AI 开源项目榜。

Multi Task Vision and Language

High-performance Vision library in Python. Scale your research, not boilerplate.

M. Beyeler (2017). Machine Learning for OpenCV: Intelligent image processing with Python. Packt Publishing Ltd., ISBN 978-178398028-4.

[ICLR 2026] FastVGGT: Fast Visual Geometry Transformer

:fire::fire: PyTorch implementation of "Progressive growing of GANs (PGGAN)" :fire::fire:

Open Robotics Automation Virtual Environment: An environment for testing, developing, and deploying robotics motion planning algorithms.

Emacs as your personal AI assistant. Use LLMs such as ChatGPT or LLaMA for text generation or DALL-E and Stable Diffusion for image generation. Also supports speech input / output.

Keras-based implementation of Relational Graph Convolutional Networks

Official Repository for MolmoAct2

Video Editor for AI agents, built on the belief that open source can beat commercial tools

A Kubernetes deployable instance of GroundX for document parsing, storage, and search.

Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.

A CLI for Kubeflow.

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)

🔥Manage Linux servers like Windows with a lightweight, secure, AI-powered SSH desktop.

Galaxea's open-source VLA repository

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.

Using Tree-of-Thought Prompting to boost ChatGPT's reasoning

The most easy-to-understand tutorial for using LoRA (Low-Rank Adaptation) within diffusers framework for AI Generation Researchers🔥

The World's Leading Cross Platform AI Engine for Edge Devices

[Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.

This is a implementation of the 3D FLAME model in PyTorch

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

An Omni Real-Time Assistant for Everyone

A Simulation Environment to train Robots in Large Realistic Interactive Scenes

Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.

🐈 A collection of LLM inference providers and models

:exclamation: uplift modeling in scikit-learn style in python :snake: