Easy Memory

Name: Easy Memory
Author: FlippySun

@FlippySun

代码仓库

关于 Easy Memory

Easy Memory MCP - Dual-engine embedding service with Qdrant vector store

#memory #mcp-server #ai-memory #qdrant #ollama #gemini #vector-search #bm25 #semantic-search #persistent-memory #embedding #hybrid-retrieval

基本信息

分类

记忆与知识

许可证

MIT

运行时

node

传输方式

stdio

发布者

FlippySun

提交者

FlippySun

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "easy-memory": {
      "command": "npx",
      "args": [
        "-y",
        "easy-memory@latest"
      ],
      "env": {
        "EASY_MEMORY_URL": "https://memory.zhiz.chat/mcp",
        "EASY_MEMORY_TOKEN": "<YOUR-TOKEN Get By: https://memory.zhiz.chat/>"
      }
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Easy Memory?

Easy Memory is an MCP (Model Context Protocol) memory service that persists AI memory across sessions and projects. It integrates with Qdrant vector database and embedding models (official OpenAI via compatible relay or Ollama), and provides dual-shell architecture: MCP Shell (stdio) for direct communication with AI clients like Claude Desktop, Cursor, and VS Code, and HTTP Shell (RESTful API) for remote access and multi-client sharing. It is intended for developers who want their AI assistants to retain context and knowledge between conversations.

How to use Easy Memory?

Easy Memory can be run via npx easy-memory, Docker Compose, or from source. Configure it by setting environment variables such as QDRANT_URL, QDRANT_API_KEY, and OLLAMA_BASE_URL for local setups, or EASY_MEMORY_URL and EASY_MEMORY_TOKEN for remote proxy mode. For client integration, edit the MCP configuration file (e.g., claude_desktop_config.json, .vscode/mcp.json) with the appropriate command and environment variables.

Key features of Easy Memory

Dual shell architecture: MCP (stdio) and HTTP (RESTful API)
Remote proxy mode – no local Qdrant or Ollama required
Supports multiple AI clients: Claude Desktop, Cursor, VS Code
Persistent memory across sessions and projects
Semantic search with hybrid retrieval (vector + BM25)
8 MCP tools: save, search, forget, status (with aliases)

Use cases of Easy Memory

Enable AI assistants to remember facts across conversations and projects
Share a central memory store among multiple clients via HTTP API
Run a remote memory

记忆与知识分类下的更多 MCP 服务器

Docs MCP Server

arabold

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

1.5K

minutes

silverstein

Every meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.

1.3K

Semantic Scholar MCP Server

YUZongmin

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

158