Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

DS Input — an LLM whole-sentence pinyin input method (macOS + Windows): toneless pinyin → Chinese inline, no candidate window. Rust core (C ABI) + thin native frontends.

An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

State-of-the-art TTS model under 25MB 😻

LLM Architecture Gallery source data

去中心化代理和聊天协议

A calm, CLI-native way to semantically grep everything, like code, images, pdfs and more.

Multi-framework streaming Markdown renderers for AI apps: Vue/Nuxt, React/Next.js, Svelte, and Angular, with Mermaid, KaTeX, Shiki, Monaco, safe HTML, and low-jitter updates.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

An iOS OCR Server Using Apple’s Vision Framework

Ultra-lightweight AI Agent

A minimal docker baseimage to ease creation of X graphical application containers

Docker container for Firefox

Glamourous agentic coding for all 💘

Claude code proxy, friendly view request log, enhance request stability

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Desktop App for downloading Videos and Audios from hundreds of sites

Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.

web ebook reader

Official inference framework for 1-bit LLMs

The best native proxy client for iOS, iPadOS, macOS, and tvOS.

📂 Web File Browser

A high-quality PDF to Markdown tool based on large language model visual recognition. 一款基于大模型视觉识别的高质量PDF转Markdown工具

可以实现按下 Option 按钮开始录制，抬起按钮就结束录制，并调用 Groq Whisper Large V3 Turbo 模型进行转译，由于 Groq 的速度非常快，所以大部分的语音输入都可以在 1-2s 内反馈。并且得益于 whisper 的强大能力，转译效果非常不错。

TTS with kokoro and onnx runtime

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…