Craft Anything: understand how any software works, and craft your own.

We're rebuilding and open-sourcing the world’s software from scratch.

[mirror] Go supplementary network libraries

[mirror] Go supplementary cryptography libraries

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io

Native A2UI Renderer for iOS/Android/HarmonyOS. High performance streaming Generative UI. Custom Components, Styles and more.

An agentic skills framework & software development methodology that works.

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

An open-source AI agent that brings the power of Gemini directly into your terminal.

High-performance proxy for MySQL and PostgreSQL

simple socket.io server for webrtc signaling

Pure Go implementation of the WebRTC API

A modern reverse proxy in Rust.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A library for building fast, reliable and evolvable network services.

阿里云数据库内核月报分类整理（定时更新） http://mysql.taobao.org/monthly/

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Inference code for CodeLlama models

Layer-Divider, an extension for stable-diffusion-webui using the segment-anything model (SAM)

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

迅排设计 - 图片编辑器、AI 在线海报设计，仿稿定设计，适用于多种场景：海报生成、电商产品图、文章长图、视频/公众号封面等。A beautiful online image designer, suitable for various scenarios like generate posters, making design easier!

an implementation of transformer, bert, gpt, and diffusion models for learning purposes

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning

Train LoRAs on Google Colab in one click: Illustrious/NoobAI, Anima and MOSS-Image, over kohya-ss/sd-scripts.

用 Express 和 Vue3 搭建的 ChatGPT 演示网页