Report · marked 10 Oct 2026

openai/openai-python

Ready for an agent to work in without hand-holding.

Python · 31,797 stars · 2,417 files · branch main

87 /100 A

Instructions 27/27Whether the repo tells an agent how to behave before it starts guessing. Full marks.Setup 18/20Whether an agent can install the project and get it running without a human. Losing marks on environment config.Verification loop 22/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on tests exist and static type checking.Context economy 14/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context.Navigability 8/10How quickly anything new can orient itself. Losing marks on written documentation.

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

Fix these first

File sizes fit in context

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

Environment config

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.

Written documentation

Prose that explains why the architecture is the way it is saves an agent from re-deriving it wrong.

The full marking

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

Instructions 27/27 A+

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

✓Agent instruction file 12/12

AGENTS.md is present, which is the format the most tools read.

✓Instruction quality 12/12

Specific enough that an agent can act on it.

6,540 characters, a workable length

names the actual commands to run

uses headings, so an agent can skim it

includes copyable code blocks

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 18/20 A

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

✓Deterministic install 6/6

pnpm-lock.yaml pins the dependency tree.

Found pnpm-lock.yaml

✓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 .node-version

✓Reproducible environment 2/2

.devcontainer/devcontainer.json gives a known-good environment.

Verification loop 22/25 A

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

✗Tests exist 6/8

329 test files against 2309 source files.

e.g. scripts/castiron/test_custom_code_budget.py, scripts/castiron/test_custom_code_github.py, scripts/castiron/test_custom_code_publication.py

✓Test command is discoverable 7/7

An agent can find and run `pytest`.

✓Continuous integration 4/4

8 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

pyproject.toml encodes the house style.

✗Static type checking 2/3

Type checking is configured, but not in strict mode.

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 14/20 B+

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 18 patterns.

✗File sizes fit in context 0/6

8 source files are over 100KB.

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

tests/test_uv_workflows.py — 385KB

src/openai/resources/beta/responses/responses.py — 267KB

src/openai/resources/responses/responses.py — 259KB

✓Repository weight 5/5

About 19.3MB 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 openai/openai-python

# AGENTS.md

The official Python library for the OpenAI API

## Setup

```
pnpm install
```

## Commands

```
pytest         # run the test suite
ruff check .   # lint
```

## Layout

- `src/`      1931 source files
- `tests/`    309 source files
- `examples/` 47 source files
- `scripts/`  22 source files

## Conventions

- Tests live alongside the code they cover, following `scripts/castiron/test_custom_code_budget.py`.
- CI defines what passing means. See `.github/workflows/castiron-custom-code-comment.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- `tests/test_uv_workflows.py` is 385KB. It will not fit comfortably in context, so read it in parts.

---

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/openai/openai-python.md

A draft gets the commands right and stops at the things only a maintainer knows. What a good Python AGENTS.md looks like covers what to add by hand, and what AGENTS.md is explains the format itself.

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](https://agentreadme.com/badge/openai/openai-python.svg)](https://agentreadme.com/openai/openai-python)

Other Python repositories, marked

vinta/awesome-python 81 A- NousResearch/hermes-agent 84 A- TheAlgorithms/Python 89 A yt-dlp/yt-dlp 54 C+ microsoft/markitdown 48 C+ Significant-Gravitas/AutoGPT 65 B

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