OpenPipe/ART

open-source RL framework for training LLM agents on real-world tasks

View on index · View in 3D Map

Related repos

• Build and train custom RL environments for LLM agents with modular tools and easy integration
• Discovers tools for autonomous agents
• Open cookbook for building top-tier code LLMs with complete training data and reproducible pipeline
• open format for guiding AI coding agents with project instructions
• Framework for building autonomous agents with open-source models
• Task engine for AI agents
• open-source reinforcement learning for language models
• multi-agent LLM app framework with modular tools and real-time control
• framework for building LLM and RAG apps with pipelines
• open-source coding assistant with agentic features, supports Claude, GPT-4o, Gemini, and local LLMs