Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built...
An MCP App for playing and inspecting local audio files in an MCP host.
Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.
MCP Server for Authentication Management
parallel-browser-mcp is an MCP server for parallel browser automation. It exposes a numeric session model over MCP so one client can create and control multiple browser sessions at the same time...
🌉 Local-first Proton Mail MCP and CLI through Proton Bridge. Search, read, draft, send, sync, and act on mail from Claude Desktop or Terminal.
A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.
The LuxAlgo ecosystem as MCP tools: free and keyless.
MCP server providing isolated sandbox environments for AI agents.
ArkTS/ArkUI 开发助手 MCP Server，为 AI 编程助手（Claude Code、Cursor、Windsurf 等）提供文档检索和华为官方智能问答能力。
FocusRelay is a fast, native Swift MCP server and CLI that helps AI assistants read and safely update OmniFocus using documented OmniFocus APIs.
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
Agent Skills
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。
- Manage Claude Code, OpenAI Codex, Google Gemini, OpenCode, and custom AI agents from one powerful command-line interface.
(As usual, XKCD has a comic for this. Appropriately enough, the comic is out of date.)
中文内部技术写作的 agent skill。约束设计文档、评审稿、postmortem、分享稿等场景的语气、句法、结构，让产出贴近技术汇报，避开营销稿和散文气质。
LeetCode Helper is a Codex skill for solving LeetCode-style coding interview problems with optimized solutions and detailed explanations.
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...
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .
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.
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.
agnix Lint agent configurations before they break your workflow
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
Everything you need to know about OpenCode — from your first prompt to custom agents, skills, plugins, and MCP integrations.