# Quickstart Guide

Get up and running with **Browser Swarm** in just a few minutes. This guide walks you through creating your first browser session and interacting with a webpage using our platform.

***

### 📝 Step 1: Create an Account

Start by signing up for a free **Browser Swarm** account. Once registered, you'll have access to the dashboard where you can:

* Manage your sessions
* View usage metrics
* Access your Project ID & API Key

***

### 📦 Step 2: Install the SDK (Optional)

Browser Swarm supports multiple languages. Install the SDK for your preferred environment:

**Node.js:**

```bash
npm install browser-swarm-sdk
```

**Python:**

```bash
pip install browser-swarm
```

***

### 🧪 Step 3: Launch a Browser Session

You can launch a session using the SDK or directly through our API.

**Node.js Example:**

```javascript
import { createSession } from 'browser-swarm-sdk';

const session = await createSession({
  browser: 'chromium',
  headless: true,
  url: 'https://example.com'
});
```

***

### 🧭 Step 4: Interact With the Page

Use your automation framework of choice to control the browser session:

```javascript
await session.page.click('#login');
await session.page.type('#username', 'yourUser');
await session.page.type('#password', 'yourPass');
await session.page.click('#submit');
```

Supports Playwright, Puppeteer, and Selenium.

***

### 📺 Step 5: Monitor or End Session

You can:

* Monitor sessions in real time via the dashboard
* Programmatically end sessions when tasks are complete

```javascript
await session.close();
```

***

### ✅ You're Ready!

You’ve just launched and automated your first headless browser with **Browser Swarm**. You're now ready to:

* Use stealth mode and proxies
* Integrate with AI agents
* Handle downloads, screenshots, and more

Explore the rest of the documentation to unlock the full power of **Browser Swarm**.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://browserswarm.gitbook.io/docs/quickstart-guide.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.