Documentation Index Fetch the complete documentation index at: https://stagehand-shrey-check-v3-metrics-docs.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Install Stagehand in your current app with the TypeScript or Python SDK.
For TypeScript/Node.js: We highly recommend using the Node.js runtime environment to run Stagehand scripts, as opposed to newer alternatives like Deno or Bun. Bun does not support Stagehand since it doesn’t support Playwright .For Python: We require Python 3.9+ and recommend using uv to manage your virtual environment. Install dependencies npm install @browserbasehq/stagehand playwright zod
If you plan to run locally, install browsers once: npx playwright install.
For cloud browser sessions, skip this.
Configure environment Set environment variables (or a .env via your framework): OPENAI_API_KEY = your_api_key BROWSERBASE_API_KEY = your_api_key BROWSERBASE_PROJECT_ID = your_project_id
Use in your codebase Add Stagehand where you need browser automation. import "dotenv/config" ; import { Stagehand } from "@browserbasehq/stagehand" ; import { z } from "zod/v3" ; async function main () { const stagehand = new Stagehand ({ env: "BROWSERBASE" }); await stagehand . init (); const page = stagehand . page ; await page . goto ( "https://example.com" ); // Act on the page await page . act ( "Click the sign in button" ); // Extract structured data const { title } = await page . extract ({ instruction: "extract the page title" , schema: z . object ({ title: z . string (), }), }); console . log ( title ); await stagehand . close (); } main (). catch (( err ) => { console . error ( err ); process . exit ( 1 ); });
Add dependencies Configure environment Set environment variables (or a .env via your framework): MODEL_API_KEY = your_api_key BROWSERBASE_API_KEY = your_api_key BROWSERBASE_PROJECT_ID = your_project_id
Use in your codebase import os import asyncio from stagehand import Stagehand async def main (): stagehand = Stagehand( env = "BROWSERBASE" , model_api_key = os.getenv( "MODEL_API_KEY" ) ) await stagehand.init() page = stagehand.page await page.goto( "https://example.com" ) # Act on the page await page.act( "Click the sign in button" ) # Extract structured data result = await page.extract({ "instruction" : "extract the page title" , "schema" : { "title" : { "type" : "string" } } }) print (result[ "title" ]) await stagehand.close() if __name__ == "__main__" : asyncio.run(main())
Next steps
Configuration Environment, Browserbase vs Local, logging, timeouts, LLM customization
Act Perform precise actions with natural language
Extract Typed data extraction with Zod schemas
Observe Discover elements and suggested actions
