clawcodex
Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.
Runssource: GitHubhomepageTypeScriptMITcommit 5c179396277d
TypeScript, MIT licensed. The project labels itself: agent, ai, ai agent, ai coding, claude, claude code, cli and code.
clawcodex runs. An Argusic agent installed it in 5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python virtual environment installs all dependencies cleanly, the 'clawcodex' CLI starts and reports version 1.6.0, and the full test suite of 10,435 tests passes with 0 failures.
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.
- anthropic SDK v1.x (1.5.0) migrated to httpx2 and rejects httpx.Client objects used throughout the codebase, breaking provider initialization and tests10 minutes
- test_advisor_chat_response_roundtrip.py called accumulate_event() without the required json_bufs arg added in anthropic 1.x2 minutes
- test_sigint_during_prefetch_clean_exit flaked — 100ms delay sent SIGINT during module import before signal handler was installed, returning rc=-2 instead of 1302 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 51 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pytest tests/ exited 0, 10435 passed, 13 skipped, 0 failed. python -m src.cli --version returned 'claw-codex version 1.6.0 (Python)'. python -m build --wheel exited 0.
- Model tokens used
- 229,608
- Exact commit tested
- 5c179396277d
- 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.
- code, signal_after_ms=100, signal_name="SIGINT"
+ code, signal_after_ms=500, signal_name="SIGINT"
)
# SIGINT exit code is 128+2 == 130.
self.assertEqual(rc, 130, msg=f"unexpected rc={rc}. out={out} err={err}")
exec
/bin/sh -lc 'cd /work/repo && .venv/bin/python -m pytest tests/ -v --tb=no -q 2>&1 | tail -5' in /w…
All tests passed already — 10,435 passed, 13 skipped, 0 failed in the previous run. Let me compile …
2026-09-12T23:07:08.128112Z ERROR codex_core::session: failed to record rollout items: thread 01a09…
tokens used
229,608
All tests passed already — 10,435 passed, 13 skipped, 0 failed in the previous run. Let me compile …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 5 minutes, faster than the median of the 32 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.
- Measured 2 times, so the result is not a one-off.
Of the 33 agent projects Argusic has installed and timed, clawcodex was the 13th 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 5 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 | Ran out of time | 0.00 | 0.33 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.16 |
Topics (from GitHub)
agentaiai-agentai-codingclaudeclaude-codeclicodecodexcodingcoding-agentdeepseekllmpythontoken-efficient
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/clawcodex)Questions
- Does clawcodex run?
- Yes. clawcodex runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test clawcodex?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c179396277d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test clawcodex?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does clawcodex take to install?
- 5 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 clawcodex need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing clawcodex?
- 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 clawcodex compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, clawcodex was the 13th fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for clawcodex?
- 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.