“Next three consultant signups get monthly. Annual stays the enterprise default.”
The product, in motion
The interface is the evidence.
Minutes captures locally, writes one inspectable Markdown file, and lets your agents recall the decision with a source. No proprietary workspace stands between you and your own history.
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.
v0.26.0 keeps consistency reports in the meeting folder you selected and lets you try sample recall without downloading speech models. On Apple Silicon, automatic transcription can use Parakeet when its plugin and model are ready. Release notes · Feed
Download, install, done. First launch downloads a speech model. Runminutes setup --demoto try the pipeline on five bundled fixture meetings.
Newer Homebrew distrusts third-party taps by default; if brew warns about silverstein/tap, run brew trust silverstein/tap once.
Reading on your phone? Minutes installs on Mac and Windows. Star the repo so it is waiting when you are back at your desk.
Works with any MCP client
Claude Code/Codex/Gemini CLI/Claude Desktop/Cowork
01Dictation
The fastest way in is your voice.
Hold the hotkey, speak, release. The text lands at your cursor and in your daily note. Dictation uses the same local transcription pipeline as your meetings and memos.
Minutes saves your dictation locally so it can become part of the history your AI searches later. You choose which context to share with a connected assistant.
Dictation
daily-note.md · 2026-07-10
⌥Spacehold to talk
08:14Remind me to send the Q3 numbers to the board before Friday.
11:02Onboarding idea: defer the model download until the first recording.
15:47Dana owns the pricing experiment; review the results next week.
Transcribed on-device · appended locally · searchable by your AI later
02On-device
Local capture. You choose what to share.
Capture, transcription, and storage run locally. Your recordings become Markdown files on your own disk. If you choose a cloud AI assistant or summarizer, the meeting context you authorize is sent to that provider.
Cloud notetakers
Leaves your device- Capture from your micon-device
device audio, on your Mac
- Transcribe☁ cloud
cloud providers
- Enhance notes☁ cloud
hosted AI
- Store transcripts + notes☁ cloud
their servers
A hosted transcription workflow sends audio to a provider. Other tools also offer local processing; check the model and storage settings you select.
Minutes
Stays on device- Capture from your micon-device
device audio, on your Mac
- Transcribeon-device
on-device speech model
- Store transcripts + noteson-device
your disk; markdown in ~/meetings
Recording and transcription stay local. Use local AI or skip summarization to keep processing on-device. Cloud assistants receive the context you authorize; file sync and backups have their own settings.
03Proof
See it work before you believe it.
Try it in two minutes
One command installs five sample meetings and connects them to your AI. Ask Claude what was decided, without recording anything.
How we test it
3,009 automated test declarations and a public eval harness, with the limits stated plainly. Read the receipts before you trust it.
Build on the files
Working Mem0 and Graphiti examples show how other tools read the same markdown. Your data, everyone's integration.
04Pipeline
How it works
Audio -> Transcribe -> Diarize -> Summarize -> Markdown -> Policy-safe Search
(local) (local) (your LLM) (decisions, (live authorized,
speech model pyannote Claude / action items) bounded reads)
OllamaTranscription runs locally. The engine depends on your platform, build, and installed models. Summarization is optional; Claude can do it conversationally when you ask, using your existing subscription. No API keys are required to get useful output.
05Audience
Capture it anywhere. Find it everywhere.
From meetings to memos to agents
If your agent is the interface
Minutes is the capture layer of a memory you own
Wait for the call banner, record, and never open the app again. Claude Code, Cursor, Codex, or OpenCode call search_meetings over MCP, and the markdown folds into your own vault or wiki. The recap is optional; the agent is the reader.
If you read the results yourself
Minutes is a complete local notetaker
Transcript, speakers, summary, and action items in one inspectable file, with Recall to ask about the meeting afterwards. No account, no server, and no agent required.
For agents
Local audio context
34 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
On-device 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 keeps voice and system audio failure-isolated, reports source dropouts and mostly-zero stems, and preserves the WAV for recovery.
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 inserts the text where you are working, keeps a clipboard copy, and saves it to your daily note.
For recall
Answers from raw output
Minutes keeps timestamps, speakers, and action items visible so you can check an answer against the source.
06Features
What you get
Capture
>
Local transcription. Whisper or Parakeet, depending on your platform and installed models. 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.
>
Policy-bound people context. Build bounded policy-safe person profiles, topic research, relationship rankings, and commitments.
>
Cross-meeting search. Search policy-authorized history or ask your assistant to pull the thread for you.
>
Voice memo pipeline. iPhone recordings arrive on Mac and join the same policy-safe search corpus.
Integration
>
Desktop app. Tauri menu bar app with recording, dictation hotkey, and meeting prompts.
>
Claude-native. 34 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.
07Comparison
How it compares
| Granola | Otter.ai | Anarlog | minutes | |
|---|---|---|---|---|
| Product | Hosted meeting notepad | Hosted meeting assistant | Local meeting notepad | Local conversation memory |
| Agent access | Hosted MCP | Hosted integrations | CLI + MCP | Files + 34 MCP tools |
| Primary storage | Hosted workspace | Hosted workspace | Local SQLite + files | Local Markdown + YAML |
| Local AI | Cloud transcription | Cloud transcription | With local providers | Local transcription; AI provider of your choice |
08Governance
Built in, not retrofitted.
Client conversations need deliberate choices about recording, access, storage, and AI providers. Minutes keeps capture and transcription local and records consent metadata alongside the conversation. Local processing alone does not establish legal or regulatory compliance.
Shipped
Every recording stamps its consent basis into the file's frontmatter. Sensitive meetings capture no audio but keep structured notes, and Require mode blocks every desktop and CLI entry point until consent is confirmed.
Next
Retention rules the corpus enforces on its own audio, and enforcement of the sensitivity contract across every agent surface, not just the debrief path.
The point
Sensitivity metadata your agents are required to respect: a restricted meeting is excluded from default agent search, bounded profiles, and anything an agent assembles.
A disclosure aid, not legal advice; make sure everyone present has agreed where required. The design is public: why we built it this way and the phase 2 plan.
