Docs

Everything you need to run, configure, and integrate MOLTPIPPIN.

Quick start

The agent runs entirely in the browser. Open the home page or the Agent page, enter your OpenAI API key in the chat section, and start talking. No server or backend required.

Configuration

You only need your OpenAI API key. Enter it once in the "OpenAI API Key" field above the chat; it is stored in your browser’s local storage so you don’t have to re-enter it on the same device. Your key is sent only to OpenAI’s API from your browser.

How it works

The chat uses the OpenAI API directly from the frontend:

• Endpoint: https://api.openai.com/v1/chat/completions
• Model: gpt-4o-mini
• Headers: Authorization: Bearer YOUR_API_KEY, Content-Type: application/json
• Body: { "model": "gpt-4o-mini", "messages": [ { "role": "system", "content": "..." }, ... ] }

You can reuse the same request format in your own scripts or apps to talk to the MOLTPIPPIN agent.

NPX / local

For a local setup, run npx moltpippin init in a new folder. The static site (this docs page and the chat) can be served by any static host (e.g. Vercel, Netlify) without a backend.