The Agent Index / Agent Frameworks / #79
OpenPipe/ART
by OpenPipe · Agent Frameworks · updated today
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
73
momentum
10,711
stars
983
forks
#79
rank
agentagentic-aigrpollmsloraqwenqwen3reinforcement-learningrl
View on GitHub →
More in Agent Frameworks
deepseek-harness
deepseek-ai
DeepSeek Harness: Everything is a Plugin.
ponytail
DietrichGebert
Makes your AI agent think like the laziest senior dev in the room. The best code is the co
langchain
langchain-ai
The agent engineering platform.
deer-flow
bytedance
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With t