Skip to content
Back to search

minutes

Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/silverstein/minutes with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/silverstein/minutes'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/silverstein--minutes/badge.svg)](/listings/silverstein--minutes)

HTML

<a href="/listings/silverstein--minutes"><img src="/api/listings/silverstein--minutes/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Choose the desktop app or one standalone CLI installation. The desktop app includes a CLI: use **About Minutes → Set up CLI** to add it to your PATH.

brew install --cask silverstein/tap/minutes  # Desktop app, with bundled CLI
brew install silverstein/tap/minutes         # Standalone CLI alternative
cargo install minutes-cli                   # Standalone CLI via Cargo

For an agent connection, add the MCP server separately with `claude mcp add minutes -- npx -y minutes-mcp` (or run `npx minutes-mcp` from another MCP client).

If Homebrew reports an untrusted tap, run `brew trust silverstein/tap` once.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 23 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "minutes",
  3. "owner": {
  4. "name": "Mat Silverstein",
  5. "email": "mat@businessvacation.com"
  6. },
  7. "plugins": [
  8. {
  9. "name": "minutes",
  10. "source": "./.claude/plugins/minutes",
  11. "description": "24 skills + 1 agent + 2 hooks for the full meeting lifecycle, including a governed Minutes to X1 closeout handoff",
  12. "version": "0.21.1",
  13. "author": {
  14. "name": "Mat Silverstein"
  15. },
  16. "homepage": "https://useminutes.app",
  17. "repository": "https://github.com/silverstein/minutes",
  18. "license": "MIT",
  19. "keywords": ["meeting", "transcription", "memory", "voice-memo", "whisper", "conversation", "ai-memory"],
  20. "category": "productivity"
  21. }
  22. ]
  23. }
README.md · README · 185 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # minutes
  2. [![GitHub stars](https://img.shields.io/github/stars/silverstein/minutes?style=social)](https://github.com/silverstein/minutes)
  3. [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
  4. [![crates.io](https://img.shields.io/crates/v/minutes-cli.svg)](https://crates.io/crates/minutes-cli)
  5. [![npm](https://img.shields.io/npm/v/minutes-mcp.svg)](https://www.npmjs.com/package/minutes-mcp)
  6. [useminutes.app](https://useminutes.app)
  7. Minutes is a free, open-source conversation memory app for the AI you already use. Record and transcribe meetings, calls, voice memos, and dictation on your device, then let Claude Code, Codex, Cursor, or another MCP client search the history you choose to share. Your records are Markdown files you own in `~/meetings/`.
  8. Capture, transcription, and storage run locally. If you choose a cloud AI assistant or summarizer, the meeting context you authorize is sent to that provider.
  9. **Your conversations. Your memory. Ready for the AI you use.**
  10. <p align="center">
  11. <img src="docs/assets/demo.gif" alt="minutes demo; record, dictate, phone sync, AI recall" width="750">
  12. </p>
  13. ## Install
  14. Choose the desktop app or one standalone CLI installation. The desktop app
  15. includes a CLI: use **About Minutes → Set up CLI** to add it to your PATH.
  16. **On Linux x86-64**, follow the [prebuilt CLI quickstart](docs/install.md#linux)
  17. for Ubuntu 24.04 or a compatible distribution. The same guide covers building
  18. from source on older distributions.
  19. ```bash
  20. brew install --cask silverstein/tap/minutes # Desktop app, with bundled CLI
  21. brew install silverstein/tap/minutes # Standalone CLI alternative
  22. cargo install minutes-cli # Standalone CLI via Cargo
  23. ```
  24. For an agent connection, we recommend Node.js 22. Add the MCP server with
  25. `claude mcp add minutes -- npx -y minutes-mcp` (or run `npx minutes-mcp`
  26. from another MCP client).
