Autonomous-Company
An autonomous company working 24/7 on your own PC - Windows/Linux/macOS.
Runssource: GitHubPythonMITcommit c7c60dbd40d2
Python, MIT licensed. The project labels itself: agentic workflows, ai agents, autonomous agents, claude code, codex, dashboard, llm and multi agent.
Autonomous-Company runs. An Argusic agent installed it in 50 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
The dashboard and product-center HTTP servers, the Python test suite (619 of 632 passing; 13 isolation-blocked failures), all fake-engine shell integration tests, frontend JS contract suites and example Node tests except scopefence run successfully in this container.
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 88 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.
- Project isolation could not start: container denies unprivileged user namespaces (unshare EPERM, seccomp/caps 0); even the bundled Codex bwrap binary reports 'No permissions to create a new namespace'. Prevents runtime_artifacts/observability/project_registry tests, project.sh status and project_governance + systemd shell tests.30 minutes
- test_ui_messages.OperatorMessageTests.test_native_bash_nounset_handles_messages_with_and_without_parameters fails deterministically: ui_message language.saved en emits the zh-CN template while the container locale is C.UTF-8 (no zh-* env), so the 'en' English string is absent; the test-then-message ordering depends on pre-seeding .autonomous-company.local, which this brand-new checkout lacks.10 minutes
- Browser and Node-20 suites cannot run: container has only Node 18.19.1 (playwright requires >=20, refused to download Chromium) and no other Node binary or root to install one.10 minutes
- Tailwind oxide native binding missing in dashboard/ui build (npm 9 + Node 18 optional-dependency bug, @tailwindcss/oxide-linux-x64-gnu absent); only reproducible on the CI-pinned Node 22 which is unavailable.5 minutes
- examples/scopefence test fails 1/8: 'crypto is not defined' in scopefence-core.js makeReceipt/randomUUID on Node 18 (browser-only global); unrelated to the framework runtime.5 minutes
- Install time
- 50 minutes
- Cold machine to finish
- 18 minutes
- Errors hit and fixed
- 5 hit, 2 fixed with no human help
- How the result was proved
- curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8891/ returned 200 and /journal, /app.js, /favicon.svg each 200; center_server.py /center returned 200; python3 -m unittest discover -s tests: Ran 632, FAILED 13 (all namespace-enabled); bash tests/test_auto_loop_integration.sh and tests/test_process_supervisor.sh exited 0; node --test tests/test_dashboard_frontend.js 37 passed and test_center_frontend.js 32 passed; node --test examples/text-meter/tests/counts.test.js 5/5 passed; scripts/core/project_isolation.py --check refused (exit 78) due to kernel userns denial.
- Model tokens used
- 815,376
- Exact commit tested
- c7c60dbd40d2
- 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.
exec
/bin/sh -lc 'ps -p 48684 -o pid,cmd 2>/dev/null || echo "no such process (pgrep matched itself)"; p…
succeeded in 0ms:
PID CMD
no such process (pgrep matched itself)
none
All background processes stopped, temp dirs cleaned, git tree pristine.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 50, "e…
tokens used
815,376
All background processes stopped, temp dirs cleaned, git tree pristine.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 50, "e…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 50 minutes.
- 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
- Hit 5 errors during setup, 3 of which were not solved.
- 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.
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/autonomous-company)Questions
- Does Autonomous-Company run?
- Yes. Autonomous-Company runs. Argusic installed and launched it on a clean machine in 50 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test Autonomous-Company?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c7c60dbd40d2. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Autonomous-Company?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Autonomous-Company take to install?
- 50 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 Autonomous-Company need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Autonomous-Company?
- 5 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Autonomous-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.