Installation and Quick Start Guide

This guide will walk you through the process of setting up CursorLens, configuring it with Cursor, and getting started with AI-assisted coding.

Prerequisites

• Node.js (v14 or later)
• pnpm
• PostgreSQL server
• ngrok
• Cursor IDE installed

Installation

1. Clone the repository:

   git clone https://github.com/HamedMP/CursorLens.git
   cd CursorLens
   

2. Install dependencies:

   pnpm install
   

3. Set up environment variables: Create a .env file in the root directory and add the following:

   DATABASE_URL="postgresql://username:password@localhost:5432/cursorlens"
   OPENAI_API_KEY="your_openai_api_key"
   ANTHROPIC_API_KEY="your_anthropic_api_key"
   # Add other API keys as needed (e.g., GROQ_API_KEY, MISTRAL_API_KEY, etc.)
   

4. Set up the database:

   pnpm prisma migrate dev
   

5. Build the project:

   pnpm build
   

Configuration

6. Start the development server:

   pnpm dev
   

7. Set up ngrok:

   • Install ngrok: https://ngrok.com/download
   • Start ngrok on the same port as your CursorLens server:
     ngrok http 3000
     

   • Copy the ngrok URL (e.g., https://1234abcd.ngrok.io)

8. Configure Cursor:

   • Open Cursor settings
   • Set the API endpoint to your ngrok URL
   • Set the toggle to use OpenAI Key on

Start Using CursorLens

9. Begin coding with Cursor:

   • Use AI-assisted features like Cmd+i, Cmd+k, or Cmd+L
   • Requests will now be routed through your local CursorLens server
   • The model you choose in Configuration as default model will be used for your requests

10. Access the CursorLens dashboard:

    • Open http://localhost:3000 in your browser
    • Explore analytics, view request logs, and monitor real-time interactions

Supported Providers and Models

CursorLens supports a wide range of AI models through various providers:

• OpenAI: GPT-4o, GPT-4o mini
• Anthropic: Claude 3 Opus, Claude 3.5 Sonnet
• Groq: LLaMA 3.1 (405B, 70B, 8B), Mixtral 8x7B
• Mistral: Mistral Large, Mistral Small, Mistral Medium
• Cohere: Command, Command-r, Command-r-plus
• Ollama: Various open-source models (CodeLlama, Llama 2, Llama 3, Mistral, Mixtral, Phi-2, Gemma, and more)

For a complete list of Ollama-supported models, refer to the Ollama model library.

Optimizing Your Workflow

• Use the insights gained from the CursorLens dashboard to improve your AI-assisted coding efficiency
• Experiment with different models to find the best fit for your coding tasks
• Keep your CursorLens server running whenever you want to use these features

You're now ready to leverage the power of CursorLens to enhance your AI-assisted coding experience!