Agent Friendly Code
← back to leaderboard

serde-rs/serdeGitHub

https://github.com/serde-rs/serde
Stars:
10.6k
Default branch:
master
Last scored:
6h ago
Overall

Strengths

  • CI configuration
  • CONTRIBUTING guide
  • Dependency manifest
  • README
  • Manageable size

Gaps

  • AGENTS.md / CLAUDE.md
  • Reproducible dev env
  • License file
  • Linter / formatter config
  • Pre-commit / git hooks

Suggestions to improve for a specific model

  1. 1
    Test suite
    Add a tests/ (or test/, __tests__/, spec/) directory with runnable tests. Document how to run them in AGENTS.md.
    +11.5 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).
    +9.0 pts
  3. 3
    Reproducible dev env
    Add a Makefile or devcontainer or Dockerfile so the agent can set up the project in one command.
    +9.0 pts

Per-model scores

Claude Code
Weights AGENTS.md and tests heavily — Claude Code leans on an instructions file and a fast feedback loop.
44.7
Cursor
Weights type config and a detailed README highly — Cursor's inline edits benefit from static types and skim-readable docs.
54.9
Devin
Weights CI and reproducible envs highly — Devin runs in a sandboxed VM and needs end-to-end automation.
52.5
GPT-5 Codex
Balanced profile as a reference point.
52.1
Gemini CLI
Weights long-form README and strict type configs — Gemini's long context favors docs-heavy codebases that spell out contracts.
52.6
Aider
Weights tests and linter highest — Aider runs both per-edit as its feedback loop, so a green bar translates directly into successful commits.
42.4
OpenHands
Weights reproducible dev-env and CI highest — OpenHands operates from a sandboxed container, so a working Dockerfile / Makefile is near-mandatory.
53.5
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.
45.1

Alternatives

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

Signal breakdown

AGENTS.md / CLAUDE.md· 0% pass
No agent instructions file found
CI configuration· 100% pass
1 GitHub Actions workflow(s)
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
CONTRIBUTING.md
Dependency manifest· 100% pass
Manifest present
Cargo.toml
Reproducible dev env· 0% pass
No Makefile / devcontainer / Docker / equivalent found
License file· 0% pass
No LICENSE/COPYING file
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 (4357 chars)
README.md
Manageable size· 100% pass
380 files
Test suite· 0% pass
No test directory or test files found
Type configuration· 100% pass
Typed language (Rust/Go)

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/serde-rs/serde
[![Agent Friendly](https://agentfriendlycode.com/api/badge/github/serde-rs/serde.svg)](https://agentfriendlycode.com/repo/68)