Popular repositories Loading

1. ART ART Public

   Forked from OpenPipe/ART

   Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

   Python

2. graph_rag graph_rag Public template

   Forked from nemegrod/graph_RAG

   Simple Graph RAG demo based on Jaguar data

   Python

3. Triage Triage Public

   Python