Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Persistent memory system for agentic AI via MCP - remember, recall, forget with semantic search with knowledge graph
MCPMate is a progressive MCP management center for organizing servers, clients, profiles, capabilities, and runtime visibility in one local workspace.
Making AI coding assistants experts at Swift and iOS development.
Fictional concept interface—not an actual Codex UI or a measured context, token, speed, or latency benchmark.
Installing MCPs is a huge pain, so I made a CLI tool to make it easier.
⚠️ ：此项目完全是 vibe coding 产物，代码由 AI 生成，未经严格审查。使用风险自己承担。
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
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.
个人知识库 MCP 服务器 — 对本地文档建立索引，并提供一组飞书 API 工具，通过 MCP 协议供 AI 客户端访问。
A secure, remote-accessible MCP server that gives LLMs read/write access to your Obsidian vault from anywhere -- your desktop, your phone, a hotel Wi-Fi network.
IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
Stop rewriting your tools. Just adapt them.
Agent Skills
LightClaw: The Real Lightweight AI Assistant
这个库的旨在为同学消除选择课程，学习资料等信息差。 在大学中存在大大小小的信息壁垒，然而要打破这些壁垒获取情报却要耗费大量时间精力。 有时上完一节课才意识到应该如何去上这门课，但为时已晚，学习结果可能不尽人意留下遗憾。 为了将那些不确定的，流状态的，短暂的，难以获取的，口口相传的信息保存下来，我们建立了这个库，希望能帮助到大家。 （摘自浙江大学课程攻略共享计划）
managed-agents helps teams move AI agents from demos to production with runtime infrastructure for sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, replayable...
我知道你在海投中一次次刷新邮箱，在 Boss 直聘上一个个点「立即沟通」， 却换来一片已读不回的沉默。 简历石沉大海，面试不知道怎么准备，求职信写了删、删了写。我们都曾经历过。
This collection of skills grew out of my day-to-day paper-writing workflow and has been iteratively refined over time.
⚠️ 本项目是作者为**而创建的个人学习项目，代码结构和实现均以探索为目的，。 ：网页版 AI 对工具调用的支持参差不齐，稳定性和准确性均有较大局限，距离实用仍有差距。 OpenLink 通过浏览器扩展模拟用户操作来驱动网页 AI，，不适合作为日常 API 调用使用。请合理使用，勿滥用。
An analysis of Moonshot AI's Kimi agent architecture (K2.5 model).
A simple template for creating persistent AI companions that remember you
A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).
A Claude Code skill for generating and editing images using the Gemini CLI's nanobanana extension.
Experimental skills for Claude Code Superpowers - new techniques and tools under active development.
Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity.