AI 开源项目榜。
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
AI-Driven Scientific, Algorithmic, and Systems Discovery
13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents.
A GPT agent framework for invoking APIs
[ICRA2023] Implementation of Visual Language Maps for Robot Navigation
Laas: 3D world built by Claude Fable 5 to test its capabilities using three.js
Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)
WhatsApp Chatbot using Gemini + WasenderAPI
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code
Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
Unofficial agent skills + reference guide that teach AI coding assistants to write Rails the 37signals way — extracted from Fizzy, Campfire, and DHH's code reviews
The web scraper that's nearly impossible to block - now called @ulixee/hero
yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.
Drop-in AGENTS.md that makes every coding agent behave like a senior engineer instead of an eager intern. Kills sycophancy, stops drive-by refactors, forces verification loops. Synthesizes Karpathy's four principles and Boris Cherny's Claude Code workflow. Works with Claude Code, Codex, Gemini CLI, Cursor, and the open standard.
Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container deployment method. The platform supports container monitoring and MCP service token verification, solving security risks and enabling rapid deployment of MCP services. It uses SSE, STDIO, and STREAMABLEHTTP access protocols to deploy MCP。
Local voice AI powered by llama-cpp, Kokoro, Nemotron STT, and LiveKit.
State-of-the-art transformers for Ruby
Anki Cozmo Python SDK
GenZ-ICP: SOTA robust LiDAR odometry (IEEE RA-L 2025)
Texas holdem OpenAi gym poker environment with reinforcement learning based on keras-rl. Includes virtual rendering and montecarlo for equity calculation.
Inference Code for Polygon-RNN++ (CVPR 2018)
An Open-Source Library for Training Binarized Neural Networks
Hashbrown is a framework for building agents that run the browser. Built for Angular and React.
A C++ based, lightweight music and noise remover for YouTube and other internet media, using DeepFilterNet for audio enhancement.
A curated list of awesome exploration RL resources (continually updated)
A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning
Point Transformers
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing