Stars
🤗 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.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
SGLang is a high-performance serving framework for large language models and multimodal models.
verl: Volcano Engine Reinforcement Learning for LLMs
The absolute trainer to light up AI agents.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
slime is an LLM post-training framework for RL Scaling.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
A unified, comprehensive and efficient recommendation library
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / U…
faster_whisper GUI with PySide6
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
[UNMAINTAINED] A reverse engineered Python API wrapper for Quora's Poe, which provides free access to ChatGPT, GPT-4, and Claude.
PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
A project to improve skills of large language models
Science-Star: A Platform for Building, Extending, and Experimenting with Scientific Agents.
AndroidWorld is an environment and benchmark for autonomous agents
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Training VLM agents with multi-turn reinforcement learning
MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.
Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.