Starred repositories
一个轻量级、支持全链路且易于二次开发的大模型应用项目(Large Model Data Assistant) 支持DeepSeek/Qwen3等大模型 基于 Dify 、LangChain/LangGraph、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目，采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 E…
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
A full featured, fast Command Line Argument Parser for Rust
OpenProject is the leading open source project management software.
☕️ HuLa Server, a high-performance instant messaging service built on Spring AI, SpringCloud Alibaba, SpringBoot3, Netty, MyBatis-Plus and RocketMQ(HuLa 服务端，基于Spring AI、SpringCloud Alibaba、SpringBo…
🍀 A cross-platform instant messaging desktop application with exceptional performance built on Rust + Vue3, compatible with Windows, macOS, Linux, Android, and iOS（一款基于Rust+Vue3极致性能的跨平台即时通讯桌面应用，兼容W…
Termora is a terminal emulator and SSH client for Windows, macOS and Linux.
Wan2.2-Animate 图片转视频，完美角色一致性，动画替换模型，本地部署教程
VUE开发的直播系统web版，接入腾讯云直播，腾讯im，dp播放器，游戏直播系统，高并发，低延迟，直播系统源码。
QiLuo is an enterprise-grade rapid development platform built on the Rust technology stack. It adopts modern architectural design and provides a complete backend management system solution.
A Rust + React fullstack admin template. Designed to be clean, modular, and developer-friendly.
Try-On Master-1: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-wise Diffusion Transformer Framework
Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.
Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)
If you live in the terminal, kitty is made for you! Cross-platform, fast, feature-rich, GPU based.
[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
Official Repository of "OmniTry: Virtual Try-On Anything without Masks"
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
Real time interactive streaming digital human
[ICCV 2025] AnyI2V: Animating Any Conditional Image with Motion Control Generation
GenHuman - 一个可直接部署商用变现的数字人项目 / GenHuman is an API based digital human product that includes web, app, mini program, backend management, and other ports for one click deployment and out of the box use.
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
Build resilient language agents as graphs.
🚀 The fast, Pythonic way to build MCP servers and clients
OmniGen2: Exploration to Advanced Multimodal Generation.
🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)