LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Public repository for Agent Skills

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

🎭 AI 驱动的中文小说创作助手。三层递进式智能问答、跨会话偏好记忆、中断续写、每章必留悬念钩子、自动校验修复。长篇小说一次性全稿完成。

Android Phone Control With Qwen3-VL

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Official PyTorch implementation of BigVGAN (ICLR 2023)

OneDL Lab Pre-training Toolbox and Benchmark

A scalable proxy for the Gemini API that handles API key rotation, polling, and load balancing. Perfect for Next.js, Cloudflare Workers, and serverless environments

Gemini API 代理, 把Gemini API免费中转到国内。还可以聚合多个Gemini API Key，随机选取API Key的使用实现负载均衡，使得Gemini API免费成倍增加。

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

An open-source AI agent that brings the power of Gemini directly into your terminal.

A Datacenter Scale Distributed Inference Serving Framework

2025年音视频开发最新总结，提供全面的音视频开发学习资源，涵盖从基础知识到实战项目的资料、论文、书籍、项目和示例，帮助你快速热门并逐步进阶，持续更新维护中！

Python binding to Poppler-cpp pdf library

A code executor for Dify that is compatible with the official sandbox API calls and dependency installation.

使用IndexTTS模型在ComfyUI中实现高质量文本到语音转换的自定义节点。支持中文和英文文本，可以基于参考音频复刻声音特征。

An open library of computer vision algorithms

Reference PyTorch implementation and models for DINOv3

MLX: An array framework for Apple silicon

Wan: Open and Advanced Large-Scale Video Generative Models

🚀 即梦3.0逆向API【特长：图像生成顶流】，零配置部署，多路token支持，仅供测试，如需商用请前往官方开放平台。