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.
Runssource: GitHubhomepageRustMITcommit 83531fa5bfc5
Rust, MIT licensed. The project labels itself: agent skills, ai, claude, mcp, meeting notes, meetings, parakeet and privacy.
minutes runs. An Argusic agent installed it in 29 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
The minutes CLI v0.27.0 binary builds and runs: 59 commands available, demo generates 5 sample meetings with correct markdown frontmatter and YAML metadata, capabilities endpoint reports 50+ features, whisper-guard passes 14/14 tests, 1827/1864 minutes-core tests pass with 37 container-limited failures, 3/4 minutes-cli tests pass with 1 container-limited failure, and MCP npm tests fail on Node 18 vs 21+ import.meta.d...
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 85 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Missing system build dependencies: glib-2.0, libpipewire-0.3, libspa-0.2, alsa .pc files and headers for bindgen/libclang10 minutes
- 37 container-specific test failures in minutes-core: all use memfd_create or process-group operations (ENOSYS/os error 95) not available in this container
- 1 container-specific test failure in minutes-cli test (authorized_process_fd): same operation-not-supported error
- 12 MCP npm test failures: tests use import.meta.dirname (Node 21+) but container has Node 18
- Install time
- 29 minutes
- Cold machine to finish
- 30 minutes
- Errors hit and fixed
- 4 hit, 1 fixed with no human help
- How the result was proved
- cargo test -p whisper-guard passed 14/14; cargo test -p minutes-core --no-default-features --features whisper passed 1827/1864; cargo test -p minutes-cli --no-default-features --features whisper passed 3/4; minutes --version prints '0.27.0'; minutes demo --full creates 5 meeting files with correct YAML frontmatter; minutes list --limit 5 returns 5 meetings as JSON array with path/date/title; minutes capabilities lists 50+ features; minutes paths returns config_path, minutes_dir, output_dir
- Model tokens used
- 151,691
- Exact commit tested
- 83531fa5bfc5
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Y.T.**: Yeah that's not good. Can you fix it yourself? **Hiro Protagonist**: I can probably hack a workaround but the real fix needs Da5id's expertise on … **Y.T.**: Makes sense. Enzo's not going to be happy about the concert delay though. He was planning… **Hiro Protagonist**: That's his problem. From now on, anything Da5id commits to goes through me. I… **Y.T.**: Want me to track him down? I know some people at the Raft. **Hiro Protagonist**: Not yet. Let me try talking to him first. If he ghosts me then... yeah then m… **Y.T.**: Anytime. Let me know how it goes. Oh and heads up, I just signed an exclusive deal for th… **Hiro Protagonist**: Noted. I'll keep an ear out. All verification is complete. Here is the final report: tokens used 151,691 All verification is complete. Here is the final report:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 29 minutes to install, slower than the median of the 42 comparable projects Argusic has measured.
- Hit 4 errors during setup, 3 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 43 agent-skills projects Argusic has installed and timed, minutes was the 40th fastest to reach a running state, and 31 of 43 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsaiclaudemcpmeeting-notesmeetingsparakeetprivacyrustspeech-to-texttranscriptionvoice-memowhisper
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/minutes)Questions
- Does minutes run?
- Yes. minutes runs. Argusic installed and launched it on a clean machine in 29 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test minutes?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 83531fa5bfc5. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test minutes?
- The run that produced this verdict cost $0.37: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does minutes take to install?
- 29 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does minutes need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing minutes?
- 4 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does minutes compare with the alternatives?
- Of the 43 agent-skills projects Argusic has installed and timed, minutes was the 40th fastest to reach a running state, and 31 of 43 reached one at all.
- Where is the evidence for minutes?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.