ray-project/ray

GitHub
https://github.com/ray-project/ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Stars:
44.2k
Language:
Python
Default branch:
master
Last scored:
Overall

At a glance

Rank
#130 of 401
Top 32% · #29 of 56 Python repos
Checks passed
9 of 17
Full list below
Best set up for
Claude Code
Score 78.9
Needs most work for
OpenHands
Biggest fix: Reproducible dev env (+10.0 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
    Manageable size
    If possible, split into smaller modules or carve out a focused entry path. Document where to start in AGENTS.md.
    +5.3 pts
  3. 3
    Test suite
    Add a tests/ (or test/, __tests__/, spec/) directory with runnable tests. Document how to run them in AGENTS.md.
    +3.9 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
#136 of 401
78.9
  • ✓AGENTS.md / CLAUDE.md
  • ~Test suite
  • ✗Reproducible dev env
Codex
#124 of 401
78.0
  • ✓AGENTS.md / CLAUDE.md
  • ✓README
  • ~Test suite
Pi
#118 of 401
77.7
  • ✓AGENTS.md / CLAUDE.md
  • ~Test suite
  • ✓Linter / formatter config
Kimi Code CLI
#121 of 401
77.5
  • ✓AGENTS.md / CLAUDE.md
  • ~Test suite
  • ✓Dependency manifest
Cursor
#115 of 401
72.1
  • ✗Cursor rules (.cursor/rules)
  • ✓README
  • ✓Type configuration
Devin
#177 of 401
70.8
  • ✗Reproducible dev env
  • ✓Dependency manifest
  • ~Test suite
Aider
#147 of 401
70.1
  • ✗.aider.conf.yml
  • ✓Linter / formatter config
  • ~Test suite
Gemini CLI
#129 of 401
69.9
  • ✗GEMINI.md
  • ✓README
  • ~Test suite
OpenHands
#168 of 401
67.7
  • ✓CI configuration
  • ✓Dependency manifest
  • ✗Reproducible dev env

Does ray-project/ray 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) · 4,319 characters
Agent-specific files
None: no GEMINI.md, .cursor/rules, .openhands/setup.sh, .aider.conf.yml or .agents/skills
Repos that have one
29 of 56 Python repos · 221 of 401 repos on the leaderboard · See examples →

All 17 checks · 9 passed

No .agents/skills/<name>/SKILL.md
Substantive (4,319 characters)
.aider.conf.yml· 0% pass
No .aider.conf.yml at repo root
CI configuration· 100% pass
5 GitHub Actions workflows
CONTRIBUTING guide· 100% pass
Guide present
No .cursor/rules/*.mdc or .cursorrules
Manifest present
No Makefile / devcontainer / Docker / equivalent found
GEMINI.md· 0% pass
No GEMINI.md at repo root
License file· 100% pass
License present
Config detected
No .openhands/setup.sh
Hook framework configured
README· 100% pass
README detailed (5,553 characters)
Manageable size· 20% pass
10000+ files — very large
Test suite· 70% pass
Test files detected (.buildkite/always.rules.test.txt)
Type configuration· 100% pass
Configured in pyproject.toml

How ray-project/ray compares

vs leaderboard average
6.8 pts above
Average 66.8
vs Python average
2.6 pts above
Average 71.0
Stars among Python repos
#32 of 56

Missing here, and how many repos have it

  • Reproducible dev env · passed by 22% of leaderboard repos, 29% of Python repos
  • Skills (.agents/skills) · passed by 17% of leaderboard repos, 20% of Python repos
  • Cursor rules (.cursor/rules) · passed by 4% of leaderboard repos, 7% of Python repos

Passes checks most repos miss

  • Pre-commit / git hooks · only 29% of repos pass it

One fix for the most agents: Reproducible dev env would raise the score for all 9 agents, by up to 11.9 points.

Similar repos

Same language and host as this repo, closest in overall score.

All Python repos →

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/ray-project/ray
[![Agent Friendly](https://agentfriendlycode.com/api/badge/github/ray-project/ray.svg)](https://agentfriendlycode.com/repo/github/ray-project/ray)

Check the score on every pull request

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