Popular repositories Loading

1. horizon horizon Public

   Capable, auditable coding that runs fully offline on a 16 GB machine. A verification-first layer (hard test execution, symbolic checking, agentic repair) that takes a local 7B to parity with its 67…

   Python 34

2. vexp-swe-bench vexp-swe-bench Public

   Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.

   Shell 11 3