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.

A platform that lets you build agents to learn to play StarCraft: Brood War.

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Optimizing inference proxy for LLMs

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

This is the official implementation of Multi-Agent PPO (MAPPO).

Universal memory layer for AI Agents

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

一个适合学习、使用、自主扩展的RAG【检索增强生成】系统！可联网做AI搜索

[CVPR 2024] Code release for TransNeXt model

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKT…

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

a PyTorch re-implementation of ECCV 2022 paper based on Detectron2: k-means mask Transformer.

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

[NeurIPS 2021] You Only Look at One Sequence

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

LLM Analytics

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Code for "Hierarchical World Models as Visual Whole-Body Humanoid Controllers"

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

High throughput synchronous and asynchronous reinforcement learning

CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.

WarAgent: LLM-based Multi-Agent Simulation of World Wars

LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)