Popular repositories Loading

1. terminal-bench terminal-bench Public

   A benchmark for LLMs on complicated tasks in the terminal

   Python 1.2k 439

2. harbor harbor Public

   Harbor is a framework for running agent evaluations and creating and using RL environments.

   Python 228 143

3. terminal-bench-2 terminal-bench-2 Public

   Shell 43 16

4. terminal-bench-leaderboard terminal-bench-leaderboard Public

   A home for run logs for terminal-bench

   Shell 12 22

5. terminal-bench-datasets terminal-bench-datasets Public

   Python 8 33

6. harbor-datasets harbor-datasets Public

   HTML 5 31