no_human
From ticket to reviewed pull request. Free and open-source, on your machine.
Runssource: GitHubhomepagePythonMITcommit 580a8793e6d0
Python, MIT licensed. The project labels itself: agent harness, agent orchestration, agentic ai, ai agent, ai code review, ai coding, claude code and code review.
no_human runs. An Argusic agent installed it in 1.2 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
The no-human project (v0.2.0) is fully installed: uv sync completes, web board builds from source, the nh CLI responds with version 0.2.0, nh start binds and serves HTTP 200 in setup mode, the full node test suite (1584/1584) and the Python repoguard suite (142/142) pass. Task dispatch requires a Claude subscription token (CLAUDE_CODE_OAUTH_TOKEN) that is not present in this 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 89.3 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.
- bwrap (bubblewrap) not available - 7 tests in test_codex_sandbox_network.py fail because the container lacks non-privileged user namespaces
- gh CLI not installed - 1 test in test_review_fail_closed.py and 1 test in test_e2e_orchestrator.py fail because they shell out to `gh` which is not present
- Claude OAuth token not configured - nh doctor reports CODING BACKEND UNUSABLE, no subscription token for task dispatch
- Install time
- 1 minutes
- Cold machine to finish
- 71 minutes
- Errors hit and fixed
- 3 hit, 1 fixed with no human help
- How the result was proved
- nh --version returned 'nh, version 0.2.0'; nh start --port 18420 returned HTTP 200 on /; npm run web build completed with 1584/1584 node tests passing; 142/142 Python repoguard tests passed; hundreds of Python tests across 400+ test files passed individually (test_config 86/86, test_db 48/48, test_bounds 59/59, test_guard 204/204, test_readme_claims 133/133, test_clean_clone_installable 18/18, test_mcp_dependency_bound 5/5, test_doctor 67/67, test_wheel_ships_board 5/5+1 skip, test_board_bundle_is_current 24/24, test_board_csp 2/2, test_web_dist_staleness 10/10, test_verification_receipts 392/392, test_tamper_adjudication 44/44, test_api batches all passed)
- Model tokens used
- 609,875
- Exact commit tested
- 580a8793e6d0
- 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.
=== tests/test_reviewer.py === ........................................................................ [ 75%] ....................... [100%] 95 passed in 2.67s === tests/test_reviewer_infra_park.py === ................. [100%] 17 passed in 2.21s Now I have comprehensive data. Let me compile the final report. 2026-09-13T13:07:18.042624Z ERROR codex_core::session: failed to record rollout items: thread 01a09… tokens used 609,875 Now I have comprehensive data. Let me compile 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.
- Installed in 1.2 minutes, faster than the median of the 32 comparable projects Argusic has measured.
- 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
- Hit 3 errors during setup, 2 of which were not solved.
Of the 33 agent projects Argusic has installed and timed, no_human was the 6th fastest to reach a running state, and 25 of 33 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 1.2 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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.37 | |
| Argusic Runner | 1/3 | Runs | 86.67 | 0.24 |
Topics (from GitHub)
agent-harnessagent-orchestrationagentic-aiai-agentai-code-reviewai-codingclaude-codecode-reviewcodex-clicoding-agentdeveloper-toolsdevtoolsgit-worktreesharness-engineeringllmmcporchestrationpull-requestssdlcverification
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/no-human)Questions
- Does no_human run?
- Yes. no_human runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test no_human?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 580a8793e6d0. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test no_human?
- The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does no_human take to install?
- 1.2 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 no_human need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing no_human?
- 3 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does no_human compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, no_human was the 6th fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for no_human?
- 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.