llvm/llvm-project

At a glance

Rank

#299 of 401

Checks passed

7 of 17

Full list below

Best set up for

Aider

Score 61.7

Needs most work for

OpenHands

Biggest fix: Reproducible dev env (+10.0 pts)

What to fix first

Showing fixes for Claude Code

1. 1
   AGENTS.md / CLAUDE.md

   Add an AGENTS.md covering project goals, layout, setup commands, and conventions. Aim for 800+ chars of real guidance (not boilerplate).
   +13.2 pts
2. 2
   Reproducible dev env

   Add a Makefile or devcontainer or Dockerfile so the agent can set up the project in one command.
   +11.8 pts
3. 3
   Pre-commit / git hooks

   Set up pre-commit (.pre-commit-config.yaml), husky, or lefthook to run format+lint on every commit.
   +5.3 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 →

Does llvm/llvm-project 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

✗None at the root (no AGENTS.md, CLAUDE.md, AGENT.md, .claude/CLAUDE.md or .claude/AGENTS.md)

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 →

# AGENTS.md

Guidance for AI coding agents working in llvm/llvm-project. The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Written mainly in LLVM.

## Where things are

- Dependencies are declared in `pyproject.toml`.
- Test files are spread through the tree, e.g. `clang/utils/ABITest/Makefile.test.common`.
- Lint and format rules are configured in `.clang-format`.
- Type checking is configured in `pyproject.toml`.
- CI is defined in `.github/workflows`; read it for the exact install, lint and test steps.
- Follow the conventions in `CONTRIBUTING.md`.

## Commands

<!-- Fill in the exact commands CI runs. -->
- Install: TODO
- Test: TODO
- Lint: TODO

How llvm/llvm-project compares

vs leaderboard average

7.5 pts below

Average 66.8

One fix for the most agents: AGENTS.md / CLAUDE.md would raise the score for all 9 agents, by up to 13.3 points.

Similar repos

The repos closest to it in overall score.

• square/leakcanary59.5
  Kotlin · 30k ★
• fmtlib/fmt59.4
  C++ · 25.9k ★
• sidekiq/sidekiq59.4
  Ruby · 13.6k ★
• dagger/dagger59.3
  Go · 16.6k ★
• alacritty/alacritty59.2
  Rust · 66.1k ★
• charmbracelet/bubbletea59.2
  Go · 45.6k ★