Stars
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
The design language that makes your AI harness better at design.
An open source collection of animated, interactive & fully customizable React components for building memorable websites.
🎥 Make videos programmatically with React
A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.
React components for Cloudscape Design System
🌥️ 速语API | OpenAI官方中转服务 🌥️ https://suyu.io 🔥 官方价格1:1 🔥 1元=1$ Token 🔥 高性价比 稳定快速！🔥 | 全球直连 | 无需代理 | 企业级稳定 | gpt3.5 | gpt4 | gpt4o | gpt4o-mini | 207+模型支持
An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具，努力让Codex变得更好用更舒服
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Turn your Notion workspace into a fast, customizable website. Built with Next.js + Notion API, with multi-platform deployment and no self-hosted server required.
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Red Ink - A one-stop Xiaohongshu image-and-text generator based on the 🍌Nano Banana Pro🍌, "One Sentence, One Image: Generate Xiaohongshu Text and Images."
Open-source. Focused on simple, beautiful, and smooth experience.
分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.
KeyCastr, an open-source keystroke visualizer
🎸 每天定时推送波奇酱（后藤一里）美图的 Telegram 机器人。基于 GitHub Actions + Python 实现，零成本自动化运行。🎸 A Telegram bot that sends daily "Bocchi the Rock!" images. 每日波奇酱自动推送机器人
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
Robust Speech Recognition via Large-Scale Weak Supervision
Single picture, one click, video face swap! Use Colab scripts, no need to burn the graphics card, no need to go to the sauna!