qm
Multiplayer agent harness for work.
Runs with mockssource: GitHubTypeScriptMITcommit 8adee4b06a59
TypeScript, MIT licensed. The project labels itself: ai, assistant, harness and qm.
qm runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2 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 installing Node 24 and building the connector SDK, npm ci installs 730 packages, TypeScript compiles with zero errors, the test suite passes 2700+ tests across representative batches, and the core server starts listening on :8081 returning HTTP 401 (expected without authentication credentials).
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 56 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.
- Node.js 18.19.1 installed, project requires >=24.15.01 minute
- Connector SDK bundle missing for some tests1 minute
- 2 dev-supervisor-child tests fail on IPv6/port ownership assertion (timing-sensitive dev tool tests)
- Install time
- 2 minutes
- Cold machine to finish
- 27 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- node --test (with --experimental-test-module-mocks) across 6 sampled batches totaling 2700+ tests passed with 0 failures (excluding 2 flaky dev-tool failures and skipped PG tests); TypeScript tsc --noEmit passes with 0 errors; server starts and answers HTTP 401 (expected auth challenge) on /
- Model tokens used
- 518,808
- Exact commit tested
- 8adee4b06a59
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
ℹ todo 0 ℹ duration_ms 467.633357 exec /bin/sh -lc 'export PATH="/tmp/node-v24.21.0-linux-x64/bin:$PATH" cd /work/repo && node --experimental-test-module-mocks --test test/agent-conversations-route.test.t… exited 1 in 31317ms: OK, now I have all the data. Here's the summary: 2026-09-26T11:00:30.595960Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… 2026-09-26T11:00:30.596004Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… tokens used 518,808 OK, now I have all the data. Here's the summary:
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
- Installed in 2 minutes, faster than the median of the 43 comparable projects Argusic has measured.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- 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
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Of the 44 ai projects Argusic has installed and timed, qm was the 7th fastest to reach a running state, and 36 of 44 reached one at all.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.11 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.06 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/qm)Questions
- Does qm run?
- qm runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test qm?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8adee4b06a59. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test qm?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does qm take to install?
- 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 qm need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing qm?
- 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 qm compare with the alternatives?
- Of the 44 ai projects Argusic has installed and timed, qm was the 7th fastest to reach a running state, and 36 of 44 reached one at all.
- Where is the evidence for qm?
- 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.