Stagehand

There’s a new way to automate the web: by prompting. Stagehand is the SDK that gives agents the tools they need to navigate the web. Build with self-healing browser primitives that adapt when websites change. Use any major model provider. 22k GitHub stars, 700k+ weekly downloads. Get started in 5 minutes.

This quickstart uses Model Gateway. LLM requests for Stagehand route through your Browserbase API key, so you don’t need a separate model provider account. You can also bring your own API key if you prefer.

Discord

Community support

Docs

Full documentation

Templates

Ready-to-use examples

Quickstart

Get your API key

Your API key is displayed in the Dashboard Navigation row. The API key is all you need to get started. The project is inferred from your API key.

Set environment variables

export BROWSERBASE_API_KEY="your-api-key"

Install and run

Node.js
Python
Go

pnpm add @browserbasehq/stagehand zod
npm pkg set type=module

npm install @browserbasehq/stagehand zod
npm pkg set type=module

Node.js

import { browserbase, Stagehand } from "@browserbasehq/stagehand";
import { z } from "zod/v4";

const browser = await browserbase.launch({
  apiKey: process.env.BROWSERBASE_API_KEY,
});

try {
  const stagehand = await Stagehand.create({ browser });

  try {
    const [page] = await browser.context.pages();
    await page.goto("https://news.ycombinator.com");

    await stagehand.act("Click the comments link for the top story");

    const result = await stagehand.extract(
      "Extract the title and points of the top story",
      z.object({
        title: z.string(),
        points: z.string(),
      }),
    );
    console.log(result.data);
  } finally {
    await stagehand.close();
  }
} finally {
  await browser.close();
}

Save as script.ts, then run:

pnpm dlx tsx script.ts

npx tsx script.ts

uv init
uv add stagehand pydantic

Python

import asyncio
import os

from pydantic import BaseModel
from stagehand import Stagehand, browserbase


class Story(BaseModel):
    title: str
    points: str


async def main() -> None:
    browser = await browserbase.launch(
        api_key=os.environ["BROWSERBASE_API_KEY"]
    )

    try:
        stagehand = await Stagehand.create(browser=browser)

        try:
            page = (await browser.context.pages())[0]
            await page.goto("https://news.ycombinator.com")

            await stagehand.act("Click the comments link for the top story")

            result = await stagehand.extract(
                "Extract the title and points of the top story", Story
            )
            print(result.data)
        finally:
            await stagehand.close()
    finally:
        await browser.close()


asyncio.run(main())

Save as script.py, then run:

uv run script.py

Debug in Session Inspector

See every AI decision in the Stagehand tab of your session at https://browserbase.com/sessions/{session_id}.

Expected output

The script prints extracted title and points fields for the top Hacker News story. These values change over time; compare them with the page in the Session Inspector.

Cleanup

Both examples close Stagehand and the browser in finally. If you interrupt the process before cleanup completes, release the session using Manage browser sessions. These examples create no persistent browser context or output file.

Next steps

Stagehand docs

Learn about Stagehand primitives, models, and Browserbase configurations

npx create-browser-app

Scaffold a Stagehand project in one command. TypeScript, zero-config.

⌘I

Welcome

Platform

Use cases

Optimization

Account

Discord

Docs

Templates

Quickstart

Expected output

Cleanup

Next steps

Stagehand docs

npx create-browser-app

Discord

Docs

Templates

​Quickstart

​Expected output

​Cleanup

​Next steps

Stagehand docs

npx create-browser-app

Quickstart

Expected output

Cleanup

Next steps