The SDK for browser agents

AI that uses the browser like humans.

Sign in once, keep the session, and pull structured data out the other side.

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

// Cookies persist in ./browser-data, so the next run starts already signed in
const browser = await localBrowser.launch({ userDataDir: "./browser-data" });
const stagehand = await Stagehand.create({
  browser,
  model: { modelName: "openai/gpt-5.4-mini", apiKey: process.env.OPENAI_API_KEY },
});

const [page] = await browser.context.pages();
await page.goto("https://app.example.com/login");

// observe() returns real selectors, so credentials never reach the model
const { data: email } = await stagehand.observe("find the email input");
const { data: password } = await stagehand.observe("find the password input");
await page.locator(email[0].selector).fill(process.env.APP_EMAIL!);
await page.locator(password[0].selector).fill(process.env.APP_PASSWORD!);

// act() self-heals when the site redesigns its form
await stagehand.act("click the sign in button");
await stagehand.act("open the billing page");

// extract() returns schema-validated data
const { data } = await stagehand.extract(
  "extract every invoice in the table",
  z.object({
    invoices: z.array(z.object({ number: z.string(), amount: z.number(), paid: z.boolean() })),
  }),
);

console.log(data.invoices);

await stagehand.close();
await browser.close();

import asyncio
import os

from pydantic import BaseModel
from stagehand import Stagehand, local_browser


class Invoice(BaseModel):
    number: str
    amount: float
    paid: bool


class Invoices(BaseModel):
    invoices: list[Invoice]


async def main() -> None:
    # Cookies persist in ./browser-data, so the next run starts already signed in
    browser = await local_browser.launch(user_data_dir="./browser-data")
    try:
        stagehand = await Stagehand.create(
            browser=browser,
            model="openai/gpt-5.4-mini",
            model_api_key=os.environ["OPENAI_API_KEY"],
        )
        try:
            page = (await browser.context.pages())[0]
            await page.goto("https://app.example.com/login")

            # observe() returns real selectors, so credentials never reach the model
            email = await stagehand.observe("find the email input")
            password = await stagehand.observe("find the password input")
            await page.locator(email.data[0].selector).fill(os.environ["APP_EMAIL"])
            await page.locator(password.data[0].selector).fill(os.environ["APP_PASSWORD"])

            # act() self-heals when the site redesigns its form
            await stagehand.act("click the sign in button")
            await stagehand.act("open the billing page")

            # extract() returns schema-validated data
            result = await stagehand.extract(
                "extract every invoice in the table",
                Invoices,
            )
            print(result.data.invoices)
        finally:
            await stagehand.close()
    finally:
        await browser.close()


asyncio.run(main())

package main

import (
	"context"
	"errors"
	"fmt"
	"log"
	"os"

	stagehand "github.com/browserbase/stagehand/packages/sdk-go/v4"
)

type invoice struct {
	Number string  `json:"number"`
	Amount float64 `json:"amount"`
	Paid   bool    `json:"paid"`
}

type invoices struct {
	Invoices []invoice `json:"invoices"`
}

func main() {
	if err := run(context.Background()); err != nil {
		log.Fatal(err)
	}
}

func run(ctx context.Context) (err error) {
	// Cookies persist in ./browser-data, so the next run starts already signed in
	browser, err := stagehand.LaunchLocalBrowser(ctx, &stagehand.LocalBrowserLaunchOptions{
		UserDataDir: "./browser-data",
	})
	if err != nil {
		return err
	}
	defer func() { err = errors.Join(err, browser.Close(ctx)) }()

	modelAPIKey := os.Getenv("OPENAI_API_KEY")
	client, err := stagehand.Create(ctx, stagehand.CreateOptions{
		Browser: browser,
		Model: &stagehand.ModelConfig{
			ModelName: "openai/gpt-5.4-mini",
			APIKey:    &modelAPIKey,
		},
	})
	if err != nil {
		return err
	}
	defer func() { err = errors.Join(err, client.Close(ctx)) }()

	browserContext, err := browser.Context()
	if err != nil {
		return err
	}
	pages, err := browserContext.Pages(ctx)
	if err != nil {
		return err
	}
	page := pages[0]
	if _, err := page.Goto(ctx, "https://app.example.com/login", nil); err != nil {
		return err
	}

	// Observe returns real selectors, so credentials never reach the model
	emailInstruction := "find the email input"
	email, err := client.Observe(ctx, &emailInstruction, nil)
	if err != nil {
		return err
	}
	if err := page.Locator(email.Data[0].Selector).Fill(ctx, os.Getenv("APP_EMAIL")); err != nil {
		return err
	}

	passwordInstruction := "find the password input"
	password, err := client.Observe(ctx, &passwordInstruction, nil)
	if err != nil {
		return err
	}
	if err := page.Locator(password.Data[0].Selector).Fill(ctx, os.Getenv("APP_PASSWORD")); err != nil {
		return err
	}

	// Act self-heals when the site redesigns its form
	if _, err := client.Act(ctx, stagehand.ActInstruction("click the sign in button"), nil); err != nil {
		return err
	}
	if _, err := client.Act(ctx, stagehand.ActInstruction("open the billing page"), nil); err != nil {
		return err
	}

	// Extract returns data decoded into a Go type
	extracted, err := stagehand.Extract[invoices](
		ctx,
		client,
		"extract every invoice in the table",
		nil,
	)
	if err != nil {
		return err
	}
	fmt.Println(extracted.Data.Invoices)

	return nil
}

Install

pnpm add @browserbasehq/stagehand 'zod@~4.4.3'

pip install stagehand

go get github.com/browserbase/stagehand/packages/sdk-go/[email protected]

Local runs need Chrome installed. Full setup: Quickstart.

This is the beginning of the README. Read the rest at the original. Read the full README ↗