Easy Memory

Name: Easy Memory
Author: FlippySun

@FlippySun

リポジトリ

Easy Memory について

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

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

FlippySun

投稿者

FlippySun

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "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/>"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

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

「メモリとナレッジ」の他のコンテンツ

Mcp Knowledge Graph

shaneholloman

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

871

Zettelkasten MCP Server

entanglr

A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.

159