Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
mem-agent mcp server
TypeScript MCP server for retrieving YouTube transcripts in Claude Desktop, Cursor, Cline, Codex, and other MCP clients
Minimal MCP Server for Aider
CAD MCP Server
A macOS AppleScript MCP server
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy.
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
MCP-NixOS - Model Context Protocol Server for NixOS resources
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
A flexible HTTP fetching Model Context Protocol server.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Agent Skills
Everything you need to know about OpenCode — from your first prompt to custom agents, skills, plugins, and MCP integrations.
是由同花顺官方提供和维护的 A股金融数据服务，面向 AI Agent、量化研究者和应用开发者。
个人常用的 Agent Skill（公开部分）。通过合适的上下文工程，可以将 Agent Skill 用在几乎任何地方。
AI coding agents are great at Python. They hallucinate in Spring Boot.
Elves is an open-source Agent Skill for handing planned development or research work to a separate worker without locking the run to one model provider.
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
- Manage Claude Code, OpenAI Codex, Google Gemini, OpenCode, and custom AI agents from one powerful command-line interface.
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...
一句话：输入一个基金代码，Agent 把基金经理 8 年的每一笔买卖翻出来，拿 12 个月后的真实走势逐笔验对错，最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测，全都有。
Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.