  27. If Homebrew reports an untrusted tap, run `brew trust silverstein/tap` once.
  28. ## Ask your agent
  29. Add Minutes to your agent, seed five sample meetings (no mic needed), then ask about them:
  30. ```bash
  31. claude mcp add minutes -- npx -y minutes-mcp
  32. minutes demo --full
  33. ```
  34. > What did Da5id promise about the rendering pipeline, and did he deliver?
  35. Da5id promised a fix by Friday in Metaverse Infrastructure Standup. In Intel
  36. Debrief, Hiro reported that the fix still hadn't landed.
  37. A direct MCP call uses the same local meeting files:
  38. ```text
  39. search_meetings({"query":"rendering pipeline"})
  40. ```
  41. Record a real one with `minutes record`, then `minutes stop` to transcribe. `minutes demo --clean` removes the samples.
  42. Setup: [Codex, Gemini CLI, and Claude Desktop](docs/integration/clients.md#any-mcp-client-claude-code-codex-opencode-gemini-cli-claude-desktop-or-your-own-agent),
  43. [Cursor](docs/integration/cursor-agent.md),
  44. [OpenCode](docs/integration/clients.md#opencode-cli),
  45. [Pi](docs/integration/pi-agent.md),
  46. [Mistral Vibe](docs/integration/clients.md#mistral-vibe), and
  47. [Cowork or Dispatch](docs/integration/clients.md#cowork--dispatch).
  48. ### Works with
  49. Claude Code · Codex · Cursor · OpenCode · Pi · Gemini CLI · Claude Desktop ·
  50. Mistral Vibe · Cowork · Dispatch · Obsidian · Logseq · any MCP client
  51. ## How it compares
  52. | Workflow | Granola | Otter.ai | Anarlog (formerly Hyprnote) | Minutes |
  53. |---|---|---|---|---|
  54. | Product | Hosted meeting notepad | Hosted meeting assistant | Local meeting notepad | Local conversation memory |
  55. | Agent access | Hosted MCP | Hosted integrations | CLI + MCP | Local files, MCP, CLI, SDK |
  56. | Primary storage | Hosted workspace | Hosted workspace | Local SQLite + files | Local Markdown + YAML |
  57. | Local AI | Cloud transcription | Cloud transcription | With local providers | Local transcription; AI provider of your choice |
  58. Reviewed September 5, 2026 against [Granola MCP](https://docs.granola.ai/help-center/sharing/integrations/mcp), [Otter privacy and security](https://otter.ai/privacy-security), and the [Anarlog repository](https://github.com/fastrepl/anarlog). Anarlog's community app is MIT; its enterprise components use a commercial license. See [the detailed comparison](https://useminutes.app/compare/hyprnote-vs-minutes) and [open-source alternatives](https://useminutes.app/resources/open-source-alternatives-to-granola-ai) for fit and limitations.
  59. ## Who it's for
  60. Agent-first users treat Minutes as the capture layer of a local second brain.
  61. They search meetings through Claude Code, Cursor, Codex, OpenCode, MCP, or the
  62. CLI, then fold useful context into a vault or wiki they own.
  63. Desktop notetaker users record and read results in the app. They value reliable
  64. setup, clear processing and recovery, Recall, documents, Coach, and summary
  65. quality. See the full [persona notes](docs/personas.md).
  66. ## Surfaces
  67. | Surface | What it provides | Docs |
  68. |---|---|---|
  69. | Desktop app | Menu bar capture, dictation, Recall, documents, and Coach. | [Install](docs/install.md#desktop-app) |
  70. | CLI (60 commands) | Local recording, processing, search, import, and automation. | [Commands](docs/features.md) |
  71. | MCP server (34 tools) | Local meeting tools and resources for any MCP client. | [MCP reference](docs/integration/agent-integrations.md) |
  72. | Claude Code plugin (23 skills) | Prep, capture, live help, debrief, and memory workflows. | [Client setup](docs/integration/clients.md#claude-code-plugin) |
  73. | SDK | TypeScript access to meeting files without MCP. | [Agent architecture](docs/architecture/README.md#building-your-own-agent-on-minutes) |
  74. ## Dictation
  75. The desktop Dictation settings bring writing preferences, personal spellings and snippets, microphone selection, and recent text together. Cursor context is optional and stays on the Mac. Recovery restores text for review; local edits use an explicit Ollama preview, and spelling corrections require confirmation.
  76. See [dictation behavior and evaluation boundaries](docs/design/dictation-experience.md) for supported fields, safe insertion and undo, clipboard restoration, and the synthetic benchmark.
  77. ## Voice Live
  78. Voice Live's optional local-agent handoff prepares bounded recent dialogue and
  79. already-shared evidence while you talk. The exact context is included in the
  80. existing local review before dispatch. It uses your configured agent CLI and
  81. authentication; context preparation needs no OpenAI API key or model request.
  82. See [voice delegation context](docs/architecture/voice-continuity-integration.md#voice-delegation-context)
  83. for disclosure, truncation, and verification boundaries.
  84. ## Output format
  85. Meetings are plain markdown with structured YAML frontmatter:
  86. ```yaml
  87. ---
  88. title: Q2 Pricing Discussion with Alex
  89. type: meeting
  90. date: 2026-03-17T14:00:00
  91. duration: 42m
  92. context: Discuss Q2 pricing
  93. action_items:
  94. - assignee: mat
  95. task: Send pricing doc
  96. due: Friday
  97. status: open
  98. decisions:
  99. - text: Test monthly billing with 10 advisors
  100. ---
  101. ```
  102. See the [frontmatter schema](docs/architecture/frontmatter-schema.md). Files work
  103. with [Obsidian](https://obsidian.md), grep, and any markdown tool.
  104. ## Privacy & consent
  105. - Transcription and speaker processing run on-device. Audio stays on your machine.
  106. - Sensitive meetings save typed markers without audio and default to restricted.
  107. - Consent reminders, acknowledgement, and provenance help you disclose recording.
  108. - Text leaves the machine only when you send authorized context to a cloud agent or summarizer.
  109. See the [security documentation](docs/security/) and
  110. [consent enforcement design](docs/architecture/consent-enforcement.md).
  111. ## Docs
  112. - [Features and commands](docs/features.md)
  113. - [Install, setup, updating, and troubleshooting](docs/install.md)
  114. - [Agent and MCP client integrations](docs/integration/clients.md)
  115. - [Phone voice memo pipeline](docs/phone-voice-memo-pipeline.md)
  116. - [Summarization and automation](docs/architecture/summarization.md)
  117. - [Configuration](docs/configuration.md)
  118. - [Architecture and agent development](docs/architecture/README.md)
  119. - [Evidence, retrieval, and decision-history contracts](docs/architecture/evidence-memory.md)
  120. - [Recall and speech evaluation](tests/eval/v02/README.md)
  121. - [Switching from Granola and importing archives](docs/switching-from-granola.md)
  122. - [Frontmatter schema](docs/architecture/frontmatter-schema.md)
  123. - [Security](docs/security/)
  124. - [Personas](docs/personas.md)
  125. - [Native call capture recovery](docs/native-capture-recovery.md) (`minutes recover-stem`)
  126. - [Opt-in automatic call recording](docs/call-auto-record.md) for Teams and Zoom desktop on macOS
  127. - [MCP tools](https://useminutes.app/docs/mcp/tools)
  128. - [Error reference](https://useminutes.app/docs/errors)
  129. - [Agent index](https://useminutes.app/llms.txt)
  130. - [Full agent index](https://useminutes.app/llms-full.txt)
  131. ## Contributing
  132. See [CONTRIBUTING.md](CONTRIBUTING.md). Minutes is MIT licensed and staying that way: no relicensing, no paid tier for anything in this repo.
  133. MIT. Built by [Mat Silverstein](https://github.com/silverstein), founder of
  134. [X1 Wealth](https://x1wealth.com).
  135. ## Star History
  136. [![Star History Chart](https://star-history.dera.page/svg?repos=silverstein/minutes&type=Date)](https://star-history.dera.page/#silverstein/minutes&Date)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.