coop-anything
Co-op Anything: point your AI agent at any single-player game and play it with friends (online and/or splitscreen!). MCP server and playbook to let you reverse engineer, fix, test, ship and share what it learns.
Runssource: GitHubPythonMITcommit b494a3f3dfd1
Python, MIT licensed.
coop-anything runs. An Argusic agent installed it in 14 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
After creating a project venv (PyYAML) and patching two real defects, the buildlock Windows-only mutation twin not used off-Windows and the MCP detect_engine silently dropping family matches without PyYAML, every Linux-runnable tool suite passes: 12 of 15 test suites ALL OK with gamepool and hotreload skipping by design on Linux, the MCP server passes 13/13 unit tests and answers MCP initialize/tools/list/tools/cal...
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. 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.
- tools/buildlock/run_tests.py mutation twin check_msvc_environment[vcvars_ignored] could never be caught on non-Windows: check_msvc_environment bails out early, so the vcvars_env patch was unobservable10 minutes
- PEP 668 blocked system pip install of PyYAML for the MCP server (README/playbook/mcp.md requires it)2 minutes
- tools/mcp/coop_mcp.py detect_engine silently returned same_engine_projects: [] when PyYAML was missing, so MCP clients got wrong engine-family data2 minutes
- Install time
- 14 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- .venv/bin/python -I tools/test_all.py -> 12 PASS, gamepool+hotreload SKIPPED(Windows-only), buildlock now ALL OK (26 checks, 22 twins, 0 failed); .venv/bin/python -m unittest tools/mcp/test_coop_mcp.py -> Ran 13 tests, OK; .venv/bin/python -I tools/build_directory.py --check -> OK: 340 entries; MCP stdio handshake probe (python -I -c): initialize returned serverInfo coop-anything, tools/list listed 9 tools, tools/call search_directory(Doom) returned count 5; live detect_engine on a temp base/pak000.pk4 fixture returned engine id Tech 4 with same_engine_projects 10.
- Model tokens used
- 1,718,559
- Exact commit tested
- b494a3f3dfd1
- 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.
succeeded in 0ms: M tools/buildlock/run_tests.py M tools/mcp/coop_mcp.py ?? .venv/ ==== tools/buildlock/run_tests.py | 5 +++++ tools/mcp/coop_mcp.py | 4 +++- 2 files changed, 8 insertions(+), 1 deletion(-) All verification is complete and reproducible; here is the final report. tokens used 1,718,559 All verification is complete and reproducible; here is the final report.
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 3 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 14 minutes to install, slower than the median of the 44 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 45 Python projects Argusic has installed and timed, coop-anything was the 41st fastest to reach a running state, and 24 of 45 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.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/coop-anything)Questions
- Does coop-anything run?
- Yes. coop-anything runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test coop-anything?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b494a3f3dfd1. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test coop-anything?
- The run that produced this verdict cost $0.39: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does coop-anything take to install?
- 14 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 coop-anything need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing coop-anything?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does coop-anything compare with the alternatives?
- Of the 45 Python projects Argusic has installed and timed, coop-anything was the 41st fastest to reach a running state, and 24 of 45 reached one at all.
- Where is the evidence for coop-anything?
- 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.