llamacoder

[

Llama Coder ](https://www.llamacoder.io)

An open source Claude Artifacts – generate small apps with one prompt. Powered by Llama 3 on Together.ai.

Tech stack

• Llama 3.1 405B from Meta for the LLM
• Together AI for LLM inference
• esbuild-wasm + esm.sh for the in-browser preview renderer (runs in a sandboxed iframe)
• Next.js app router with Tailwind
• Braintrust for observability
• Plausible for website analytics

Cloning & running

1. Clone the repo: git clone https://github.com/Nutlope/llamacoder
2. Create a .env file and add your API keys:
   • Together AI API key: TOGETHER_API_KEY=
   • Database URL: Use Neon to set up your PostgreSQL database and add the Prisma connection string: DATABASE_URL=
   • Braintrust API key (optional, for observability): BRAINTRUST_API_KEY=
   • Screenshot uploads: Configure S3_UPLOAD_KEY, S3_UPLOAD_SECRET, S3_UPLOAD_BUCKET, S3_UPLOAD_REGION, and IMAGE_UPLOAD_TOKEN_SECRET. The uploader uses the existing bucket as-is; it does not require bucket policy, CORS, lifecycle, delete-permission, or second-bucket changes.
3. Run npm install and npm run dev to install dependencies and run locally

Contributing

For contributing to the repo, please see the contributing guide