Packages

MCP server that enables AI agents to control web browsers via the browser-use library and Playwright, supporting navigation, data extraction, and web-based task automation with real-time VNC streaming for visual monitoring.

Cloud security assessment tool for Chinese cloud providers (Alibaba, Tencent, Huawei, Baidu, Qiniu). Enumerates cloud assets (storage buckets, compute instances, IAM users/roles, domains), tests access permissions, hardens bucket policies, and creates honey tokens for intrusion detection. Has a Metasploit-like CLI interface and MCP protocol support via SSE and STDIO modes.

A Claude Code skill that delegates tasks to an OpenCode "intern" agent via [ACP (Agent Communication Protocol)](https://agentclientprotocol.com/overview/introduction). This enables Claude Code to offload tasks to a secondary AI agent running in [OpenCode](https://OpenCode.ai/docs/acp/) using any model you like.

Claude Code skill that automates end-to-end GitHub Pages deployment — git init to live URL, zero manual steps.

[🇨🇳 中文文档](./README_CN.md)

[](LICENSE)

Self-hosted deep research tool that generates comprehensive research reports in about 2 minutes using configurable thinking and task LLM models. Combines multiple LLM providers (OpenAI, Anthropic, Google, Deepseek, Mistral, Ollama, etc.) with multiple search providers (Tavily, Searxng, Brave, Exa, Firecrawl). Includes MCP server support, knowledge graph generation, research history, and a multi-language web UI.

Terminal-based MCP client that connects local Ollama language models to MCP servers. Supports agent mode with iterative tool execution, multi-server connections, STDIO/SSE/Streamable HTTP transports, MCP prompts, human-in-the-loop tool approval, thinking mode, and conversation history export. This is a CLIENT, not an MCP server.

A lightweight Flask API bridge that connects Claude Desktop (or any MCP-compatible client) to a Kali Linux machine, enabling AI-assisted command execution for authorized penetration testing and CTF challenges. The server exposes a thin HTTP API on port 5000 that accepts arbitrary shell commands and returns their output, effectively giving an AI assistant a live Kali terminal. Tools like Nmap, Metasploit, sqlmap, Gobuster, enum4linux, and any other Kali tool are accessible by name. The architecture is intentionally minimal — a single Flask server with no auth, no sandboxing, and no command filtering — making it fast to set up for isolated testing environments but completely unsuitable for production or shared infrastructure.

Agentic framework that automatically generates complete PowerPoint presentations from documents, research topics, or freeform prompts, with reflective design capabilities and text-to-image asset generation.

An MCP server that enables AI agents to publish content, search posts, retrieve recommendations, manage comments, and access user profiles on Xiaohongshu (小红书/RedNote) via headless browser automation.

Comprehensive configuration and plugin repository for Claude Code and OpenAI Codex. Bundles 16+ pre-built plugins (Azure, GitHub, Slack, Linear, MongoDB, Supabase, Playwright, etc.), custom skills, agents, hooks for auto-formatting, and MCP server integrations. Also supports alternative LLMs via proxy configurations.

Google Calendar integration for OpenClaw/Clawd agents

MCP server and CLI tool for searching and downloading books and articles from Anna's Archive, supporting title/author/topic search and DOI-based article retrieval.

Self-hosted, multilingual FAQ and knowledge-base web application for PHP 8.4+ with enterprise auth (LDAP, Active Directory), full-text search via Elasticsearch/OpenSearch, REST API, and support for 40+ languages.

<h1 align="center">Apple-Hig-Designer</h1>

[](./LICENSE)

A Python/Java/Vue backend server for the Xiaozhi ESP32 open-source smart hardware project, providing voice interaction, speaker recognition, multi-LLM dialogue, visual perception, and IoT device control for ESP32-based AI assistants.

Search medications and check real-time stock at Clalit pharmacies in Israel