🦜🔗 The platform for reliable agents.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Fully local web research and report writing assistant

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!

A library for mechanistic interpretability of GPT-style language models

slime is an LLM post-training framework for RL Scaling.

A library for advanced large language model reasoning

τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem

Simulation code for paper "Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality"