​
Quick Start Guide

Get up and running with Auto-Browse quickly by following these simple steps.

​
Installation

Install Auto-Browse using npm:

npm install @auto-browse/auto-browse

​
Basic Setup

  1. Create a .env file in your project root with your OpenAI API key:
OPENAI_API_KEY=your_openai_api_key_here
LLM_MODEL=gpt-4o-mini  # Optional, defaults to gpt-4o-mini

​
Simple Example

Here’s a complete example showing form automation:

import { auto } from "@auto-browse/auto-browse";

async function main() {
	try {
		// Navigate to the form
		await auto("go to https://httpbin.org/forms/post");

		// Take a snapshot to analyze the page structure
		await auto("take a snapshot");

		// Fill out the form
		await auto('type "John Doe" in the customer name field');
		await auto('select "Large" for size');
		await auto('select "Mushroom" for topping');
		await auto('check "cheese" in extras');

		// Submit the form
		await auto("click the Order button");

		// Take a snapshot of the response page
		await auto("take a snapshot of the response page");
	} catch (error) {
		console.error("Error:", error);
	}
}

// Run the script
main().catch(console.error);

​
Using with Playwright Tests

Auto-Browse seamlessly integrates with Playwright tests:

import { test, expect } from "@playwright/test";
import { auto } from "@auto-browse/auto-browse";

test("example test", async ({ page }) => {
	await page.goto("https://example.com");

	// Get text using natural language
	const headerText = await auto("get the header text");

	// Type in an input using natural language
	await auto('type "Hello World" in the search box');

	// Click elements using natural language
	await auto("click the login button");
});

​
Next Steps