A modular full-stack reinforcement learning library for training and fine-tuning LLMs with advanced agent capabilities
Async reinforcement learning framework for training 1T+ parameter agentic AI models at scale
RL environments and evaluation framework for training and testing LLMs
Open-source AI agent framework that achieves any idea without invite codes
Fine-tune 600+ LLMs and 300+ MLLMs with PEFT, full-parameter training, and advanced RL algorithms.
Evaluate and train AI agents in stateful environments at scale
Train multi-step AI agents with reinforcement learning using GRPO
AI-native modular infrastructure for quantitative trading with LLM and agentic AI support
Open-source autonomous driving simulator powered by Unreal Engine for AI research
Agentic execution environments for RL training with simple Gymnasium-style APIs
