openharness

The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.

Runssource: GitHubhomepageTypeScriptMITcommit e7736e268fe6

TypeScript, MIT licensed. The project labels itself: 3d modeling, agent framework, agent harness, ai agents, cad, claude code, codex and coding agents.

openharness runs. An Argusic agent installed it in 45 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The CLI monorepo package installs, typechecks, builds, and passes all 5741 tests on Ubuntu 24.04 with Node 22.23.3, with sqlite3 and lsof made available in the container environment.

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 91 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
91 / 100
cost of the verifying run
$0.30 (measured)
recorded runs
2
last tested
stars
1,522
forks
145
open issues
95
watchers
3
size
878 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 openharness, 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 PATH /usr/bin:/bin contains /usr/bin/node (v18), so dshNodeFallback (which checks `command -v node`) never appends the managed runtime, causing 2 tests to fail5 minutes
  • lsof not available in container — support.spec.ts processView test could not list open files of the current process5 minutes
  • loginForceRace.spec.ts timed out because tsx transpilation startup was too slow in the container5 minutes
  • sqlite3 CLI not on PATH — 9 tests in opencode/hermes/devin spec failed because the sqlite3 CLI reader path couldn't find the binary3 minutes
  • machineList.spec.ts mtimeMs check failed because filesystem writes happened within the same millisecond3 minutes
  • dsh/install.spec.ts doctor timeout test exceeded 5s default vitest timeout because the `sleep 30` subprocess kill-then-SIGKILL grace period took too long3 minutes
Install time
45 minutes
Cold machine to finish
48 minutes
Errors hit and fixed
7 hit, 7 fixed with no human help
How the result was proved
npx vitest run exited 0, 324 test files passed, 5741 tests passed, 37 skipped. CLI: `node dist/cli.js version` printed 0.0.1, `node dist/cli.js --help` printed usage.
Model tokens used
495,706
Exact commit tested
e7736e268fe6
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.

5. machineList mtimeMs precision -> added 20ms delay before write check
6. loginForceRace timeout (tsx startup slow) -> use dist/cli.js instead of tsx
7. dsh/install doctor test timeout -> increased global testTimeout to 30s
Test Results: 324 passed, 6 skipped, 0 failed
5741 tests passed, 37 skipped
exec
/bin/sh -lc '# Calculate elapsed minutes
echo $(( (1791597752 - 1791595033) / 60 ))' in /work/repo
 succeeded in 0ms:
45
tokens used
495,706

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 7 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 45 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.

Of the 4 3d-modeling projects Argusic has installed and timed, openharness was the 3rd fastest to reach a running state, and 4 of 4 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 Runner2/3Runs with mocks82.000.13
Argusic Runner1/3Runs100.000.30

Topics (from GitHub)

3d-modelingagent-frameworkagent-harnessai-agentscadclaude-codecodexcoding-agentsdeveloper-toolsesp32game-developmentmcp-servermulti-agentopen-hardwareopencodeopenharnesspcbroboticsterminaltmux

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/openharness.svg)](https://argusic.com/subject/openharness)

Questions

Does openharness run?
Yes. openharness runs. Argusic installed and launched it on a clean machine in 45 minutes, hitting 7 errors on the way, and recorded the session.
How did Argusic test openharness?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e7736e268fe6. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test openharness?
The run that produced this verdict cost $0.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does openharness take to install?
45 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 openharness need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing openharness?
7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does openharness compare with the alternatives?
Of the 4 3d-modeling projects Argusic has installed and timed, openharness was the 3rd fastest to reach a running state, and 4 of 4 reached one at all.
Where is the evidence for openharness?
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.

Discussion