same as self-hosting the product's infrastructure. No evidence of an official self-hostable sync/publish server or open-source core.

   • [community] “Obsidian being closed-source makes it harder to verify their security model compared to note-taking systems where all plugin code is visible…”
   • [claimed-docs] “Obsidian Sync encrypts your remote vault and all communication with Obsidian's servers.”
   • [claimed-docs] “Obsidian Publish is a cloud-based hosting service that lets you publish your notes as a wiki, knowledge base, documentation, or digital gard…”
   • [claimed-docs] “Obsidian Sync is an add-on service that allows you to privately sync your notes across devices.”

   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 Obsidian
   Obsidian~partialcommunity5/10

   Obsidian's Bases core plugin (database-like views of notes) and internal linking support the kind of structured organization/retrieval a power-user would want, and community evidence confirms Bases is used as a fast, if less comprehensive, alternative to Dataview for querying notes by metadata. However, the evidence pack never explicitly documents Obsidian's Properties (YAML frontmatter with typed fields) or tag system, nor how tags/properties are used consistently for retrieval. Missing for 10: explicit docs on typed Properties/frontmatter, dedicated tag-pane/tag-search documentation, and hands-on confirmation that typed properties work reliably for retrieval across a vault.

   • [claimed-docs] “Bases is a core plugin that lets you create database-like views of your notes.”
   • [community] “Bases is essentially a 90% replacement for the Dataview plugin, much faster and more responsive, though not yet as comprehensive.”
   • [claimed-docs] “By linking notes, you can create a network of knowledge.”

   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 Obsidian
   Obsidian~partialcommunity7/10

   Obsidian's core 'Bases' plugin is documented as letting users 'create database-like views of your notes' from structured properties, and community evidence corroborates it as a real, working feature comparable to the popular Dataview plugin, confirming table/board-style query views exist. However, community feedback notes Bases is 'not yet as comprehensive' as Dataview and lacks its imperative dataviewjs scripting for custom dynamic rendering, so some advanced query/view flexibility power-users expect is limited. Missing for 10: detailed first-party documentation of specific view types (table/board/list) and their query syntax, plus independent confirmation these views match the full breadth of 'live database' functionality claimed.

   • [claimed-docs] “Bases is a core plugin that lets you create database-like views of your notes.”
   • [community] “Bases is essentially a 90% replacement for the Dataview plugin, much faster and more responsive, though not yet as comprehensive.”
   • [community] “Dataview's dataviewjs mode lets you write custom imperative JavaScript to dynamically render content in notes, a capability Bases (queries-t…”

   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 drawn
   Obsidian~partialclaimed4/10

   Evidence confirms offline-first, local plain-text storage (docs-2, docs-20, docs-23) and Bases as a database-like filtering view on note properties (docs-6), plus tag-based linking (docs-18), which together imply some filterable retrieval. However, the pack contains no explicit documentation of Obsidian's full-text search engine, search operators for tags/paths, or performance claims about instant search across large vaults. Missing for 10: dedicated full-text search docs, tag/path/property query syntax evidence, independent hands-on confirmation of search speed/completeness.

   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [claimed-docs] “Bases is a core plugin that lets you create database-like views of your notes.”
   • [claimed-docs] “By linking notes, you can create a network of knowledge.”
   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”

   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 drawn
   Obsidian~partialprobed6/10

   Obsidian documents a native URI protocol for triggering actions like opening or creating notes, which directly supports scripting/automation via deep links (obsidian-docs-8). However, there is no first-party local HTTP endpoint or official CLI evidenced — the probe explicitly confirms Obsidian ships no official CLI or vendor MCP server, leaving any local-endpoint automation to third-party community plugins not covered in this pack. Missing for 10: vendor-documented local REST/HTTP endpoint, independent hands-on examples of URI-driven workflows in real automation pipelines.

   • [claimed-docs] “Obsidian URI is a custom URI protocol supported by Obsidian that lets you trigger various actions, such as opening a note or creating a note…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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 Obsidian
   Obsidian✓fullprobed9/10

   Obsidian's own docs describe a dedicated Community Plugins system for extending functionality (obsidian-docs-7, obsidian-docs-31, obsidian-docs-33), and a runtime probe confirms the vendor's official plugin registry lists 7,275 published community plugins, verifying the catalog's scale beyond marketing claims. Community discussion corroborates real-world reliance on specific popular plugins (Dataview, Git, Text-Generator) as everyday power-user tools, and docs also cover the security model (Restricted Mode) governing plugin installation. Missing for 10: independent step-by-step hands-on installation walkthrough/review of the browse-and-install UI flow itself.

