AI-company

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen, pure CC native integration.

Runssource: GitHubPythonMITcommit 329c525e5f56

Python, MIT licensed. The project labels itself: agent framework, agent orchestration, ai agents, autonomous agents, claude, claude code, claude code plugin and dashboard.

AI-company runs. An Argusic agent installed it in 23 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

AI Team OS v1.14.0 API answers 200 on /api/health, serves 187 REST endpoints and 116 MCP tools. Codex adapter installed with 7/7 hook files, MCP via stdio verified. SQLite database at ~/.claude/data/ai-team-os/aiteam.db holds 47 tables with working project/task CRUD and cross-request persistence. Unit tests pass 4109/4128 (1 pre-existing test-env isolation failure).

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
$0.42 (measured)
recorded runs
1
last tested
stars
379
forks
66
open issues
0
watchers
4
size
38 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 AI-company, 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.

  • test_restart_development.py::test_source_switch_child_keeps_existing_database fails — subprocess resolves user-site relative to tmp HOME, not finding sqlalchemy installed in /home/runner/.local5 minutes
  • test_codex_adapter_start.py (2 tests) fail — HTTP MCP preflight fails in isolated HOME; same user-site root cause2 minutes
  • test_codex_runtime.py (12 tests) fail — subprocesses with isolated HOME can't import psutil from /home/runner/.local2 minutes
  • test_mcp_concurrency.py, test_mcp_http_sharing.py (4 tests) fail — child process in isolated env can't import psutil2 minutes
  • PEP 668 externally-managed-environment error on 'pip install -e .' in Debian system Python1 minute
  • test_codex_release_database.py fails — reference commit dd60e97 not present in shallow clone1 minute
Install time
23 minutes
Cold machine to finish
44 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
pip install -e . (PEP 668 bypass) -> codex_adapter.py start -> curl localhost:8000/api/health returned 200, status=ok, version=1.14.0 -> MCP stdio client session returned 116 tools -> task_create MCP tool called via API -> task persisted in SQLite (verified via sqlite3 CLI) -> E2E API coverage suite: 22/23 PASS -> API smoke: 13/24 PASS (hardcoded project ID not found) -> Unit tests: 4109 passed, 18 skipped (1 pre-existing env-isolation gap)
Model tokens used
1,801,192
Exact commit tested
329c525e5f56
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.

            \"fix\": \"unfixed — shallow clone doesn't contain the release baseline; CI does a full…
            \"minutes\": 1
        }
    ],
    \"test_depth\": \"tier1_real\",
    \"verified_how\": \"pip install -e . (PEP 668 bypass) -> codex_adapter.py start -> curl localho…
    \"final_state\": \"AI Team OS v1.14.0 API answers 200 on /api/health, serves 187 REST endpoints…
}))
EOF" in /work/repo
 succeeded in 0ms:
tokens used
1,801,192

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 6 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.

What did not, or is not known

  • Took 23 minutes to install, slower than the median of the 63 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 64 agent-framework projects Argusic has installed and timed, AI-company was the 59th fastest to reach a running state, and 51 of 64 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.

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 Runner1/3Runs100.000.42

Topics (from GitHub)

agent-frameworkagent-orchestrationai-agentsautonomous-agentsclaudeclaude-codeclaude-code-plugindashboardfastapimcpmcp-servermeeting-systemmulti-agent-systempipeline-workflowpythonreactsqlitetask-managementteam-collaborationtypescript

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/AI-company.svg)](https://argusic.com/subject/ai-company)

Questions

Does AI-company run?
Yes. AI-company runs. Argusic installed and launched it on a clean machine in 23 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test AI-company?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 329c525e5f56. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test AI-company?
The run that produced this verdict cost $0.42: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does AI-company take to install?
23 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 AI-company need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing AI-company?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does AI-company compare with the alternatives?
Of the 64 agent-framework projects Argusic has installed and timed, AI-company was the 59th fastest to reach a running state, and 51 of 64 reached one at all.
Where is the evidence for AI-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.

Discussion