SWE-bench for your codebase — mine your merged PRs into local, contamination-free coding-agent benchmarks. Adapters: claude-code, aider (Opus 4.7 / GPT-5.5 / Sonnet 4.6 / Gemini 3.1 Pro).
Python MIT 309 KB Created Apr 29, 2026
Stars 30 Forks 0 Watchers 0 Open issues 1 Open PRs 0