Popular repositories Loading

1. Pev Pev Public

   Pev: a calibrated fast-decision model for personal agents — Pev-Bench benchmark, evaluation harness, LoRA on Qwen3.8-27B, tech report

   Python 1

2. cua-rsibench cua-rsibench Public

   Python

3. harbor harbor Public

   Forked from harbor-framework/harbor

   Framework for evaluating and improving agents

   Python

4. verl verl Public

   Forked from verl-project/verl

   verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

   Python

5. litellm litellm Public

   LiteLLM fork (upstream BerriAI/litellm), base v1.104.0

6. verl-recipe verl-recipe Public

   Forked from verl-project/verl-recipe

   A set of examples based on verl for end-to-end RL training recipes.

   Python