   • [claimed-docs] “Use plugins to adapt Obsidian to fit your specific needs, such as support for additional file formats or integrating with a third-party serv…”
   • [claimed-docs] “Learn how to extend Obsidian with plugins built by the community.”
   • [claimed-docs] “Plugins let you extend Obsidian with your own features to create a custom note-taking experience.”
   • [claimed-docs] “By default, Obsidian runs in Restricted Mode to prevent third-party code execution.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”
   • [community] “Bases is essentially a 90% replacement for the Dataview plugin, much faster and more responsive, though not yet as comprehensive.”
   • [community] “The Git plugin is great for single-device backup but not great for device sync or collaboration; a real-time collaboration plugin using CRDT…”

   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 Obsidian
   Obsidian✓fullprobed8/10

   Obsidian has a dedicated developer docs site with a 'Build a plugin' tutorial that compiles a sample plugin from source, an official API repository (obsidian-api) documenting interfaces like Vault, and TypeScript-based plugin development guidance; the registry-verified 7,275 community plugins confirm the extension API is actively used at scale. missing for 10: independent hands-on review of doc quality/completeness, and no official CLI/scaffolding tool beyond the sample build tutorial.

   • [claimed-docs] “In this tutorial, you'll compile a sample plugin from source code and load it into Obsidian.”
   • [claimed-docs] “Build plugins to extend the existing functionality in Obsidian using TypeScript.”
   • [claimed-docs] “you'll compile a sample plugin from source code and load it into Obsidian.”
   • [claimed-docs] “Plugins let you extend Obsidian with your own features to create a custom note-taking experience.”
   • [github] “Vault, the interface that lets you interact with files and folders in the vault.”
   • [github] “`Vault`, the interface that lets you interact with files and folders in the vault.”
   • [probe] “PROBE runtime (recorded 2026-09-05): the vendor's own community-plugin registry (obsidianmd/obsidian-releases community-plugins.json) counte…”

   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 Obsidian
   Obsidian~partialclaimed5/10

   Obsidian's core value proposition is local-first storage — notes are plain-text Markdown files kept on the user's own device, giving inherent control over data location without relying on a vendor cloud (obsidian-docs-2, obsidian-docs-20, obsidian-docs-23). However, for users who opt into Obsidian Sync, there is no documented ability to choose a specific storage region/jurisdiction for the encrypted cloud vault. missing for 10: explicit region/residency selection for Obsidian Sync servers, any multi-region hosting options, independent confirmation of server locations.

   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [claimed-docs] “Obsidian Sync is an add-on service that allows you to privately sync your notes across devices.”
   • [claimed-docs] “Obsidian Sync encrypts your remote vault and all communication with Obsidian's servers.”

   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 Obsidian
   Obsidian~partialcommunity6/10

   Obsidian's core architecture (local plain-text Markdown storage, optional end-to-end encrypted Sync where 'no one — not even the Obsidian team — can access your notes') strongly implies user data isn't harvested for AI training since it never leaves the user's control by default. However, there is no explicit vendor statement or policy addressing AI-training use of data, and Obsidian's own docs admit community plugins have unrestricted filesystem/network access with no sandboxing, meaning third-party plugins (e.g. AI plugins) could still exfiltrate data outside Obsidian's control. Missing for 10: an explicit anti-AI-training data policy statement, and any assurance/controls over what community AI plugins do with vault data.

   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “End-to-end encryption (default) offers the strongest security... This guarantees that no one — not even the Obsidian team — can access your …”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [community] “Confirmed via Obsidian's own docs: there is no sandboxing at all for community plugins - every plugin has full access to your computer's fil…”
   • [community] “Obsidian being closed-source makes it harder to verify their security model compared to note-taking systems where all plugin code is visible…”

   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 Obsidian
   Obsidian~partialclaimed6/10

   Obsidian's local-first, plain-text vault model (obsidian-docs-20, obsidian-docs-23, obsidian-docs-2) gives users full control to delete or retain data simply by managing files on disk, and Sync is end-to-end encrypted with version history to restore/rollback (obsidian-docs-21, obsidian-docs-28). However there's no explicit documentation on server-side retention windows, deletion guarantees for Sync/Publish-hosted data, or export/purge tooling tailored to AI-native automation. Missing for 10: explicit Sync/Publish data-retention or deletion policy, documented data-export/erasure API, and any AI-specific retention controls.

