karpathy-llm-wiki

Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.

Runssource: GitHubPythonMITcommit eafcc77001e4

Python, MIT licensed. The project labels itself: agent skill, claude code, codex, cursor, karpathy, knowledge base, knowledge management and llm.

karpathy-llm-wiki runs. An Argusic agent installed it in 2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 52 tests pass and the check_evidence.py script verifies wiki article fidelity against raw source material, detecting mismatched numbers, dates, and quotes.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.05 (measured)
recorded runs
2
last tested
stars
2,765
forks
317
open issues
11
watchers
17
size
0 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 karpathy-llm-wiki, 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.

  • npx add-skill install fails: Node.js v18.19.1 < required v22.20.00.5 minutes
Install time
2 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
python3 -m unittest discover tests/ exited 0, 52 passed; python3 scripts/check_evidence.py against a real wiki correctly confirmed matching values and flagged fabricated value 5,000 as a fidelity suspect
Model tokens used
42,082
Exact commit tested
eafcc77001e4
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.

....................................................
Ran 52 tests in 2.505s
OK
exit: 0
All tests pass and the evidence checker works correctly end-to-end. Let me compile the final result.
exec
/bin/sh -lc 'cd /work/repo && python3 -m unittest discover tests/ 2>&1 | grep -E "''^Ran|''^OK|''^F…
 succeeded in 2414ms:
Ran 52 tests in 2.501s
OK
tokens used
42,082

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 13 comparable projects Argusic has measured.
  • Recovered from all 1 error 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 14 agent-skill projects Argusic has installed and timed, karpathy-llm-wiki was the 5th fastest to reach a running state, and 12 of 14 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.05
Argusic Runner1/3Runs100.000.04

Topics (from GitHub)

agent-skillclaude-codecodexcursorkarpathyknowledge-baseknowledge-managementllmllm-wikimarkdownpersonal-knowledge-baseproductivityrag-alternative

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/karpathy-llm-wiki.svg)](https://argusic.com/subject/karpathy-llm-wiki)

Questions

Does karpathy-llm-wiki run?
Yes. karpathy-llm-wiki runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test karpathy-llm-wiki?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit eafcc77001e4. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test karpathy-llm-wiki?
The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does karpathy-llm-wiki 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 karpathy-llm-wiki need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing karpathy-llm-wiki?
1 thing 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 karpathy-llm-wiki compare with the alternatives?
Of the 14 agent-skill projects Argusic has installed and timed, karpathy-llm-wiki was the 5th fastest to reach a running state, and 12 of 14 reached one at all.
Where is the evidence for karpathy-llm-wiki?
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