Chester Liu

snip. CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

qinglong-mcp-server. TypeScript

microclaw. 🦀An agentic AI assistant that lives in your chats, inspired by nanoclaw and incorporating some of its design ideas. Built with Rust 🦀

headroom. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

verdaccio. A lightweight Node.js private proxy registry

hermes-webui. Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

pocket-tts. A TTS that fits in your CPU (and pocket)

tokscale. 🛰️ A CLI tool for tracking token usage from OpenCode, Claude Code, 🦞OpenClaw, Pi, Codex, Gemini, Cursor, AmpCode, Factory Droid, Kimi, and more! • 🏅Global Leaderboard + 2D/3D Contributions Graph

rtk. CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

nanoclaw. A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

ClawRouter. The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.

opentui. OpenTUI is a library for building terminal user interfaces (TUIs)

hermes-agent. The agent that grows with you

golembot. Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

nanobot. Lightweight, open-source AI agent for your tools, chats, and workflows.

zeroclaw-helm. A Helm Chart for ZeroClaw to deploy on Kubernetes

opencode. The open source coding agent.

WinMosh. Mosh for Windows, written in Rust

loong. Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉

picoclaw. Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

cline. Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Ninty-Launcher. Nintendo Switch-styled launcher.

readest. Readest is a modern, feature-rich ebook reader designed for avid readers offering seamless cross-platform access, powerful tools, and an intuitive interface to elevate your reading experience.

open-r1. Fully open reproduction of DeepSeek-R1

ARC-AGI. The Abstraction and Reasoning Corpus

DeepSeek-R1.

DeepSeek-LLM. DeepSeek LLM: Let there be answers

Ext4Fsd. Ext4 file system driver for Windows

AnimatedCollectionViewLayout. A UICollectionViewLayout subclass that adds custom transitions/animations to the UICollectionView without effecting your existing code.

sitefetch. Fetch an entire site and save it as a text file (to be used with AI models).

AMDVLK. AMD Open Source Driver For Vulkan

all-ways-egpu. Configure eGPU as primary under Linux Wayland desktops

UFO. UFO³: Weaving the Digital Agent Galaxy

dnSpy. Unofficial revival of the well known .NET debugger and assembly editor, dnSpy

tabby. Self-hosted AI coding assistant

MiniMax-01. The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention

keda. KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes

spiffe. The SPIFFE Project

Roo-Code. Roo Code gives you a whole dev team of AI agents in your code editor.

ghz. Simple gRPC benchmarking and load testing tool

gamescope. SteamOS session compositing window manager

bazzite. Bazzite makes gaming and everyday use smoother and simpler across desktop PCs, handhelds, tablets, and home theater PCs.

cbindgen. A project for generating C bindings from Rust code

DeepSeek-V3. Python

ImageViewer.swift. An easy to use Image Viewer that is inspired by Facebook

storm. An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

FairEmail. Fully featured, open source, privacy friendly email app for Android

clay. High performance UI layout library in C.

Lightbox. :milky_way: A convenient and easy to use image viewer for your iOS app

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Cognitive-Speech-TTS. Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

markitdown. Python tool for converting files and office documents to Markdown.

ZhiLight. A highly optimized LLM inference acceleration engine for Llama and its variants.

ha_xiaomi_home. Xiaomi Home Integration for Home Assistant

APlayer. Android Music Player

turso. Turso is an in-process SQL database, compatible with SQLite.

fluent-bit. Fast and Lightweight Logs, Metrics and Traces processor for Linux, BSD, OSX and Windows

kiota. OpenAPI based HTTP Client code generator

mise. dev tools, env vars, task runner

greenlight. Greenlight is an open-source client for xCloud and Xbox home streaming made in Typescript.

stdexec. `std::execution`, the standard C++ framework for asynchronous and parallel programming.

one-api. LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

sccache. Sccache is a ccache-like tool. It is used as a compiler wrapper and avoids compilation when possible. Sccache has the capability to utilize caching in remote storage environments, including various cloud storage options, or alternatively, in local storage.

listmonk. High performance, self-hosted, newsletter and mailing list manager with a modern dashboard. Single binary app.

cali. AI agent for building React Native apps

VALL-E-X. An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

promptic. 90% of what you need for LLM app development. Nothing you don't.

WinDepends. Windows Dependencies

minbpe. Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

LiteRT. LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

AlertKit. Native alert from Apple Music & Feedback. Contains Done, Heart & Message and other presets.

lite-xl. A lightweight text editor written in Lua

plcrashreporter. Reliable, open-source crash reporting for iOS, macOS and tvOS

lmql. A language for constraint-guided and efficient LLM programming.

llguidance. Super-fast Structured Outputs

logits-processor-zoo. A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

katana. A next-generation crawling and spidering framework.

openwrt. This repository is a mirror of https://git.openwrt.org/openwrt/openwrt.git It is for reference only and is not active for check-ins. We will continue to accept Pull Requests here. They will be merged via staging trees then into openwrt.git.

ai-dev-gallery. An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.

doxygen-action. GitHub Action for generating Doxygen documentation for your projects.

grammers. (tele)gramme.rs - use Telegram's API from Rust

mind-map. SimpleMindMap（思绪思维导图）：一个强大的思维导图。A powerful mind map.

dotnet-repl. A polyglot REPL built on .NET Interactive

crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Qwen3-Coder. Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

windows. Windows inside a Docker container.

corrosion. Marrying Rust and CMake - Easy Rust and C/C++ Integration!

anki. Anki is a smart spaced repetition flashcard program

docling. Get your documents ready for gen AI

swift-markdown. A Swift package for parsing, building, editing, and analyzing Markdown documents.

CopilotForXcode. AI coding assistant for Xcode

OLMo. Modeling, training, eval, and inference code for OLMo

beancount. Beancount: Double-Entry Accounting from Text Files.

android. Bitwarden mobile apps (Password Manager and Authenticator) for Android.

VideoLingo. Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

BitNet. Official inference framework for 1-bit LLMs

E2B. Open-source, secure environment with real-world tools for enterprise-grade agents.

guidance. A guidance language for controlling large language models.

ell. A language model programming library.

mi-gpt. 🏠 将小爱音箱接入 ChatGPT 和豆包，改造成你的专属语音助手。

open-notebooklm. Convert any PDF into a podcast episode!

Mist. A Mac utility that automatically downloads macOS Firmwares / Installers.

TranslateYou. Privacy focused translator app built with MD3

ClockYou. Privacy focused clock app built with MD3

86Box. Emulator of x86-based machines.

chat-macOS. Making the community's best AI chat models available to everyone.

aural-player. (Archived) An audio file player for macOS, inspired by Winamp.

OpenCore-Install-Guide. Repo for the OpenCore Install Guide

Loop. Window management made elegant.

strongarm. Mach-O analysis library 💪

chsrc. chsrc 全平台通用换源工具与框架. Change Source everywhere for every software

continue. open-source coding agent

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

ryzen-hackintosh. OpenCore EFI for AMD Ryzen Hackintosh

macdependency. MacDependency shows all dependent libraries and frameworks of a given executable, dynamic library or framework on Mac OS X

LLamaSharp. A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.

dr_libs. Audio decoding libraries for C/C++, each in a single source file.

Cog. Cog - A Free and Open Source Audio Player for macOS 10.15+

asciichart. Nice-looking lightweight console ASCII line charts ╭┈╯ for NodeJS, browsers and terminal, no dependencies

MathConverter. An All-in-One XAML Converter

StableLM. StableLM: Stability AI Language Models

asitop. Perf monitoring CLI tool for Apple Silicon

FreeTube. An Open Source YouTube app for privacy

swift-transformers. Swift Package to implement a transformers-like API in Swift

shadPS4. PlayStation 4 emulator for Windows, Linux, macOS and FreeBSD written in C++

dsu-controller-guides. A mobile app to simulate some game controllers.

bitmagnet. A self-hosted BitTorrent indexer, DHT crawler, content classifier and torrent search engine with web UI, GraphQL API and Servarr stack integration.

rats-search. rats-search: BitTorrent P2P multi-platform search engine for Desktop and Web servers with integrated torrent client

tribler. Privacy enhanced BitTorrent client with P2P content discovery

binexport. Export disassemblies into Protocol Buffers

bindiff. Quickly find differences and similarities in disassembled code

Queryable. Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.

verso. Mirror of https://gitlab.com/verso-browser/verso

vanilla. Vanilla Music Player for Android

MindSearch. 🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

vault. A tool for secrets management, encryption as a service, and privileged access management

LibreHardwareMonitor. Libre Hardware Monitor is free software that can monitor the temperature sensors, fan speeds, voltages, load and clock speeds of your computer.

XNNPACK. High-efficiency floating-point neural network inference operators for mobile, server, and Web

txtai. 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

axlearn. An Extensible Deep Learning Library

PlayCover. Community fork of PlayCover

RouteLLM. A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

tempo. An open source and lightweight music client for Subsonic, designed and built natively for Android.

everyone-can-use-english. 人人都能用英语

executorch. On-device AI across mobile, embedded and edge for PyTorch

android-appcachecleaner. Android Cache Cleaner

onnxruntime-inference-examples. Examples for using ONNX Runtime for machine learning inferencing.

awesome-hpp. A curated list of awesome header-only C++ libraries

godot. Godot Engine – Multi-platform 2D and 3D game engine

PhiCookBook. This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

cake. Distributed inference for mobile, desktop and server.

CppCon2017. Slides and other materials from CppCon 2017

openagent. ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

awesome-english-ebooks. 经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

LivePortrait. Bring portraits to life!

onnxruntime-swift-package-manager. A light-weight repository for providing Swift Package Manager support for ONNX Runtime.

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

jemallocator. Rust allocator using jemalloc as a backend

libcoap. A CoAP (RFC 7252) implementation in C

uv. An extremely fast Python package and project manager, written in Rust.

WebVoyager. Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

ultimate-macOS-KVM. Helping noobs and pros alike build the ultimate macOS virtual machine with easy automation, powered by KVM. Now with macOS Tahoe support!

DiffSynth-Studio. Enjoy the magic of Diffusion models!

gpt-2. Code for the paper "Language Models are Unsupervised Multitask Learners"

ladybird. Truly independent web browser

llama2.c. Inference Llama 2 in one file of pure C

trafilatura. Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

RTranslator. Open source real-time translation app for Android that runs locally

Jlama. Jlama is a modern LLM inference engine for Java

Docker-Proxy. 🔥 🔥 🔥 自建Docker镜像加速服务，基于官方Docker Registry 一键部署Docker、K8s、Quay、Ghcr、Mcr、Nvcr等镜像加速\管理服务。支持免服务器部署到 ClawCloud\Render\Koyeb

attention-viz. Visualizing query-key interactions in language + vision transformers (VIS 2023)

warp. A Python framework for GPU-accelerated simulation, robotics, and machine learning.

leedl-tutorial. 《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

Awesome-LLM-Inference. 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

LeetCUDA. 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

skip. Skip enables the creation of native SwiftUI apps for iOS and Android

YesPlayMusic. 高颜值的第三方网易云播放器，支持 Windows / macOS / Linux :electron:

pocketbase. Open Source realtime backend in 1 file

Thanks-Mirror. 整理记录各个包管理器，系统镜像，以及常用软件的好用镜像，Thanks Mirror。 走过路过，如觉不错，麻烦点个赞👆🌟

public-image-mirror. 很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。

docker-registry-mirrors. 多平台容器镜像代理服务,支持 Docker Hub, GitHub, Google, k8s, Quay, Microsoft 等镜像仓库.

cobalt. best way to save what you love

glibc_version_header. Build portable Linux binaries without using an ancient distro

Dependencies. A rewrite of the old legacy software "depends.exe" in C# for Windows devs to troubleshoot dll load dependencies issues.

ubicloud. Open source alternative to AWS. Elastic compute, block storage (non replicated), firewall and load balancer, managed Postgres, K8s, AI inference, and IAM services.

CasaOS-LinuxServer-AppStore. A CasaOS custom Appstore containing over 100+ LinuxServer.io images.

tldextract. Accurately separates a URL’s subdomain, domain, and public suffix, using the Public Suffix List (PSL).

furl. 🌐 The easiest way to parse and modify URLs in Python.

QuickRecorder. 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

Music-Player-GO. 🎶🎼 Very slim music player 👨‍🎤 100% made in Italy 🍕🌳🌞🍝🌄

tinygrad. You like pytorch? You like micrograd? You love tinygrad! ❤️

stable-diffusion.cpp. Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

inference. Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

command-line-api. Command line parsing, invocation, and rendering of terminal output.

marker. Convert PDF to markdown + JSON quickly with high accuracy

nocobase. NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.

onnxruntime-extensions. onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime

onnxruntime-genai. Generative AI extensions for onnxruntime