Agent Friendly Code
← back to leaderboard

ml-explore/mlxGitHub

https://github.com/ml-explore/mlx
Stars:
26k
Default branch:
main
Last scored:
1d ago
Overall

Strengths

  • CI configuration
  • CONTRIBUTING guide
  • Dependency manifest
  • License file
  • Linter / formatter config

Gaps

  • AGENTS.md / CLAUDE.md
  • .aider.conf.yml
  • Cursor rules (.cursor/rules)
  • Reproducible dev env
  • GEMINI.md

Suggestions to improve for a specific model

  1. 1
    Reproducible dev env
    Add a Makefile or devcontainer or Dockerfile so the agent can set up the project in one command.
    +13.0 pts
  2. 2
    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).
    +7.8 pts
  3. 3
    Type configuration
    Add a type config (tsconfig.json for JS/TS, mypy.ini or pyrightconfig.json for Python). Rust/Go/JVM/Scala/Swift/C#/OCaml/Haskell/Zig are typed by default.
    +6.5 pts

Per-model scores

Devin
Operates from a sandboxed Ubuntu VM and runs an 8-step machine setup (deps, secrets, language versions, lint/test commands) per Cognition's repo-setup docs. CI config files alone aren't what the docs ask for — a runnable dev environment is.
71.2
GPT-5 Codex
Reads AGENTS.md before doing any work per OpenAI's Codex docs — the strictest AGENTS.md adherent of any agent here. Hierarchical (per-directory) AGENTS.md and AGENTS.override.md are first-class.
68.0
Pi
Minimal terminal coding harness. Loads `AGENTS.md` (or `CLAUDE.md`) at startup — global, parent dirs, then cwd — per the Pi coding-agent README. Sandboxing is deferred to user-installed extensions.
67.6
OpenHands
Runs in a sandboxed container and executes `.openhands/setup.sh` at session start per OpenHands' repo-customization docs. Root AGENTS.md is now the preferred always-on instruction surface (microagents are deprecated in favor of it).
67.3
Claude Code
Loads CLAUDE.md at the start of every conversation per Anthropic's memory docs, so AGENTS.md / CLAUDE.md and a fast test loop carry the most weight.
65.8
Aider
Auto-lints on every edit by default; runs the configured test command after edits when `--test-cmd` is set (per Aider's lint/test docs). A green linter and a declared test command translate directly into successful commits.
63.8
Gemini CLI
Reads hierarchical `GEMINI.md` (global → workspace → component-level) at every prompt per Gemini CLI's docs. The long-context advantage favors repos that split context per directory rather than docs-heavy in general.
61.4
Cursor
Per Cursor's Rules docs, reads `.cursor/rules/*.mdc` and AGENTS.md as the canonical repo-side input. Type config and a clean README still aid the codebase index but aren't the docs-cited signal.
59.3

Alternatives

Same-language repos scored for Devin. Heuristic v1 (same language + same host); cross-language matches are refined in v0.6.0.

Signal breakdown

AGENTS.md / CLAUDE.md· 0% pass
No agent instructions file found
.aider.conf.yml· 0% pass
No .aider.conf.yml at repo root
CI configuration· 100% pass
4 GitHub Actions workflow(s)
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
CONTRIBUTING.md
Cursor rules (.cursor/rules)· 0% pass
No .cursor/rules/*.mdc or .cursorrules
Dependency manifest· 100% pass
Manifest present
pyproject.toml
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· 100% pass
Config detected
.clang-format
.openhands/setup.sh· 0% pass
No .openhands/setup.sh
Pre-commit / git hooks· 100% pass
Hook framework configured
.pre-commit-config.yaml
README· 100% pass
README detailed (4596 chars)
README.md
Manageable size· 80% pass
864 files
Test suite· 100% pass
Found /tests
tests
Type configuration· 0% pass
No type config found

Embed this badge

Drop the snippet below into the top of this repo's README so visitors can see its agent-friendliness at a glance — clicks land back here.

Agent friendly score for github/ml-explore/mlx
[![Agent Friendly](https://agentfriendlycode.com/api/badge/github/ml-explore/mlx.svg)](https://agentfriendlycode.com/repo/1574)

Catch score regressions on every PR

Drop the workflow below into your repo and the action will post (or edit) a single comment on each PR with the score delta and the per-signal changes — runs entirely inside your CI, no third-party server in the loop.

# .github/workflows/agent-friendly.yml
name: Agent-friendly score diff

on:
  pull_request:
    branches: [main]

permissions:
  contents: read
  pull-requests: write

jobs:
  score-diff:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
      - uses: hsnice16/agent-friendly-action@v0
        with:
          agents-badge-token: ${{ secrets.AGENTS_BADGE_TOKEN }}

Set AGENTS_BADGE_TOKENin the repo's secrets to enable the comment; leave it unset and the action exits silently. Where do I add it?