Lightweight Python desktop app for Windows that improves upon Windows Voice Typing (Win+H) by offering superior transcription accuracy while maintaining a simple, intuitive interface.

Manage multiple AI terminal agents like Claude Code, Aider, Codex, OpenCode, and Amp.

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

The simplest way to learn and explore horse racing data

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

A Python frontend and library for ComfyUI

Enjoy the magic of Diffusion models!

aka: (Why Isn't There) A Poignant Guide to Vibing w/ AI

A powerful set of tools for ComfyUI

一个为 ComfyUI 开发的自定义节点实用工具包 A custom node utility package developed for ComfyUI

Civitai model downloader for ComfyUI

Improve the interactive experience of using ComfyUI, such as making the loading of ComfyUI models more intuitive and making it easier to create model thumbnails

A super simple Claude Code session browser

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Fork of the Triton language and compiler for Windows support and easy installation

A TTS model capable of generating ultra-realistic dialogue in one pass.

🙌 OpenHands: Code Less, Make More

MAGI-1: Autoregressive Video Generation at Scale

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

A C++17 library to access the entire OpenAI API.

Integration for the OpenAI Api in Unreal Engine

🚀 Fast and simple Node.js version manager, built in Rust

A command-line interface for interacting with MCP (Model Context Protocol) servers using both stdio and HTTP transport.

An Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. Supports Claude Desktop App, Windsurf & Cursor, also includes OpenAI's GPT 5, Deepseek V3.1, Claude Sonnet 4 APIs and Grok 4, with pla…

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

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.