OpenCompany
Self-improving AI Employees for everyone
Runssource: GitHubhomepagePythonMITcommit 261cf9391f45
Python, MIT licensed. The project labels itself: ai agents, ai employee, ai employees, assistant, autonomous agents, co employees, company and grok bot.
OpenCompany runs. An Argusic agent installed it in 5.2 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
OpenCompany v0.2.1 builds, starts, serves the React SPA and health API on localhost:5678, and passes 4253 combined tests (3788 backend + 465 frontend).
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.
- bun not found in container — needed to install/build1 minute
- python command not found — only python3 available1 minute
- uv not found; pip install uv failed with externally-managed-environment1 minute
- PEP 668 externally-managed-environment blocked pip install -e . for CLI dependencies1 minute
- Install time
- 5 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- bun run test:backend (uv run pytest tests/) exited 0 with 3788 passed, 2 skipped; bun run test:frontend (vitest run) exited 0 with 465 passed; company start launched uvicorn serving http://localhost:5678/health returning 200 with full health JSON and SPA returning 200
- Model tokens used
- 66,934
- Exact commit tested
- 261cf9391f45
- 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.
Temporal: enabled
[OK] Port 5678: Killed 1 process(es)
PIDs: 7493
[OK] Port 5679: Free
[OK] Port 5681: Killed 1 process(es)
PIDs: 7510
[OK] Port 5680: Free
All services stopped.
Let me compute the elapsed time from the start.
tokens used
66,934
Let me compute the elapsed time from the start.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 4 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 MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 5.2 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
Of the 237 ai projects Argusic has installed and timed, OpenCompany was the 136th fastest to reach a running state, and 168 of 237 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 5.2 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)
ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opencompany)Questions
- Does OpenCompany run?
- Yes. OpenCompany runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test OpenCompany?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 261cf9391f45. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test OpenCompany?
- 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 OpenCompany take to install?
- 5.2 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 OpenCompany need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenCompany?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does OpenCompany compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, OpenCompany was the 136th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for OpenCompany?
- 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.