AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Stable Diffusion web UI

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

The best ChatGPT that $100 can buy.

🚀🚀 「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!

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Code and documentation to train Stanford's Alpaca models, and generate the data.

The official Meta Llama 3 GitHub site

A generative world for general-purpose robotics & embodied AI learning.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Mamba SSM architecture

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Wan: Open and Advanced Large-Scale Video Generative Models

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Nano vLLM

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

DUSt3R: Geometric 3D Vision Made Easy

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

Unified framework for robot learning built on NVIDIA Isaac Sim

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

A modular high-level library to train embodied AI agents across a variety of tasks and environments.