Agent Friendly Code
← back to leaderboard

symfony/aiGitHub

https://github.com/symfony/ai
Stars:
1.1k
Default branch:
main
Last scored:
4h ago
Overall

Strengths

  • AGENTS.md / CLAUDE.md
  • CI configuration
  • CONTRIBUTING guide
  • Dependency manifest
  • License file

Gaps

  • Reproducible dev env
  • Linter / formatter config
  • Pre-commit / git hooks
  • Test suite
  • Type configuration

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.
    +11.6 pts
  2. 2
    Test suite
    Add a tests/ (or test/, __tests__/, spec/) directory with runnable tests. Document how to run them in AGENTS.md.
    +10.5 pts
  3. 3
    Linter / formatter config
    Configure a linter/formatter (ESLint+Prettier, Biome, Ruff, rustfmt+clippy, golangci-lint) and commit the config.
    +7.0 pts

Per-model scores

Claude Code
Weights AGENTS.md and tests heavily — Claude Code leans on an instructions file and a fast feedback loop.
50.7
Cursor
Weights type config and a detailed README highly — Cursor's inline edits benefit from static types and skim-readable docs.
50.7
Devin
Weights CI and reproducible envs highly — Devin runs in a sandboxed VM and needs end-to-end automation.
53.8
GPT-5 Codex
Balanced profile as a reference point.
52.7
Gemini CLI
Weights long-form README and strict type configs — Gemini's long context favors docs-heavy codebases that spell out contracts.
50.6
Aider
Weights tests and linter highest — Aider runs both per-edit as its feedback loop, so a green bar translates directly into successful commits.
47.0
OpenHands
Weights reproducible dev-env and CI highest — OpenHands operates from a sandboxed container, so a working Dockerfile / Makefile is near-mandatory.
54.1
Pi
Weights AGENTS.md heavily and rewards a fast test/lint loop — Pi's minimal terminal harness reads AGENTS.md explicitly and defers sandboxing to user-installed extensions.
50.0

Alternatives

Same-language repos scored for OpenHands. Heuristic v1 (same language + same host); cross-language matches are refined in v0.5.0.

Signal breakdown

AGENTS.md / CLAUDE.md· 100% pass
Substantive (5598 chars)
AGENTS.md
CI configuration· 100% pass
8 GitHub Actions workflow(s)
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
CONTRIBUTING.md
Dependency manifest· 100% pass
Manifest present
composer.json
Reproducible dev env· 0% pass
No Makefile / devcontainer / Docker / equivalent found
License file· 100% pass
License present
LICENSE
Linter / formatter config· 0% pass
No linter/formatter config found
Pre-commit / git hooks· 0% pass
No pre-commit / husky / lefthook found
README· 100% pass
README detailed (1891 chars)
README.md
Manageable size· 50% pass
2679 files — large
Test suite· 0% pass
No test directory or test files found
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/symfony/ai
[![Agent Friendly](https://agentfriendlycode.com/api/badge/github/symfony/ai.svg)](https://agentfriendlycode.com/repo/155)