Selenium

npm install @browserbasehq/stagehand selenium-webdriver @browserbasehq/sdk

import http from "http";
import { Builder, Key } from "selenium-webdriver";
import Browserbase from "@browserbasehq/sdk";
import { Stagehand } from "@browserbasehq/stagehand";

const bb = new Browserbase({
  apiKey: process.env.BROWSERBASE_API_KEY,
});

// Create shared session
const session = await bb.sessions.create({});

console.log("Session created:", session.id);

const stagehand = new Stagehand({
  env: "BROWSERBASE",
  browserbaseSessionID: session.id,
  model: "openai/gpt-5",
  verbose: 2,
});

await stagehand.init();

// Create custom HTTP agent with signing key
const customHttpAgent = new http.Agent({});
(customHttpAgent as any).addRequest = (req: any, options: any) => {
  req.setHeader("x-bb-signing-key", session.signingKey);
  (http.Agent.prototype as any).addRequest.call(customHttpAgent, req, options);
};

// Connect Selenium WebDriver
const driver = new Builder()
  .forBrowser("chrome")
  .usingHttpAgent(customHttpAgent)
  .usingServer(session.seleniumRemoteUrl)
  .build();

// Navigate with Stagehand
const page = stagehand.context.pages()[0];
await page.goto("https://www.google.com");

// Extract page content with Stagehand AI
const pageContent = await stagehand.extract();
console.log("Page content:", pageContent);

// Use Selenium for precise element interaction
const searchBox = await driver.findElement({ name: "q" });
await searchBox.sendKeys("Browserbase automation");
await searchBox.sendKeys(Key.RETURN);

// Wait for results
await driver.sleep(2000);

console.log("Search completed!");