etomberg391
README.md

Cerebras Coder

An AI code assistant powered by Cerebras that generates fully functional web applications in seconds.

Inspired by Hassan's Llama Coder.

Features

  • Multiple Model Support: Choose from three powerful AI models:

    • Qwen 3 235B Instruct (235B parameters, ~1400 tokens/s)
    • Z.ai GLM 4.6 (357B parameters, ~1000 tokens/s)
    • OpenAI GPT OSS (120B parameters, ~3000 tokens/s)

  • Flexible API Key Management:

    • Use the default hosted API key (no setup required)
    • Or use your own personal Cerebras API key for private usage

  • Instant Code Generation: Turn your ideas into fully functional apps in less than a second

  • Live Preview: See your code come to life in real-time

  • Version History: Track and revert to previous versions of your code

  • Share Your Projects: Generate shareable links to your creations

Setup

Option 1: Use Default API Key (No Setup Required)

Simply open the application and start coding! The default API key is already configured.

Option 2: Use Your Personal API Key

  1. Sign up for Cerebras
  2. Get your Cerebras API Key
  3. In the application, click the "Default API Key" button in the header
  4. Select "Personal API Key" from the dropdown
  5. Enter your API key in the modal
  6. Your key will be used for the current session only

Note: Personal API keys are stored only in browser memory and are forgotten when you close or refresh the page.

For Developers

To deploy with your own default API key:

  1. Save your Cerebras API key in your project environment variable called CEREBRAS_API_KEY
  2. The application will use this key by default

Usage

  1. Select a Model: Click the model dropdown in the header to choose your preferred AI model
  2. Choose API Key Mode: Select between "Default API Key" or "Personal API Key"
  3. Enter Your Prompt: Type what you want to build (e.g., "Build me a calculator app")
  4. Generate Code: Click the prompt button or press Enter
  5. View & Edit: See your code in the editor and preview it live
  6. Iterate: Make changes by entering new prompts
  7. Share: Click the Share button to get a link to your project

Model Comparison

ModelParametersSpeedBest For
Qwen 3 235B Instruct235B~1400 tokens/sBalanced performance
Z.ai GLM 4.6357B~1000 tokens/sComplex reasoning
OpenAI GPT OSS120B~3000 tokens/sFast generation

Technology Stack

  • Frontend: React, TypeScript, Tailwind CSS
  • Backend: Val Town
  • AI: Cerebras Cloud SDK
  • Code Highlighting: react-syntax-highlighter

License

This project is open source. Feel free to fork and customize it for your needs!