Stagehand — Agents-OSS

Overview

Lets you write deterministic Playwright for the steps you already know and drop into natural language only where the page is unpredictable. That mix is the pragmatic middle ground: fully AI-driven automation is slow and flaky, fully scripted automation breaks on redesigns.

What can you do with Stagehand?

Mix natural language with locators — stagehand.act("click on the stagehand repo") handles a step you cannot predict, while observe() hands back concrete selectors you can replay deterministically through Playwright-style page.locator(...).click().
Extract page data to a schema — stagehand.extract() takes a Zod schema and returns exactly the fields you declared, so page content arrives as typed values rather than text you parse yourself.
Survive site redesigns — act, observe and extract are self-healing: when a site changes, Stagehand detects it and refreshes how the action is carried out instead of failing on a selector that no longer matches.
Reach into nested DOM structures — Deep locators reach inside out-of-process iframes and closed Shadow DOM, which ordinary automation cannot cross, and clipboard support and batch commands come alongside.
Work in TypeScript, Python or Go — One browser driver ships as three SDKs — @browserbasehq/stagehand on npm plus packages/sdk-python and packages/sdk-go in the same monorepo — which just install and just build compile together.

Documentation

Reproduced from the browserbase/stagehand README, published under MIT. Read the original ↗

What is Stagehand?

Stagehand is the SDK for browser agents. Playwright was built for testing, Stagehand is built for agents. Use familiar APIs, self-healing actions, and network-level security across TypeScript, Python, and Go.

Why Stagehand?

Stagehand gives browser agents an interface built for how they actually work. It combines familiar Playwright-style APIs with self-healing actions, agent-optimized page context, and native support for complex DOM structures like out-of-process iframes and closed Shadow DOMs.

Agents use fewer tokens, recover when websites change, and complete tasks more reliably. With a complete browser driver across TypeScript, Python, and Go, Stagehand delivers the flexibility of AI without sacrificing the speed, control, determinism, reliability, and observability required in production.

1. Familiar APIs

The Playwright-style methods you and your agents already know and love (goto, click, locator, screenshot).

2. Token efficiency as a priority

Stagehand’s hybrid accessibility tree trimming gives your agents exactly what they need to understand the page and nothing more.

3. Faster in production

Stagehand runs as an extension next to the browser, closing the distance and reducing round-trip latency for all actions on the page.

4. Self-healing primitives

Use act, observe, and extract with natural language to automate pages. When sites change, Stagehand detects it and refreshes how the actions happen on the page automatically.

5. Features agents need

WebMCP, clipboard support, self-healing actions, batch commands, deep locators for nested iframes, and OTel support.

Getting Started

Check out our Quickstart Guide for more information:

Example

Here’s how to build a sample browser automation with Stagehand:

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

const { BROWSERBASE_API_KEY, OPENAI_API_KEY } = process.env;

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

const stagehand = await Stagehand.create({
  browser,
  model: {
    modelName: "openai/gpt-5.4-mini",
    apiKey: OPENAI_API_KEY,
  },
});

// Stagehand's CDP engine provides an optimized, low level interface to the browser built for automation
const [page] = await browser.context.pages();
await page.goto("https://github.com/browserbase");

// Use act() to execute individual actions
await stagehand.act("click on the stagehand repo");

// Use observe() to see what's actionable on the page
const { data: actions } = await stagehand.observe("find the latest PR");

// Use locators for deterministic Playwright-style actions
await page.locator(actions[0].selector).click();

// Use extract() to get structured data from the page
const {
  data: { author, title },
} = await stagehand.extract(
  "extract the author and title of the PR",
  z.object({
    author: z.string().describe("The username of the PR author"),
    title: z.string().describe("The title of the PR"),
  }),
);

See the Python and Go READMEs for equivalent examples.

Documentation

Visit docs.stagehand.dev to view the full documentation.

Build and Run from Source

Stagehand is a TypeScript, Python, and Go monorepo. We use just to drive pnpm, uv, and go together.

git clone https://github.com/browserbase/stagehand.git
cd stagehand
just install
just generate
just build

Stagehand is best when you have an API key for an LLM provider and Browserbase credentials. Export them so they’re available on process.env:

export OPENAI_API_KEY="your-openai-api-key"
export BROWSERBASE_API_KEY="your-browserbase-api-key"

Then run any of the scripts in packages/sdk-ts/examples:

just example act # runs packages/sdk-ts/examples/act.ts

See CONTRIBUTING.md for the full TypeScript, Python, and Go setup.