The official Python library for the OpenAI API

A lightweight, powerful framework for multi-agent workflows

Paper list of multi-agent reinforcement learning (MARL)

A collection of MCP servers.

Build effective agents using Model Context Protocol and simple workflow patterns

An open-source platform for Visual AI.

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"

Fully Open Framework for Democratized Multimodal Training

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation

OpenVLA: An open-source vision-language-action model for robotic manipulation.

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Build resilient language agents as graphs.

The absolute trainer to light up AI agents.

🦜🔗 The platform for reliable agents.

verl: Volcano Engine Reinforcement Learning for LLMs

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment

Witness the aha moment of VLM with less than $3.

A latent text-to-image diffusion model

"RAG-Anything: All-in-One RAG Framework"

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

LlamaIndex is the leading framework for building LLM-powered agents over your data.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

A fork to add multimodal model training to open-r1

Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).

Python toolkit for document information extraction using LMDX

A Bulletproof Way to Generate Structured JSON from Language Models

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!