AutoHarness
AutoHarness: Automated Harness Engineering for AI Agents
Runssource: GitHubPythonMITcommit 3561e468f9ca
Python, MIT licensed. The project labels itself: agent framework, ai agents, audit, context management, governance, harness engineering, llm and multi agent.
AutoHarness runs. 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.
The AutoHarness CLI and library install and build cleanly in a project venv, the governance pipeline runs for real (validation, allowed/denied tool calls, mode switching, wrap, export, claude-code hook install), and the full test suite passes 958/958; the only mocks needed are LLM credentials for the AgentLoop.
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, 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.
- System pip refused install: PEP 668 externally-managed environment1 minute
- pytest not installed in fresh venv1 minute
- test_cli_wrap test_wrap_failing_command failed: 'python' not found on PATH in this container (only python3 exists), exit 127 instead of 421 minute
- Install time
- 2 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- .venv/bin/python -m pytest tests/ -q exited 0 with 958 passed; .venv/bin/autoharness version returned 'autoharness 0.1.1'; autoharness check --stdin on 'rm -rf /' returned JSON action:deny; AgentLoop mock run returned 'Final answer: done reading.'
- Model tokens used
- 41,369
- Exact commit tested
- 3561e468f9ca
- 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.
........................................................................ [ 90%]
........................................................................ [ 97%]
...................... [100%]
958 passed in 1.91s
Everything is verified. Let me compute the final results.
The install used a venv (the standard workaround for this PEP 668-externally-managed container; a r…
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 2, "er…
tokens used
41,369
Everything is verified. Let me compute the final results.
The install used a venv (the standard workaround for this PEP 668-externally-managed container; a r…
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 2, "er…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 2 minutes, faster than the median of the 62 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.
- 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 63 agent-framework projects Argusic has installed and timed, AutoHarness was the 20th fastest to reach a running state, and 50 of 63 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.
- A quick evaluation: it was running 2 minutes after the clone.
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)
agent-frameworkai-agentsauditcontext-managementgovernanceharness-engineeringllmmulti-agentprompt-injectionsafetytool-use
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/autoharness)Questions
- Does AutoHarness run?
- Yes. AutoHarness runs. 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 AutoHarness?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3561e468f9ca. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test AutoHarness?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does AutoHarness 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 AutoHarness need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing AutoHarness?
- 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 AutoHarness compare with the alternatives?
- Of the 63 agent-framework projects Argusic has installed and timed, AutoHarness was the 20th fastest to reach a running state, and 50 of 63 reached one at all.
- Where is the evidence for AutoHarness?
- 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.