agentreadme

Report · marked 25 Aug 2026

karpathy/nanochat

An agent can work here, but it will waste turns finding its footing.

Python · 57,513 stars · 53 files · branch master

61 /100 B-
Instructions 3/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file and instruction quality.Setup 16/18Whether an agent can install the project and get it running without a human. Losing marks on environment config.Verification loop 15/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on continuous integration and lint and format rules.Context economy 20/20Whether the repo fits in a context window, or fights it. Full marks.Navigability 7/10How quickly anything new can orient itself. Losing marks on written documentation and repository description.

Higher is better. Accent marks what is costing you most.

Fix these first

01
Agent instruction file
Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.
02
Instruction quality
Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.
03
Continuous integration
A CI workflow doubles as machine-readable documentation: it's the one file that states, unambiguously, the exact commands that must succeed.

The full marking

Every deduction below names the file or setting it came from.

Instructions 3/27 F

Whether the repo tells an agent how to behave before it starts guessing.

✗Agent instruction file 0/12
None found. Every agent that opens this repo starts from zero.
Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.
Looked for AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .cursorrules
✗Instruction quality 0/12
Nothing to judge, since there are no instructions.
Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.
✓README as an entry point 3/3
README has a clear getting-started section.
Setup 16/18 A

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6
uv.lock pins the dependency tree.
Found uv.lock
✓Discoverable commands 6/6
Commands are declared where an agent will look for them.
scripts/ directory
✗Environment config 2/4
Env vars are mentioned in the README but there's no example file to copy.
Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.
✓Pinned runtime version 2/2
The language runtime version is pinned.
Found .python-version
–Reproducible environment n/a
Not applicable — a library doesn't need a container to be worked on.
Verification loop 15/25 B-

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✓Tests exist 8/8
6 test files against 40 source files.
e.g. tests/test_attention_fallback.py, tests/test_engine.py, tests/test_execution.py
✓Test command is discoverable 7/7
An agent can find and run `pytest`.
✗Continuous integration 0/4
No CI config. Nothing outside a developer's laptop enforces correctness.
A CI workflow doubles as machine-readable documentation: it's the one file that states, unambiguously, the exact commands that must succeed.
✗Lint and format rules 0/3
No linter or formatter config. Style is tribal knowledge, so agent output will drift from yours.
A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.
✗Static type checking 0/3
No static type checking.
A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.
Context economy 20/20 A+

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6
No generated directories committed.
✓.gitignore hygiene 3/3
.gitignore covers 9 patterns.
✓File sizes fit in context 6/6
No source file is large enough to crowd out a context window.
✓Repository weight 5/5
About 2.2MB checked out, which is comfortable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for karpathy/nanochat 
# AGENTS.md

The best ChatGPT that $100 can buy.

## Setup

```
uv sync
```

## Commands

```
pytest   # run the test suite
```

## Layout

- `nanochat/` 14 source files
- `scripts/`  9 source files
- `tasks/`    6 source files
- `tests/`    6 source files
- `runs/`     4 source files
- `dev/`      1 source file

## Conventions

- Tests live alongside the code they cover, following `tests/test_attention_fallback.py`.
- TODO: add the two or three conventions a newcomer always gets wrong here.

---

Drafted by agentreadme.com from what is in this repository. Everything marked TODO
needs a human. Check it in as AGENTS.md at the root.

Open the raw markdown  or  curl -o AGENTS.md agentreadme.com/draft/karpathy/nanochat.md

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

agent ready 61 out of 100

[![agent ready](https://agentreadme.com/badge/karpathy/nanochat.svg)](https://agentreadme.com/karpathy/nanochat)

Other Python repositories, marked

vinta/awesome-python 81 A- NousResearch/hermes-agent 84 A- TheAlgorithms/Python 66 B yt-dlp/yt-dlp 54 C+ Significant-Gravitas/AutoGPT 63 B microsoft/markitdown 46 C

All Python repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in