Simple Memory MCP

Simple Memory MCP is a memory management system designed for AI assistants, implementing the Model Context Protocol (MCP) to provide persistent memory storage and retrieval capabilities.

Tell your AI assistant: "Open memory" or "Open memory WEB", the AI will:

- Automatically start the web server
- Open the default browser
- Display the visual management interface

Tell your AI assistant: "Get all memories" or "Show memory list", the AI will execute thelist_memory_titlestool to retrieve all memory titles.

Tell your AI assistant: "Get 'XXX' memory content and execute", the AI will execute theget_memory_by_titletool to retrieve the complete content of the specified memory.

Tell your AI assistant: "Help me store a memory", the AI will:

- First ask you to provide the memory title
- Then ask you to input the memory content
- Execute thestore_memorytool to complete storage

- Smart Memory Storage: AI assistants must first ask users for memory titles, then request content
- 📋 Efficient Retrieval: Optimized MCP tools return only essential data (title + timestamp) for better performance
- 🌐 Web Management Interface: Intuitive visual management with full CRUD operations
- 🔍 Full-text Search: Search through both titles and content
- 🎯 Intelligent Port Management: Automatic port detection and conflict resolution
- 📱 Responsive Design: Optimized for both desktop and mobile devices
- 🔒 Single Instance Design: Automatic detection prevents multiple server instances
- 🤝 Multi-AI Support: Multiple AI assistants can safely share the same server instance

# Clone the repository git clone https://github.com/eragonht1/simple-memory-mcp.git # Navigate to project directory cd simple-memory-mcp

- Node.js 16.0.0 or higher
- 512MB RAM minimum
- 100MB available storage
- VisitNode.js official website
- Download the LTS (Long Term Support) version
- Run the installer (.msi file)
- Follow the installation wizard with default settings
- Restart your computer after installation

# Option 1: Download from official website # Visit https://nodejs.org/ and download the LTS version # Option 2: Using Homebrew (recommended) brew install node

# Ubuntu/Debian sudo apt update sudo apt install nodejs npm # CentOS/RHEL/Fedora sudo dnf install nodejs npm # Arch Linux sudo pacman -S nodejs npm

# Check Node.js version node --version # Check npm version npm --version

# Install dependencies npm install # Initialize database npm run init-db

# Start MCP Server npm start # Start Web Interface (recommended) node start-web.js # or npm run web

- Default URL:http://localhost:8011
- The system will automatically detect and allocate available ports
- Browser will open automatically with the professional launcher

{ "mcpServers": { "simple-memory": { "command": "node", "args": ["./start-mcp.js"], "cwd": "/path/to/your/simple-memory-mcp" } } }

- Replace/path/to/your/simple-memory-mcpwith your actual project path
- Add this configuration to your AI assistant's MCP settings file
- Restart your AI assistant to load the new configuration

Note:Thestart-mcp.jsscript provides better error handling and user-friendly output compared to directly callingsrc/server.js.

Simple Memory MCP uses asingle instance designto ensure optimal resource usage and data consistency:

- Automatic Detection: Before starting, the system checks if an MCP server is already running
- Smart Sharing: Multiple AI assistants (Claude, Augment, etc.) can safely share the same server instance
- Resource Efficiency: Prevents duplicate server processes and database conflicts
- Seamless Experience: If a server is already running, new AI connections will automatically use the existing instance
- First AI starts→ Detects no server → Starts new MCP server → Connects successfully
- Second AI starts→ Detects existing server → Shows friendly message → Connects to existing instance
- Both AIs can use memory functions simultaneouslywithout conflicts
- When all AIs close→ MCP server automatically shuts down to free resources

User: Help me store a memory AI: Please provide the title for this memory: User: Study Notes - MCP Protocol AI: Please enter the memory content: User: [Enter content] AI: Memory "Study Notes - MCP Protocol" has been successfully stored!

Simply say any of these trigger phrases to your AI assistant:

- "打开记忆MCP"(Open Memory MCP)
- "打开记忆"(Open Memory)
- "打开记忆WEB"(Open Memory WEB)
- "开启记忆"(Start Memory)
- 🚀 Start the web server (if not running)
- 🌐 Open your default browser
- 📋 Display the memory management interface
- ✨ Provide usage tips and access URLs
- Click "➕ Add Memory" to create new memories
- Click memory cards to view details
- Use action buttons on each memory card:

- Edit(🖊️) - Modify memory content
- Copy(📋) - Copy title and content to clipboard in plain text
- Delete(🗑️) - Remove memory permanently

- store_memory- Store new memory (requires title and content)
- list_memory_titles- Get list of all memory titles
- get_memory_by_title- Retrieve memory content by title
- delete_memory- Delete specified memory
- open_memory_web-NEW!Open memory management web interface with auto browser launch

For detailed documentation, seeDOCS.mdwhich includes:

# Windows netstat -ano | findstr :8011 taskkill /PID <PID> /F # Linux/macOS lsof -i :8011 kill -9 <PID>

# If browser doesn't open automatically # Check if the web server is running curl http://localhost:8011 # Manually open the URL shown in AI response # Example: http://localhost:8011 # Check browser availability (Linux) which xdg-open firefox google-chrome # Check browser availability (Windows) where start # Check browser availability (macOS) which open

