A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

An Android RSS reader presented in Material You style.

Ready made components for your AI agents

Native local video understanding for the Pi coding agent via Kimi Coding

Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font icons for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1，细粒度的自定义选项

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

Software simulation for Android hardware-backed key pairs with key attestation | https://t.me/superpowers9

Build SukiSU-Ultra/KernelSU/KernelSU-Next/ReSukiSU Kernels For All OnePlus QCOM & MTK Devices (GKI2.0), Supporting SUSFS, KPM, ZRAM and more feats.

Modern Xposed Framework

An Xposed module to intercept applist detections

Fix Play Integrity <A13 verdicts, allowing custom fields and props

Standalone implementation of Zygisk

A collection of familiar, friendly, and modern emoji from Microsoft

File uploader built with shadcn/ui and Radix UI.

A full-featured, hackable Next.js AI chatbot built by Vercel

Local-first desktop markdown editor

⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.

Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tools, with iPhone & Apple Watch companions

Port of OpenAI's Whisper model in C/C++

A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.

🎃 A fast, out-of-the-box terminal built for AI coding.

A Commander for modern Go CLI interactions

从零开始玩转OpenClaw：最全面的中文教程，涵盖安装、配置、实战案例和避坑指南（github版）

Go RPC framework with high-performance and strong-extensibility for building micro-services.

非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-…

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.

A framework for few-shot evaluation of language models.