Stars
OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.
We're rebuilding and open-sourcing the world’s software from scratch.
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
A lightweight and high-performance reverse proxy for NAT traversal, written in Rust. An alternative to frp and ngrok.
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
Open-source State-of-the-art TTS model which runs on a CPU 😻
LLM Architecture Gallery source data
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, Octane, SolidJS, Svelte, Angular, and Vue 2. Mermaid, KaTeX, streaming code blocks, SSR, and virtualized histories.
⚡ 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
A minimal docker baseimage to ease creation of X graphical application containers
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 to download audio/video from hundreds of sites
Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.
Official inference framework for 1-bit LLMs
The best native proxy client for iOS, iPadOS, macOS, and tvOS.