crew44

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT.

Runssource: GitHubhomepageGoMITcommit cfcf1e74d9a2

Go, MIT licensed. The project labels itself: ai agents, claude code, codex, coding agent, developer tools, eletron, gemini and local first.

crew44 runs. An Argusic agent installed it in 7 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Daemon builds and serves health endpoint at 127.0.0.1:8080; all 16 Go test packages and all 341 frontend vitest tests pass with Node 22.23.4 and Go 1.26.1.

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

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.06 (measured)
recorded runs
1
last tested
stars
358
forks
12
open issues
0
watchers
4
size
7 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 crew44, 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 18.19.1 too old (needs >=20.19.0 for jsdom/html-encoding-sniffer CJS/ESM compat); also Go missing3 minutes
Install time
7 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
go test ./... -> 16/16 packages ok; vitest run -> 21 files, 341 tests passed; daemon boot -> curl /health returned HTTP 200 {"status":"ok"}
Model tokens used
239,848
Exact commit tested
cfcf1e74d9a2
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.

5. **Ran vitest frontend tests** — 21 test files, 341 tests passed (after upgrading Node to 22.23.4…
6. **Launched the daemon** — health endpoint returned `{"status":"ok"}` HTTP 200.
tokens used
239,848
Now I have a complete picture. Let me finalize.
**Summary of what I did:**
1. **Installed prerequisites**: Go 1.26.1 was missing, Node 18.19.1 was too old (needs 20+). Instal…
2. **Ran `npm install`** — succeeded with 1307 packages.
3. **Built the Go daemon** — `go build` succeeded.
4. **Ran Go tests** — all 16 packages passed (cached after initial run, all `ok`).
5. **Ran vitest frontend tests** — 21 test files, 341 tests passed (after upgrading Node to 22.23.4…
6. **Launched the daemon** — health endpoint returned `{"status":"ok"}` HTTP 200.

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 1 error 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 MIT, as reported by its host.

What did not, or is not known

  • Took 7 minutes to install, slower than the median of the 123 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 124 ai-agents projects Argusic has installed and timed, crew44 was the 72nd fastest to reach a running state, and 96 of 124 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 7 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 Runner1/3Runs100.000.06

Topics (from GitHub)

ai-agentsclaude-codecodexcoding-agentdeveloper-toolseletrongeminilocal-firstmulti-agentorchestration

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/crew44.svg)](https://argusic.com/subject/crew44)

Questions

Does crew44 run?
Yes. crew44 runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test crew44?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit cfcf1e74d9a2. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test crew44?
The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does crew44 take to install?
7 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 crew44 need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing crew44?
1 thing 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 crew44 compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, crew44 was the 72nd fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for crew44?
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.

Discussion