Stars
Fast, reliable download accelerator and video downloader since 2013
NOVA opeN sOurce Video plAyer: main repository to build them all
MzDKPlayer: Android TV Media Player with Danmaku. Supports SMB, WebDAV, NFS, FTP, HTTP. Dolby Vision & DTS passthrough. | 安卓电视本地弹幕播放器。
Open-source AI gateway. Self-hosted LLM gateway with OpenAI-, Claude- and Gemini-compatible APIs, model routing, access control, usage tracking and cost accounting.
proxy core module for bepass, supports socks5/socks5h full UDP/TCP, IPv4, IPv6. supports socks4/a, http and https-connect proxy
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
将微信私聊消息桥接到 OpenCode，支持文本、图片、文件、音视频的双向传输。目标是在微信端还原OpenCode TUI和Desktop的体验
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost…
Experimental llama.cpp fork for inference research and development
SystemPanic / vllm-windows
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)
playIntegrityFixDetector is a native app designed to detect modifications, bypasses, or "fixes" applied to the Google Play Integrity API.
Test LLMs on real tasks. Compare models side-by-side.
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
An agentic skills framework & software development methodology that works.
A Kawaii React UI component library 一个可爱的 React UI 组件库
#1 Persistent memory for AI coding agents based on real-world benchmarks
Production-grade engineering skills for AI coding agents.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
OpenCode plugin that gives coding agents persistent memory using local vector database
Warp is an agentic development environment, born out of the terminal.
llama-cpp support turboquant and gemma 4
Long-memory plugin for OpenCode with context-mode interop
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 & k…
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
The Windows tray app and installer for Jellyfin Server on Windows.