INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document intelligence.

Phonics Game & Posters

GEO-first SEO skill for Claude Code. Comprehensive AI search optimization for any website — citability scoring, AI crawler analysis, brand authority, schema markup, platform-specific optimization, …

Gamified phonetics learning app with streaks, levels, and real-time mouth tracking

Interactive phonics learning app for ages 9-15 with games, AI features, and gamification. Built with Next.js, Firebase, and Gemini AI.

Tiny Vue component, that helps to create Quill v2 based WYSIWYG editors https://vue-quilly.vercel.app/

真正从基础开始学英语 - 自然拼读练习应用

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.

Voice activity detector (VAD) for the browser with a simple API

On-device voice activity detection (VAD) powered by deep learning

Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.

使用Github Action将国外的Docker镜像转存到阿里云私有仓库，供国内服务器使用，免费易用

WebAssembly build of RNNoise

✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器：支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性

A Cloudflare-based online text/large file sharing platform that supports multiple syntax Markdown rendering, self-destructing messages, S3 aggregated storage, password protection, and more. It can …

A small macOS menu bar-residing screen and system audio recorder which uses the ScreenCaptureKit API introduced in Ventura

[ICLR 2025 Oral] TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

一键将音视频转化为小红书/公众号/知识笔记/思维导图/视频字幕等各种风格的文档。

Build mindmaps with plain text

A lightweight screen recorder based on ScreenCapture Kit for macOS / 基于 ScreenCapture Kit 的轻量化多功能 macOS 录屏工具

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

🛡️ 抖音 X-Bogus，msToken 和 ttwid 获取

支持视频号、小程序、抖音、快手、小红书、直播流、酷狗、QQ音乐等常见网络资源!

ElectronCaptureKit is a powerful and flexible Electron-based library for macOS screen recording, leveraging the advanced capabilities of ScreenCaptureKit.

Process audio/video data in the browser using WebCodecs. 基于 WebCodecs 在浏览器中处理音视频数据。

Instant voice cloning by MyShell.

Brand new TTS solution