Wisdomforge

🚀 WisdomForge

A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. It uses the Qdrant vector database for efficient knowledge storage and retrieval.

🚀 Quick Start

WisdomForge is a robust knowledge management system designed to streamline the storage and retrieval of knowledge. It leverages the Qdrant vector database to ensure high - efficiency operations.

✨ Features

• Intelligent knowledge management and retrieval.
• Support for multiple knowledge types (best practices, lessons, insights, experiences).
• Configurable database selection (via environment variables).
• Efficient embedding generation using Qdrant's built - in FastEmbed.
• Domain knowledge storage and retrieval.
• Deployable to the Smithery.ai platform.

📦 Installation

Prerequisites

• Node.js 20.x or higher (LTS version recommended).
• npm 10.x or higher.
• Qdrant or Chroma vector database.

Steps

1. Clone the repository:

git clone https://github.com/hadv/wisdomforge
cd wisdomforge

2. Install dependencies:

npm install

3. Create a .env file in the root directory based on the .env.example template:

cp .env.example .env

4. Configure environment variables in the .env file:

Required Environment Variables

Database Configuration

• DATABASE_TYPE: Select the vector database (qdrant or chroma).
• COLLECTION_NAME: Name of the vector collection.
• QDRANT_URL: URL of the Qdrant instance (required only when using Qdrant).
• QDRANT_API_KEY: Qdrant API key (required only when using Qdrant).
• CHROMA_URL: URL of the Chroma instance (required only when using Chroma).

Server Configuration

• HTTP_SERVER: Set to true to enable HTTP server mode.
• PORT: Port number for local development (default: 3000). Only used for Smithery cloud deployment.

Example .env configuration (for Qdrant):

DATABASE_TYPE=qdrant
COLLECTION_NAME=wisdom_collection
QDRANT_URL=https://your-qdrant-instance.example.com:6333
QDRANT_API_KEY=your_api_key
HTTP_SERVER=true
PORT=3000  # Only for local development

5. Build the project:

npm run build

💻 Usage Examples

AI IDE Integration

Cursor AI IDE

Add the following configuration to the ~/.cursor/mcp.json or .cursor/mcp.json file:

{
  "mcpServers": {
    "wisdomforge": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@hadv/wisdomforge",
        "--key",
        "YOUR_API_KEY",
        "--config",
        "{\"database\":{\"type\":\"qdrant\",\"collectionName\":\"YOUR_COLLECTION_NAME\",\"url\":\"YOUR_QDRANT_URL\",\"apiKey\":\"YOUR_QDRANT_API_KEY\"}}",
        "--transport",
        "ws"
      ]
    }
  }
}

Replace the following placeholders:

• YOUR_API_KEY: Your Smithery API key.
• YOUR_COLLECTION_NAME: Your Qdrant collection name.
• YOUR_QDRANT_URL: Your Qdrant instance URL.
• YOUR_QDRANT_API_KEY: Your Qdrant API key.

⚠️ Important Note

Ensure that the correct version of Node.js is installed.

Claude Desktop

Configure as follows in Claude Desktop:

{
  "config": {
    "path": "your_project_path",
    "server": {
      "command": "npm start"
    }
  }
}

⚠️ Important Note

Make sure the project path is correct and the server is started.