Public repository for Agent Skills

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

🔥[MobiCom'25 Poster] AFL-Lib: An Asynchronous Federated Learning Library and Benchmark

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills"

GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

世界模型（World Model）调研项目：收集李飞飞、LeCun和Meta的最新世界模型开源代码和研究资料

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

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

[EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Fully open reproduction of DeepSeek-R1

复现大模型相关算法及一些学习记录

OpenHuFu is an open-sourced data federation system to support collaborative queries over multi databases with security guarantee.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

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

Official pytorch Implementation of Relational Knowledge Distillation, CVPR 2019

PyTorch implementation of JEI-DNN (ICLR 2024)

Boosted Dynamic Neural Networks, AAAI 2023

Code and pretrained models for paper: Data-Free Adversarial Distillation

Code and data accompanying the FedGen paper

EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).