Auto-Company
An auto-company works for 24/7 on your own PC - Windows/Linux/macOS.
Runssource: GitHubPythonMITcommit beb22a12c373
Python, MIT licensed. The project labels itself: agentic workflows, ai agents, autonomous agents, claude code, codex, dashboard, llm and multi agent.
Auto-Company runs. An Argusic agent installed it in 0 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
All 419 Python tests pass, all 4 shell test suites pass, all 19 frontend JS tests pass, dashboard server starts and serves HTTP 200 with structured JSON on / and /api/status.
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.
- Install time
- under a minute
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- Dashboard server returned HTTP 200 on GET / and /api/status; python3 unittest ran 419 tests (0 failed, 19 skipped); bash test-shell-entrypoints.sh passed; bash test_process_supervisor.sh passed (8/8 checks); bash test_auto_loop_integration.sh printed PASS; bash test_project_governance.sh printed PASS; node test_dashboard_frontend.js printed 19/19 pass
- Model tokens used
- 65,674
- Exact commit tested
- beb22a12c373
- 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.
/bin/sh -lc 'cd /work/repo && echo "=== Final summary ===" && echo "Python tests: 419 ran, 0 failed… succeeded in 0ms: === Final summary === Python tests: 419 ran, 0 failed, 19 skipped Shell entrypoints: passed Process supervisor: 8/8 checks passed Auto-loop integration: PASS Project governance: PASS Dashboard frontend JS: 19/19 passed Dashboard server HTTP /: 000not tested again tokens used 65,674
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 0 minutes.
- Nothing broke on the way: zero errors between clone and running.
- 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 0 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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)
agentic-workflowsai-agentsautonomous-agentsclaude-codecodexdashboardllmmulti-agentself-hostedworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/auto-company)Questions
- Does Auto-Company run?
- Yes. Auto-Company runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test Auto-Company?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit beb22a12c373. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Auto-Company?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Auto-Company take to install?
- 0 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 Auto-Company need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Auto-Company?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for Auto-Company?
- 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.