Main
把它当“AI 内容版 Git”:让对话产出可版本化、可归因,并便于团队协作与审计。
用 MCP Hub 统一接入:集中发现、配置与命名空间管理,降低工具冲突与维护成本。
先用 Docker Compose 自托管跑通;再评估是否需要外部向量服务(README 也提到内置方案)。
安全上把 Token/Key 放到环境变量并定期轮换,把它当内部平台凭据管理。
README (excerpt)
plugged.in 🔌

Turn your AI conversations into permanent organizational memory
🚀 Get Started • 📚 Documentation • 🌟 Features • 💬 Community
🧩 Now Multi‑Arch Ready!
Plugged.in Docker images support both amd64 and arm64 architectures via a unified manifest.
🧠 v3.0.0 — Embedded RAG Vector Engine:
RAG now runs fully in-process using zvec (RocksDB + HNSW). No external services needed — document processing, chunking, and semantic search are all built-in.
🎯 The Problem We Solve
Every day, you have brilliant conversations with AI - strategy sessions with GPT-4, code reviews with Claude, analysis with Gemini. But when you close that chat window, all that knowledge vanishes. This is the "AI knowledge evaporation" problem.
💡 The Solution
plugged.in is the world's first AI Content Management System (AI-CMS) - a platform that transforms ephemeral AI interactions into persistent, versioned, and searchable organizational knowledge.
Think of it as "Git for AI-generated content" meets "WordPress for AI interactions".
✨ What Makes plugged.in Special
🧠 AI Memory That Persists
Your AI conversations become permanent assets. Every document is versioned, attributed, and searchable.
🤝 Multi-Model Collaboration
Claude writes v1, GPT-4 adds technical specs in v2, Gemini refines in v3 - all tracked and attributed.
🔌 Universal MCP Integration
Works with 1,500+ MCP servers. Connect any tool, any AI, any workflow - all through one interface.
Source-backed notes
- README 提供 Docker Quick Start,并在
http://localhost:12005访问应用。 - README 强调内置 MCP Server Hub,用于集成与发现/配置 servers。
- README 给出平台统计与自托管的向量/RAG 方案描述(含内置能力)。
FAQ
- 一定要单独的向量数据库吗?:不一定:README 提到内置方案;先跑通再扩展更稳妥。
- 它只做 MCP 吗?:不止:它是 AI 知识平台,MCP Hub 是核心模块之一。
- 最快怎么本地跑起来?:按 Docker Compose Quick Start 跑通,并确认 UI 里能看到 MCP Hub。