Memorymesh

🚀 Memory Mesh

MemoryMesh is an MCP server for managing knowledge graph data in the Claude desktop environment. It enables AI to perform reasoning through structured data and provides an in-memory data storage system.

🚀 Quick Start

Installation

1. Clone the repository:

   git clone https://github.com/CheMiguel23/memorymesh.git
   cd memorymesh
   

2. Install dependencies:

   npm install
   

3. Compile the project:

   npm run build
   

   This command compiles the TypeScript code into JavaScript and stores it in the dist directory. It also copies the example schema and data files to this directory.

4. Configure the Claude desktop environment:

   • Open your configuration file:

     • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
     • Windows: %APPDATA%\Claude\claude_desktop_config.json

   • Add the following content to the mcpServers section:

     "memorymesh": {
       "command": "node",
       "args": ["/ABSOLUTE/PATH/TO/YOUR/PROJECT/memorymesh/dist/index.js"]
     }
     

     Replace /ABSOLUTE/PATH/TO/YOUR/PROJECT/ with the actual path of your project.

Verify the Installation

1. Launch the Claude desktop.
2. Open a new chat window.
3. Check the MCP plugin icon in the top - right corner. If you see the icon, the configuration is correct.
4. Click the icon and view the list of connected servers. You should see "memorymesh".

✨ Features

• Pluggable Knowledge Representation: Define entities and relationships through JSON Schema.
• Persistent Storage: Data is saved in files to prevent data loss due to power outages or restarts.
• AI Programmable Interface: Provide custom tools for Claude to interact with the knowledge graph.

💻 Usage Examples

Basic Usage

// Create a user using the add_user tool
{
  "tool": "add_user",
  "args": {
    "username": "john_doe",
    "email": "john@example.com",
    "age": 30,
    "hobbies": ["reading", "music"]
  }
}

Advanced Usage

// Query a user using the query_user tool
{
  "tool": "query_user",
  "args": {
    "username": "john_doe"
  },
  "result": {
    "found": true,
    "user": {
      "username": "john_doe",
      "email": "john@example.com",
      "age": 30,
      "hobbies": ["reading", "music"]
    }
  }
}

📚 Documentation

Dependencies

• express: Used to create an HTTP server.
• yargs: Command - line argument parsing.
• uuid: Generate unique identifiers.

Install via npm

npm install memorymesh --save

Directory Structure

memorymesh/
├── dist/                 # Compiled output directory
│   ├── index.js         # Entry file
│   └── data/            # Data storage directory
├── schemas/              # Schema files defining entities and relationships
└── src/                  # Source code directory
    ├── server.ts        # Server implementation
    └── tools/           # Custom tools

Tutorial

Create a New Entity Type

1. Create a new JSON Schema file in the schemas directory.
2. Define the attributes and relationships of the entity.
3. Use AI tools for data operations.

🤝 Contribution

Any contributions, feedback, or ideas are welcome to further advance this project or inspire new explorations.