← Discover MCPs and Agents
K
MCPAI & MLGitHub

Kodix

A blindingly fast AI Code Assistant built with Next.js, Tailwind CSS, and the Groq Cloud API (Llama 3.3 70B).

Links

Repository

README

From the repo.

Kodix - AI Code Assistant

Kodix is an AI-powered code generation and debugging assistant built with Next.js and Groq Cloud API running Llama 3.3 70B. It helps developers generate code, debug broken code, explain complex logic, and optimize performance.

🚀 Live Demo

Check out the live application: https://kodix-topaz.vercel.app/

✨ Features

  • Code Generation: Generate clean, readable code in multiple programming languages
  • Code Debugging: Debug broken code with detailed explanations
  • Code Explanation: Get plain English explanations of complex code
  • Code Optimization: Optimize code for better performance
  • Real-time Streaming: Watch code generate in real-time
  • History: Save and restore previous generations
  • Multiple Languages: Support for Python, JavaScript, TypeScript, Java, C++, and more

🛠️ Tech Stack

  • Frontend: Next.js 16, React, TypeScript
  • Styling: Tailwind CSS
  • Editor: Monaco Editor
  • AI: Groq Cloud API (llama-3.3-70b-versatile)
  • AI: Groq Cloud API (llama-3.3-70b-versatile)
  • Deployment: Vercel

📦 Installation

  1. Clone the repository:
git clone https://github.com/shubham124rawat/Kodix.git
cd Kodix
  1. Install dependencies:
npm install
  1. Set up environment variables: Create a .env.local file and add your Groq API key:
GROQ_API_KEY=your_api_key_here
  1. Run the development server:
npm run dev
  1. Open http://localhost:3000 in your browser

🏗️ Build for Production

npm run build
npm start

📝 Usage

  1. Select a module (Code Generator, Debugger, Explainer, or Optimizer)
  2. Choose your programming language
  3. Enter your prompt or paste your code
  4. Click "Generate" and watch the AI work its magic

🤝 Contributing

Contributions are welcome! Feel free to open an issue or submit a pull request.

📄 License

This project is open source and available under the MIT License.

Collected info

  • ★ 0 stars
  • Language: TypeScript
  • Source updated: 7/17/2026

Config for your environment

Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "{MCP_ENDPOINT_URL}"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.