Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama, with your choice of Anthropic (Claude) or Ollama as the main LLM.
MCP server that lets Claude Code pause mid-task and ask a human a question via Slack — then resume once you reply.
MCP server for Exa Search API.
An experimental way to connect MCPs to Pi using Code
claude-mem-lite is a (also called long-term memory or cross-session context) system for — Anthropic's CLI coding agent.
An MCP-based Google Scholar search service optimized for Cherry Studio, providing academic paper search, abstract retrieval, and supporting both Chinese and English queries.
A Flutter MCP to interact with your flutter app
An MCP server that slurps data from Google News and Google Trends RSS endpoints, optionally distills it with LLM/NLP, and barfs out structured results.
A local-first, single-user AI partner you host yourself — no matter the model. It remembers, keeps a stable identity you author, and reaches back — all on your machine, with your data in a file you...
An MCP server that allows you to run Node.js scripts and npm commands, with permission prompts via node-notifier.
A browser extension and MCP server that allows you to interact with the browser you are using.
Most AI coding tools give you a result but no record of how you got there - no trail of decisions for teammates to follow, no way to continue work across sessions, and no framework for managing large...
Agent Skills
A coding agent on par with Claude Code; as a personal assistant, lighter than OpenClaw — one MIT-licensed Go binary, no Node / Python / Ruby, running on (DeepSeek, Kimi, Anthropic, OpenAI, or...
Bring Codex, Claude Code, Cursor, Gemini CLI, OpenCode, or your own agent. ContentOS is a workflow and data contract, not a model, vendor, or CLI-specific application.
DSH 插件，在 Web 设置页同时提供「技能」与「MCP」两个管理面板，并随包提供统一终端命令 dsh-panel（skill / mcp 两个子命令族）。
Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文
A prompt-based pipeline for finding, validating, and proving vulnerabilities using LLM sub-agents — structured to resist false positives.
Market Map agent eval suite for the Reforge AI Evaluation course
SD 2.5 Prompt 是一套面向 Seedance 2.5 / SD 2.5 视频生成的实用 Skill。它不依赖冗长术语，用五个部分统一处理产品广告、人物动作、原片反推、多模态参考、音乐节奏和复杂打斗。
Фреймворк агентной разработки для 1С BSL с применением модульного подхода. Позволяет настроить AI-агентов (Cursor, Claude Code и др.
产品经理从需求调研分析到 PRD、交互原型、功能验收与数据分析的完整工作流 Skill
— functional but APIs change, Apify actors rotate, and edge cases are still being discovered.
DNA Memory 把一个 Markdown/Obsidian 目录作为长期记忆真源，把 SQLite 作为可删除、可重建的索引。多个 AI 客户端通过同一个 MCP 服务召回、写入和反馈， 不再各自维护互相冲突的长期记忆副本。
A Claude Code skill that generates 120fps GPU-accelerated animations using Motion.dev (the successor to Framer Motion).