CowAgent
Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
Runssource: GitHubhomepagePythonMITcommit 4ea7bdb45255
Python, MIT licensed. The project labels itself: ai, ai agent, ai agents, chatgpt on wechat, claude, claude code, codex and cowagent.
CowAgent runs. An Argusic agent installed it in 3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CowAgent 2.1.9 installs, builds, all 1949 tests pass, web console binds on 127.0.0.1 and answers /api/health with 200 OK, and the CLI reports version 2.1.9.
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
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.
- test_a_zombie_does_not_count_as_alive failed in full suite (zombie detection race with multi-threaded fork)5 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- .venv/bin/python -m pytest tests/ exited 0, 1949 passed, 9 skipped, 5 warnings; curl -s http://127.0.0.1:9876/api/health returned HTTP 200 with body '{"status": "ok"}'; .venv/bin/cow version returned 'cow 2.1.9'
- Model tokens used
- 285,879
- Exact commit tested
- 4ea7bdb45255
- 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 2, 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.
os.kill(pid, 0)
except OSError:
return False
try:
with open(f"/proc/{pid}/stat") as f:
state = f.read().split()[2]
except (OSError, IndexError, ValueError):
2026-11-01T19:33:25.999663Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce…
Now let me compile the complete results.
tokens used
285,879
Now let me compile the complete results.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.
- Installed in 3 minutes, faster than the median of the 231 comparable projects Argusic has measured.
- 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.
- Measured 2 times, so the result is not a one-off.
Of the 232 ai projects Argusic has installed and timed, CowAgent was the 75th fastest to reach a running state, and 153 of 232 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 3 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
Topics (from GitHub)
aiai-agentai-agentschatgpt-on-wechatclaudeclaude-codecodexcowagentdeepseekharnessllmmcpmulti-agentopenaiopenclawpersonal-agentskills
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cowagent)Questions
- Does CowAgent run?
- Yes. CowAgent runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test CowAgent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4ea7bdb45255. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test CowAgent?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does CowAgent take to install?
- 3 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 CowAgent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing CowAgent?
- 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 CowAgent compare with the alternatives?
- Of the 232 ai projects Argusic has installed and timed, CowAgent was the 75th fastest to reach a running state, and 153 of 232 reached one at all.
- Where is the evidence for CowAgent?
- 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.