vexa

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

Runssource: GitHubhomepagePythonApache-2.0commit dba990b413bd

Python, Apache-2.0 licensed. The project labels itself: api, claude code, codex, google meet, mcp, mcp server, meeting assistant and meeting minutes.

vexa runs. An Argusic agent installed it in 8 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

11 Python service test suites and the JS terminal client test suite run successfully in a container with Node 22.13 and Python 3.12.3; the compose/Docker deployment path cannot execute without Docker engine being available.

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 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.08 (measured)
recorded runs
2
last tested
stars
2,989
forks
548
open issues
810
watchers
12
size
90 MB
created
last push

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.

Time lost to each failure while testing vexa, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Node.js v18 incompatible (needs >=22.13)2 minutes
  • pnpm not found and npm install -g lacked permission1 minute
  • pnpm corepack signature verification failed with Node 221 minute
  • Python setuptools build-backend mismatch in clients/slim/pyproject.toml1 minute
  • Python flat-layout package discovery error in clients/slim1 minute
  • pydantic-settings missing for core/agent tests0.5 minutes
Install time
8 minutes
Cold machine to finish
17 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
pytest --tb=no -q across 11 Python test suites: 24+67+1422+366+694+589+4+86+26+176+1 = 3458 passed, 3 failed; vitest run in clients/terminal: 58 test files, 462 passed (0 failed)
Model tokens used
171,849
Exact commit tested
dba990b413bd
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

    'notes': '11 Python test suites ran (3458 passed, 3 failed) + clients/terminal JS tests (58 tes…
    'verified_how': 'pytest --tb=no -q across 11 Python test suites: 24+67+1422+366+694+589+4+86+26…
    'final_state': '11 Python service test suites and the JS terminal client test suite run success…
}
print('JSON valid')
print(json.dumps(result))
\"" in /work/repo
 succeeded in 0ms:
JSON valid
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 8, "errors": [{"msg": "Nod…
tokens used
171,849

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.
  • Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 8 minutes to install, slower than the median of the 61 comparable projects Argusic has measured.

Of the 62 api projects Argusic has installed and timed, vexa was the 40th fastest to reach a running state, and 37 of 62 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.
  • A quick evaluation: it was running 8 minutes after the clone.

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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.26
Argusic Runner1/3Runs100.000.08

Topics (from GitHub)

apiclaude-codecodexgoogle-meetmcpmcp-servermeeting-assistantmeeting-minutesmeeting-notesmodel-context-protocolms-teamsnotetakerself-hostedspeech-to-texttranscriptionzoom

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/vexa.svg)](https://argusic.com/subject/vexa)

Questions

Does vexa run?
Yes. vexa runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test vexa?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit dba990b413bd. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test vexa?
The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does vexa take to install?
8 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 vexa need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing vexa?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does vexa compare with the alternatives?
Of the 62 api projects Argusic has installed and timed, vexa was the 40th fastest to reach a running state, and 37 of 62 reached one at all.
Where is the evidence for vexa?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion