readmeX
An AI Powered README and Interactive Wiki Generator for Any Projects. AI驱动的README及交互式Wiki生成工具,面向中文的开源DeepWiki。
Runssource: GitHubJavaScriptMITcommit 782fc3f54b6c
JavaScript, MIT licensed. The project labels itself: ai tools, cli, documentation, gpt, llm, markdown, python and readme.
readmeX runs. An Argusic agent installed it in 26 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The readmex skill is installed in the user's Codex skills directory and its scanner runs; a live codex run on a mock repo generated README.md, images/logo.svg, and 9 MkDocs pages, and the emitted site builds successfully with mkdocs 1.6.1 + material 9.7.7 from a local venv.
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.
- Initial `codex exec` run timed out at 150s without writing files (model generated an invalid apply_patch hunk and stalled)8 minutes
- System Python is PEP 668 externally-managed, so `pip install --user mkdocs` failed3 minutes
- README's `gh skill install` command cannot run here: `gh` binary is not installed in this container2 minutes
- MkDocs build emitted a warning: docs/index.md links `../../images/logo.svg` which is not a documentation file1 minute
- Install time
- 26 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- `python3 /home/runner/.codex/skills/readmex/scripts/scan.py /work/repo` emitted a valid JSON scan (primary_language python, git readmeX) with exit 0; `codex exec resume --last` completed with exit 0 and wrote README.md + images/logo.svg + website/; `/tmp/mkdocs-venv/bin/mkdocs build -f website/mkdocs.yml` exited 0 (9 HTML pages, INFO Documentation built in 0.28s); `python3 -c ET.parse('images/logo.svg')` parsed OK
- Model tokens used
- 186,420
- Exact commit tested
- 782fc3f54b6c
- 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.
- **Install**: copied the readmex skill to `~/.codex/skills/readmex`; scanner compiles and runs; in… - **Gap recorded**: README's `gh skill install` path can't run here (`gh` binary absent) — performe… - **Full end-to-end verification (tier1_real)**: ran the `codex` CLI harness with the readmex skill… - Note: `website/site/` build output is not ignored by the skill's scanner config, so a built site … tokens used 186,420 Everything checks out. Let me compile the final ARGUSIC_RESULT line. Key findings from the run: - **Install**: copied the readmex skill to `~/.codex/skills/readmex`; scanner compiles and runs; in… - **Gap recorded**: README's `gh skill install` path can't run here (`gh` binary absent) — performe… - **Full end-to-end verification (tier1_real)**: ran the `codex` CLI harness with the readmex skill… - Note: `website/site/` build output is not ignored by the skill's scanner config, so a built site …
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 4 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
- Took 26 minutes to install, slower than the median of the 26 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 27 ai-tools projects Argusic has installed and timed, readmeX was the 26th fastest to reach a running state, and 19 of 27 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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/readmex)Questions
- Does readmeX run?
- Yes. readmeX runs. Argusic installed and launched it on a clean machine in 26 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test readmeX?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 782fc3f54b6c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test readmeX?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does readmeX take to install?
- 26 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 readmeX need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing readmeX?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does readmeX compare with the alternatives?
- Of the 27 ai-tools projects Argusic has installed and timed, readmeX was the 26th fastest to reach a running state, and 19 of 27 reached one at all.
- Where is the evidence for readmeX?
- 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.