# 克隆仓库 git clone https://github.com/eragonht1/simple-memory-mcp.git # 进入项目目录 cd simple-memory-mcp

- Node.js 16.0.0 或更高版本
- 最低512MB内存
- 100MB可用存储空间
- 访问Node.js官方网站
- 下载LTS（长期支持）版本
- 运行安装程序（.msi文件）
- 按照安装向导的默认设置进行安装
- 安装完成后重启计算机

# 方法1：从官网下载 # 访问 https://nodejs.org/ 下载LTS版本 # 方法2：使用Homebrew（推荐） brew install node

# Ubuntu/Debian sudo apt update sudo apt install nodejs npm # CentOS/RHEL/Fedora sudo dnf install nodejs npm # Arch Linux sudo pacman -S nodejs npm

# 检查Node.js版本 node --version # 检查npm版本 npm --version

# 安装依赖 npm install # 初始化数据库 npm run init-db

# 启动MCP服务器 npm start # 启动Web管理界面（推荐） node start-web.js # 或者 npm run web

- 默认地址:http://localhost:8011
- 系统会自动检测并分配可用端口
- 使用专业启动器时会自动打开浏览器

{ "mcpServers": { "simple-memory": { "command": "node", "args": ["/path/to/your/simple-memory-mcp/start-mcp.js"], "cwd": "/path/to/your/simple-memory-mcp" } } }

- 将/path/to/your/simple-memory-mcp替换为你的实际项目路径
- 将此配置添加到你的AI助手的MCP设置文件中
- 重启你的AI助手以加载新配置

注意：start-mcp.js脚本相比直接调用src/server.js提供了更好的错误处理和用户友好的输出信息。

Simple Memory MCP 采用单实例设计，确保最佳的资源使用和数据一致性：

- 自动检测: 启动前系统会检查是否已有MCP服务器在运行
- 智能共享: 多个AI助手（Claude、Augment等）可以安全地共享同一个服务器实例
- 资源高效: 防止重复的服务器进程和数据库冲突
- 无缝体验: 如果服务器已在运行，新的AI连接会自动使用现有实例
- 第一个AI启动→ 检测无服务器 → 启动新MCP服务器 → 成功连接
- 第二个AI启动→ 检测到现有服务器 → 显示友好提示 → 连接到现有实例
- 两个AI可以同时使用记忆功能而不会产生冲突
- 当所有AI关闭时→ MCP服务器自动关闭以释放资源

用户: 帮我存储一个记忆 AI: 请提供这个记忆的标题： 用户: 学习笔记 - MCP协议 AI: 请输入记忆的具体内容： 用户: [输入内容] AI: 记忆 "学习笔记 - MCP协议" 已成功存储！

- "打开记忆MCP"
- "打开记忆"
- "打开记忆WEB"
- "开启记忆"
- 🚀 启动Web服务器（如果未运行）
- 🌐 打开默认浏览器
- 📋 显示记忆管理界面
- ✨ 提供使用提示和访问地址
- 点击"➕ 添加记忆"创建新记忆
- 点击记忆卡片查看详情
- 使用每个记忆卡片上的操作按钮：

- 编辑(🖊️) - 修改记忆内容
- 复制(📋) - 将标题和内容以纯文本格式复制到剪贴板
- 删除(🗑️) - 永久删除记忆

- store_memory- 存储新记忆（需要标题和内容参数）
- list_memory_titles- 获取所有记忆标题列表
- get_memory_by_title- 根据标题检索记忆内容
- delete_memory- 删除指定记忆
- open_memory_web-新功能！打开记忆管理Web界面并自动启动浏览器

# Windows netstat -ano | findstr :8011 taskkill /PID <PID> /F # Linux/macOS lsof -i :8011 kill -9 <PID>

# 如果浏览器没有自动打开 # 检查Web服务器是否运行 curl http://localhost:8011 # 手动打开AI响应中显示的URL # 例如: http://localhost:8011 # 检查浏览器可用性 (Linux) which xdg-open firefox google-chrome # 检查浏览器可用性 (Windows) where start # 检查浏览器可用性 (macOS) which open

Simple Memory MCP- 让AI助手拥有持久记忆的能力 💾✨Simple Memory MCP- Giving AI assistants persistent memory capabilities 💾✨

Engram is a hosted MCP server that provides reliable memory for AI agents:

Persistent memory, teams, and projects for AI agents. 76 MCP tools for storing, recalling, and sharing knowledge across sessions.

Provides searchable local storage for Claude conversation history, enabling context retrieval during sessions.

Deterministic O(1) memory for AI agents — local-first, MCP-native, with multi-agent speaker attribution and millisecond recall.

A server providing persistent memory for AI assistants, with support for multiple AI providers.

Enables Large Language Models to store and retrieve persistent memories with intelligent search capabilities.

Agent memory with git-like version control. Custom LLMs turn conversations into structured facts with automatic conflict detection - your agent sees how decisions evolved, not four contradictory text blobs. 80% token reduction vs RAG/graph systems. MCP + REST.

Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.

An autonomous memory management system for Claude AI, featuring multi-provider LLM integration and a persistent memory database.

One shared, versioned memory for your AI agents across Claude Code, Cursor, Kiro and Grok, with a source on every answer and full history.