Agent Friendly Code

openai/openai-cookbook

GitHub
https://github.com/openai/openai-cookbook

Examples and guides for using the OpenAI API

Stars:
76.9k
Language:
Jupyter Notebook
Default branch:
main
Last scored:
Overall

At a glance

Rank
#379 of 401
Checks passed
5 of 17
Full list below
Best set up for
Claude Code
Score 50.7
Needs most work for
Aider
Biggest fix: .aider.conf.yml (+14.1 pts)

What it has

What it's missing

What to fix first

Pick an AI agent

Showing fixes for Claude Code

  1. 1
    Reproducible dev env
    Add a Makefile or devcontainer or Dockerfile so the agent can set up the project in one command.
    +11.8 pts
  2. 2
    Dependency manifest
    Commit a proper manifest (package.json, pyproject.toml, Cargo.toml, go.mod, etc.) plus a lockfile.
    +9.2 pts
  3. 3
    Linter / formatter config
    Configure a linter/formatter (ESLint+Prettier, Biome, Ruff, rustfmt+clippy, golangci-lint) and commit the config.
    +7.9 pts

Score for each AI agent

Each agent weighs the checks by its own docs. Under each score are its top three. How each agent is scored →

Claude Code
#373 of 401
50.7
  • ✓AGENTS.md / CLAUDE.md
  • ~Test suite
  • ✗Reproducible dev env
Codex
#375 of 401
49.5
  • ✓AGENTS.md / CLAUDE.md
  • ✓README
  • ~Test suite
Kimi Code CLI
#371 of 401
48.4
  • ✓AGENTS.md / CLAUDE.md
  • ~Test suite
  • ✗Dependency manifest
Pi
#374 of 401
46.4
  • ✓AGENTS.md / CLAUDE.md
  • ~Test suite
  • ✗Linter / formatter config
Devin
#384 of 401
44.4
  • ✗Reproducible dev env
  • ✗Dependency manifest
  • ~Test suite
OpenHands
#387 of 401
42.8
  • ✓CI configuration
  • ✗Dependency manifest
  • ✗Reproducible dev env
Gemini CLI
#383 of 401
41.1
  • ✗GEMINI.md
  • ✓README
  • ~Test suite
Cursor
#380 of 401
40.1
  • ✗Cursor rules (.cursor/rules)
  • ✓README
  • ✗Type configuration
Aider
#390 of 401
36.6
  • ✗.aider.conf.yml
  • ✗Linter / formatter config
  • ~Test suite

Does openai/openai-cookbook have agent instructions?

An AGENTS.md (or CLAUDE.md) at the root tells AI coding agents how to build, test and work in the repo. A few agents also read a file of their own.

AGENTS.md / CLAUDE.md
AGENTS.md (new tab) · 5,672 characters
Agent-specific files
None: no GEMINI.md, .cursor/rules, .openhands/setup.sh, .aider.conf.yml or .agents/skills
Repos that have one
221 of 401 repos on the leaderboard · See examples →

All 17 checks · 5 passed

Skills (.agents/skills)· 0% pass
No .agents/skills/<name>/SKILL.md
AGENTS.md / CLAUDE.md· 100% pass
Substantive (5,672 characters)
AGENTS.md
.aider.conf.yml· 0% pass
No .aider.conf.yml at repo root
CI configuration· 100% pass
3 GitHub Actions workflows
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
CONTRIBUTING.md
Cursor rules (.cursor/rules)· 0% pass
No .cursor/rules/*.mdc or .cursorrules
Dependency manifest· 0% pass
No dependency manifest found
Reproducible dev env· 0% pass
No Makefile / devcontainer / Docker / equivalent found
GEMINI.md· 0% pass
No GEMINI.md at repo root
License file· 100% pass
License present
LICENSE
Linter / formatter config· 0% pass
No linter/formatter config found
.openhands/setup.sh· 0% pass
No .openhands/setup.sh
Pre-commit / git hooks· 0% pass
No pre-commit / husky / lefthook found
README· 100% pass
README detailed (1,173 characters)
README.md
Manageable size· 50% pass
3644 files — large
Test suite· 70% pass
Test files detected (examples/agents_sdk/tests/test_security_review_repository_labels.py)
examples/agents_sdk/tests/test_security_review_repository_labels.py
Type configuration· 0% pass
No type config found

How openai/openai-cookbook compares

vs leaderboard average
22.4 pts below
Average 66.8

Missing here, and how many repos have it

  • Dependency manifest · passed by 92% of leaderboard repos
  • Type configuration · passed by 68% of leaderboard repos
  • Linter / formatter config · passed by 65% of leaderboard repos

One fix for the most agents: Linter / formatter config would raise the score for all 9 agents, by up to 14.1 points.

Similar repos

The repos closest to it in overall score.

Same topics, any language

Repos tagged with the same GitHub topics, most shared first.

Add a badge to your README

Paste this at the top of the README. It shows the score, and links back to this page.

Agent friendly score for github/openai/openai-cookbook
[![Agent Friendly](https://agentfriendlycode.com/api/badge/github/openai/openai-cookbook.svg)](https://agentfriendlycode.com/repo/github/openai/openai-cookbook)

Check the score on every pull request

A GitHub Action posts one comment per pull request with how the score changed and why.