Starred repositories
Code for the paper Hybrid Spectrogram and Waveform Source Separation
An open-source AI agent that brings the power of Gemini directly into your terminal.
Deezer source separation library including pretrained models.
Windows desktop front end for Spleeter - AI source separation
Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, Demucs, BS-RoFormer. Built with React and Django.
Browser-based visual editor for building WebGL, WebGPU, WebXR apps
A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous soci…
NekoBox for Android / sing-box / universal proxy toolchain for Android
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
不再维护，自寻替代品。 Qt based cross-platform GUI proxy configuration manager (backend: sing-box)
Use commands in English to control Blender with OpenAI's GPT-4
Blender addons to make the bridge between Blender and geographic data
📦 🚀 Blazing fast, simple and complete solution for micro frontends.
A feature-rich command-line audio/video downloader
是一款炫酷的任务定时器，采用 HTML、CSS 和 JavaScript 打造。它融合了科幻风格的霓虹星际背景和强大的任务管理功能，让用户可以轻松定时和播放音频任务。无论是开发者、爱好者，还是追求视觉震撼的用户，这款工具都将为你带来非凡体验！🌌
electron-progressbar provides an easy-to-use and highly customizable API to show and control progress bars on Electron applications.
GitLab CE Mirror | Please open new issues in our issue tracker on GitLab.com
Git with a cup of tea! Painless self-hosted all-in-one software development service, including Git hosting, code review, team collaboration, package registry and CI/CD
Git Source Code Mirror - This is a publish-only repository but pull requests can be turned into patches to the mailing list via GitGitGadget (https://gitgitgadget.github.io/). Please follow Documen…
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model