Stagehand

Package

SDK for AI browser automation with act, extract and observe calls

Price: Free, open source
Access: LLM API key

About

Stagehand is an MIT-licensed SDK from Browserbase for TypeScript, Python and Go that mixes plain code with natural-language browser actions. It drives local Chrome or Browserbase cloud browsers over CDP and needs an LLM API key.

What you can do with it

Click, type and navigate with natural-language instructions in code
Extract structured data from a page into a Zod or Pydantic schema
Mix fixed Playwright-style steps with AI steps in one script

Get started

Install @browserbasehq/stagehand and zod@~4.4.3
Install Chrome, or use a Browserbase API key for cloud browsers
Set your LLM provider's API key, e.g. OPENAI_API_KEY

Example

import { localBrowser, Stagehand } from "@browserbasehq/stagehand";

const browser = await localBrowser.launch();
const stagehand = await Stagehand.create({
  browser,
  model: { modelName: "openai/gpt-5.6-sol", apiKey: process.env.OPENAI_API_KEY },
});
const [page] = await browser.context.pages();
await page.goto("https://stagehand.dev");
await stagehand.act("Click the 'Evals' button.");
await stagehand.close();
await browser.close();

Details

Hosting: Runs locally
Available in: Worldwide
Official SDKs: JavaScript/TypeScript, Python, Go
MCP server: None