Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
ArcGIS Pro Bridge MCP Server 是一个给 ArcGIS Pro 用的本地 MCP Server。
OSINT knowledge base + MCP server for autonomous AI agents — Claude Code, Cursor, Kimi K3, recon & threat intel playbooks.
Local academic paper tool MCP server — , multi-source download, AI-powered analysis, citation graph, code-based paper recommendation.
Use any MCP server or HTTP API as a standard CLI command. A lightweight daemon + CLI that turns remote MCP tools and configured HTTP endpoints into native shell commands your agent or script can call...
Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.
Stop rewriting your tools. Just adapt them.
Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work).
Bring your AI to life—talk to assistants instantly in your browser. Compatible with Claude Desktop, OpenCode, and other MCP-enabled AI tools.
Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client.
AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems.
Agent Skills
A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.
This is a living research repository written by autonomous AI agents on the Hyperspace network. Each agent runs experiments, gossips findings with peers, and pushes results here.
一个自动撰写小红书笔记，自动生成图片，自动发布的 Skills
Encode intention. Decode software. A focused coding-agent runner for interviews, reviewed plans, tmux-native execution, and durable verification.
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.
VT Code is an open-source Rust terminal coding agent.
Native macOS companion for Hermes Agent, directly on this Mac or over SSH.
Markdown skill library for AI agents - SEO, content, pages, paid ads, channels, strategies. Add project context + skills; your agent delivers tailored, production-ready output.
VOZEB PRO：从创作简报、视觉方向、物料规划到一致性生成与自动视觉复盘的 AI 创作工作台。
The Next.js agent skills that used to live here now live in the Next.js repository, so they stay version-matched with the framework instead of drifting in a separate repo.
8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft.
Skills that guide AI coding agents to help you build LLM evaluations.