Popular repositories Loading

1. pybench pybench Public

   Discover benchmark functions, run them across many seeds, and statistically detect regressions against a saved baseline.

   Python 3

2. spec_driven_xpbd spec_driven_xpbd Public

   A method for steering coding agents on underspecified tasks, validated by a physics engine in a domain I knew nothing about.

   Python 2

3. chessop chessop Public

   Grind chess openings against the moves people at your rating really play, drawn from Lichess games. Free, no sign-up.

   Python