Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A working pattern for SSE-based MCP clients and servers
Every AI can do tax math. None of them can stand behind an answer. Here, real accountants put their on the Guides your AI reads — publicly, on the record, in this repo.
Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.
An MCP server that converts a layered PSD character into a Spine 4.2 project — skeleton JSON, texture atlas, and atlas page PNG(s) — ready to import into the Spine editor and Unity.
- Let AI assistants analyze binaries directly
Please see the updated mcpb format Claude Desktop Extension
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
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).
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
A MCP server that enables AI models to access and search ZIM format knowledge bases offline
This repo provides a reference implementation for creating a remote MCP server that supports the Streamable HTTP & SSE Transports, authorized with OAuth based on the MCP specification.
Deploy anything on your own servers. Connect a server, click deploy, done. MIT licensed and free to self-host forever.
Agent Skills
消除中文 AI 写作痕迹的 Claude Skill：拆排比三件套、去名词化、换抽象主语为具体细节。灵感来自 hardikpandya/stop-slop。
Claude Code skill for comprehensive website design research using browser-automation agent teams
astrbook的适配插件，让bot拥有在astrbook上聊天的能力
Claude Code skill that removes your own personal info from people-search sites and data brokers (discovery + automated opt-outs in your own browser).
Async State Management without the Management. REST, GraphQL, SSE, Websockets
ChatWiki 微信公众号的AI知识库工作流Agent平台，RAG大模型AI客服机器人，致力于成为垂直领域的coze、n8n。
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
🤖 Data Science & AI/ML skill suite derived from wshobson/commands.
A curated list of Quarto talks, tools, examples & articles! Contributions welcome!
A task runner that works well with poetry or uv.
The world's first Autonomous Product Engine (APE): AI agents research your market, generate features, and ship code as PRs. Convoy mode, crash recovery, cost tracking, 80+ API endpoints.