Open-source. MCP-native.

v0.16.5 • 29 MCP tools • 50 CLI commands • 1039+ tests

Every meeting, memo, and voice note,
structured and searchable.

Cloud meeting tools rent your own conversations back to you. Minutes captures meetings and voice memos locally, writes them as structured markdown to your disk, and lets you and every AI you use read the same folder.

Get started View on GitHub See proof

Local, open source, free forever.

v0.16.5 fixes the stale processing-recovery loop: dismissed failed-capture notices now stay dismissed after restart, while retry still clears the dismissal marker for a fresh attempt. It also carries forward the active-recording status polling fix that keeps desktop calls from piling up while audio capture is running.

Transcript Output

2026-04-08-strategy-sync.md

2 speakers42 min3 actions

09:02matWe should switch consultants to monthly billing instead of annual.09:04danaTest it on the next three signups first and compare retention.09:11matMinutes, capture that as a pricing experiment and link it to Q2 planning.

Action Items

☐Test monthly billing with the next three consultant signups

☐Compare retention and payback against annual billing

☐Review experiment results in next week's pricing sync

Minutes keeps the raw transcript visible. The structure is the interface: timestamps, speakers, action items, and decisions stay readable even before an assistant touches them.

Mac (Apple Silicon)Windows

Download, install, done. First launch downloads a speech model. Runminutes setup --parakeetfor the multilingual Parakeet backend, orminutes setup --demoto try the pipeline on five bundled fixture meetings.

Works with any MCP client

Claude Code/Codex/Gemini CLI/Claude Desktop/Cowork

01Proof

Start with the evidence, not the pitch.

Runnable demo

One command installs a five-meeting fixture corpus and prints an MCP config pointed at it.

Honest eval

v0.1 is a public smoke test with a provisional 20/20 pre-grade, not benchmark evidence.

Adapter examples

Mem0 and Graphiti examples show the file contract; v2 hardening is tracked separately.

02Pipeline

How it works

Audio -> Transcribe -> Diarize -> Summarize -> Markdown -> Relationship Graph
       (local)      (local)    (your LLM)  (decisions,   (people, commitments,
      whisper.cpp   pyannote   Claude /     action items) topics, scores)
                                Ollama

Transcription is local via whisper.cpp or parakeet.cpp. Parakeet is multilingual by default with native VAD. Live transcription falls back cleanly through Apple Speech, Parakeet, and Whisper. Summarization is optional — Claude can do it conversationally when you ask, using your existing subscription. No API keys are required to get useful output.

03Audience

Capture it anywhere. Find it everywhere.

From meetings to memos to agents

For agents

Local audio context

29 MCP tools, live transcript reads, and structured markdown let Claude, Codex, Gemini CLI, and Cowork work from what was actually said.

For developers

Local and inspectable

whisper.cpp or parakeet.cpp transcription, diarized markdown, YAML frontmatter, and a plain-files workflow that still works with grep and git.

For meetings

Capture what matters

One-click recording, streaming transcription, speaker separation, decisions, and action items without shipping your audio to a SaaS vendor.

For voice memos

Phone to desktop

Minutes watches for iPhone Voice Memos, transcribes them on your Mac, and makes them available to the same memory layer.

For daily work

Dictation that stays useful

Hold the hotkey, speak, release. Minutes sends the text to the clipboard and your daily note without changing tools.

For recall

Answers from raw output

Competitors hide the transcript. Minutes keeps timestamps, speakers, and action items visible so the source stays readable.

04Features

What you get

Capture

Local transcription. whisper.cpp with GPU acceleration. Your audio stays on your machine.

Streaming results. Text appears as you speak, with partial updates every few seconds.

Speaker diarization. pyannote separates who said what in multi-person meetings.

Dictation mode. Clipboard + daily note flow for short-form thoughts and commands.

Intelligence

Structured extraction. Action items, decisions, and commitments become queryable markdown.

Relationship memory. Track people, projects, and unresolved commitments across meetings.

Cross-meeting search. Search everything or ask your assistant to pull the thread for you.

Voice memo pipeline. iPhone recordings arrive on Mac and join the same memory graph.

Integration

Desktop app. Tauri menu bar app with recording, dictation hotkey, and meeting prompts.

Claude-native. 29 MCP tools for Claude Desktop, Cowork, Dispatch, and Claude Code.

Any LLM. Use Ollama, OpenAI-compatible gateways, local servers, or skip summarization entirely.

Markdown is truth. YAML frontmatter, plain files, and a workflow that works outside Minutes.

05Comparison

How it compares

	Granola	Otter.ai	Meetily	minutes
Local transcription	—	—	Yes	Yes
Open source	—	—	Yes	MIT
Free	$18/mo	Freemium	Free	Free
Agent surface	Hosted MCP/API	Hosted integrations	Local app	Files + 29 MCP tools
Cross-meeting intelligence	—	—	—	Yes
Dictation mode	—	—	—	Yes
Voice memos	—	—	—	iPhone pipeline
People memory	—	—	—	Yes
Data ownership	Their servers	Their servers	Local	Local
Data format	Cloud DB	Cloud DB	Markdown	Markdown + YAML
Agent-agnostic	—	—	—	Yes

Every meeting, memo, and voice note,structured and searchable.