   • [claimed-docs] “Obsidian stores your notes as Markdown-formatted plain text files in a vault.”
   • [claimed-docs] “Apps come and go, but your data should last. Obsidian uses non-proprietary plain text Markdown files stored locally on your device.”
   • [claimed-docs] “Obsidian uses non-proprietary plain text Markdown files stored locally on your device. You have total control over your data, which means yo…”
   • [claimed-docs] “End-to-end encryption (default) offers the strongest security... This guarantees that no one — not even the Obsidian team — can access your …”
   • [claimed-docs] “Version history - View or restore previous versions of a note.”

   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
   Obsidian—none0/10

   The evidence pack covers local-first storage and Sync encryption but contains no mention of telemetry, usage analytics, or an opt-out setting for such tracking. This is a fair question for any desktop app, so absence of evidence yields 'none' rather than 'na'.

   ⚑ 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 Obsidian
   Obsidian✓fullclaimed8/10

   Obsidian Publish lets users select notes from their vault and publish them as a hosted, browsable site (digital garden/wiki) at publish.obsidian.md/your-site, with working internal links preserved via Obsidian's native linking system, all configured from within the app. missing for 10: no independent hands-on account of the publish workflow or link-rendering fidelity, and Publish is a paid add-on rather than free/bundled.

   • [claimed-docs] “Obsidian Publish is a cloud-based hosting service that lets you publish your notes as a wiki, knowledge base, documentation, or digital gard…”
   • [claimed-docs] “Select the notes you want to share with the world, press Publish, and we'll host it at publish.obsidian.md/your-site”
   • [claimed-docs] “By linking notes, you can create a network of knowledge.”

   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
   Obsidian!disputedcontradicted4/10

   Vendor docs claim Obsidian Sync lets teams 'collaborate on a shared vault' and offers version history to restore prior versions, but this is file-sync-based rather than real-time conflict-free editing — community evidence explicitly notes that neither Sync-adjacent tools (e.g. Git plugin) are 'great for device sync or collaboration' and that a separate third-party CRDT-based plugin had to be built to achieve Google-Docs-style simultaneous editing without overwriting changes, implying native Sync doesn't guarantee non-destructive concurrent edits. missing for 10: evidence of built-in conflict-free simultaneous multi-user editing, first-party documentation on merge/conflict handling during concurrent edits, hands-on reports confirming no data loss when two collaborators edit the same note at once.

   • [claimed-docs] “With Obsidian Sync you can collaborate on a shared vault with your team.”
   • [claimed-docs] “Version history - View or restore previous versions of a note.”
   • [community] “The Git plugin is great for single-device backup but not great for device sync or collaboration; a real-time collaboration plugin using CRDT…”

   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 Obsidian
   Obsidian✓fullcommunity8/10

   Obsidian Sync is an official first-party add-on service documented to encrypt the remote vault and all communications, with end-to-end encryption as the default so 'no one — not even the Obsidian team — can access your notes,' directly matching the story. Missing for 10: independent third-party security audit or hands-on verification of the E2E claim, and one community report notes an Android sync edge case (files not saved until note unloads) that can cause missing content during sync, a minor reliability caveat.

   • [claimed-docs] “Obsidian Sync encrypts your remote vault and all communication with Obsidian's servers.”
   • [claimed-docs] “End-to-end encryption (default) offers the strongest security... This guarantees that no one — not even the Obsidian team — can access your …”
   • [claimed-docs] “Obsidian Sync is an add-on service that allows you to privately sync your notes across devices.”
   • [claimed-docs] “End-to-end encryption (default) offers the strongest security but requires you to safely store your encryption password.”
   • [community] “The Obsidian Android app does not save files to storage until the note unloads, which can break things if you sync/pull mid-edit, sometimes …”

   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
   Obsidian✓fullclaimed6/10

   Obsidian's own docs explicitly list 'Version history - View or restore previous versions of a note' as a feature of Obsidian Sync, directly matching the story's core ask for power-users who pay for Sync. Missing for 10: explicit documentation of deleted-note recovery workflow, and independent/hands-on corroboration beyond the single first-party doc line.

   • [claimed-docs] “Version history - View or restore previous versions of a note.”
   • [claimed-docs] “Obsidian Sync is an add-on service that allows you to privately sync your notes across devices.”

   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