facebookresearch/faissGitHub
https://github.com/facebookresearch/faiss- Stars:
- 39.8k
- Default branch:
- main
- Last scored:
- 4h ago
45.3
Overall
Strengths
- CI configuration
- CONTRIBUTING guide
- License file
- README
- Test suite
Gaps
- AGENTS.md / CLAUDE.md
- Dependency manifest
- Reproducible dev env
- Linter / formatter config
- Pre-commit / git hooks
Suggestions to improve for a specific model
- 1AGENTS.md / CLAUDE.mdAdd an AGENTS.md covering project goals, layout, setup commands, and conventions. Aim for 800+ chars of real guidance (not boilerplate).+9.6 pts
- 2Dependency manifestCommit a proper manifest (package.json, pyproject.toml, Cargo.toml, go.mod, etc.) plus a lockfile.+9.6 pts
- 3Reproducible dev envAdd a Makefile or devcontainer or Dockerfile so the agent can set up the project in one command.+9.6 pts
Per-model scores
Claude Code
Weights AGENTS.md and tests heavily — Claude Code leans on an instructions file and a fast feedback loop.
Cursor
Weights type config and a detailed README highly — Cursor's inline edits benefit from static types and skim-readable docs.
Devin
Weights CI and reproducible envs highly — Devin runs in a sandboxed VM and needs end-to-end automation.
GPT-5 Codex
Balanced profile as a reference point.
Signal breakdown
AGENTS.md / CLAUDE.md· 0% pass
No agent instructions file found
CI configuration· 100% pass
9 GitHub Actions workflow(s)
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
CONTRIBUTING.md
Dependency manifest· 0% pass
No dependency manifest found
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 (6363 chars)
README.md
Manageable size· 80% pass
939 files
Test suite· 100% pass
Found /tests
tests
Type configuration· 0% pass
No type config found