# Browserbase 发布 Stagehand：面向 Agent 的浏览器 SDK，号称比 Playwright 快 2 倍、节省 80% token

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：wittydeveloper
- 发布时间：2026-09-19 21:15
- AIHOT 分数：52
- AIHOT 链接：https://aihot.news/items/cmu8ezrfq1iy8rogrqy9qpl52
- 原文链接：https://github.com/browserbase/stagehand

## AI 摘要

Browserbase 发布 Stagehand，一个支持 TypeScript、Python 和 Go 的浏览器 SDK，定位是为 AI Agent 提取网页数据和操作网站，在 Browserbase 上运行速度可达等效 Playwright 浏览器的 2 倍、token 利用率提升 80%。

## 正文

Stagehand is the SDK to extract data and interact with any site on the web. Playwright was built for testing. Stagehand is built for agents, in TypeScript, Python, and Go.

Docs · Quickstart · ⭐ Star this repo

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();

Python

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())

Go

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'

Python

pip install stagehand

Go

go get github.com/browserbase/stagehand/packages/sdk-go/v4@v4.0.0

Local runs need Chrome installed. Full setup: Quickstart.

Why Stagehand

Familiar APIs The Playwright-style methods you and your agents already know: goto, click, locator, screenshot.

Token efficiency Hybrid accessibility-tree trimming gives agents exactly the page context they need and nothing more.

Faster in production Stagehand runs as an extension next to the browser, cutting round-trip latency on every action.

Self-healing act, observe, and extract refresh how an action happens when the site changes underneath it.

Built for agents WebMCP, clipboard support, batch commands, deep locators for nested iframes and closed Shadow DOMs, OTel traces.

Three languages One complete browser driver across TypeScript, Python, and Go.

Run it on Browserbase

Point the same script at Browserbase and get 2x faster execution than Playwright cloud equivalent browsers. Configure the Model Gateway so you never wire up a provider, and enable server-side caching to cache repeated actions.

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

const browser = await browserbase.launch({ apiKey: process.env.BROWSERBASE_API_KEY! });

// No model configuration: the Model Gateway picks the cheapest model for each action // cache: true: identical calls come back from Browserbase, no tokens spent const stagehand = await Stagehand.create({ browser, cache: true });

Python

import os

from stagehand import Stagehand, browserbase

browser = await browserbase.launch(api_key=os.environ["BROWSERBASE_API_KEY"])

# No model configuration: the Model Gateway picks the cheapest model for each action # cache=True: identical calls come back from Browserbase, no tokens spent stagehand = await Stagehand.create(browser=browser, cache=True)

Go

browser, err := stagehand.LaunchBrowserbase(ctx, stagehand.BrowserbaseLaunchOptions{ APIKey: os.Getenv("BROWSERBASE_API_KEY"), }) if err != nil { return err }

// No model configuration: the Model Gateway picks the cheapest model for each action // CacheEnabled(true): identical calls come back from Browserbase, no tokens spent cache := stagehand.CacheEnabled(true) client, err := stagehand.Create(ctx, stagehand.CreateOptions{ Browser: browser, Cache: &cache, }) if err != nil { return err }

Verified mode, residential proxies, persistent contexts, and session recordings come with it. Get an API key and learn how to configure your browser here.

Give your coding agent a browser

The hosted Browserbase MCP server puts navigate, act, observe, and extract in any MCP client — no install, no local browser.

claude mcp add --transport http browserbase https://mcp.browserbase.com/mcp \ --header "Authorization: Bearer $BROWSERBASE_API_KEY"

Cursor, Codex, and other MCP clients

{ "mcpServers": { "browserbase": { "url": "https://mcp.browserbase.com/mcp", "headers": { "Authorization": "Bearer YOUR_BROWSERBASE_API_KEY" } } } }

Search and fetch without a browser

Fetch lets you grab the content of any URL as markdown. Search provides fast, token-efficient web search results. Both as a lightweight complement to browser sessions.

import { browserbase } from "@browserbasehq/stagehand";

const { results } = await browserbase.search({ apiKey: process.env.BROWSERBASE_API_KEY!, query: "browser agent frameworks", numResults: 5, });

const fetched = await browserbase.fetch({ apiKey: process.env.BROWSERBASE_API_KEY!, url: results[0].url, format: "markdown", });

console.log(fetched.content);

Docs and resources

Quickstart Empty directory to working automation in three steps

page · locator Playwright-style browser and element APIs

WebMCP Discover and invoke WebMCP tools exposed by web pages

act · extract · observe Browser actions and data extraction with natural language

Search · Fetch Web search and page content without a browser

Migrate from Playwright Port an existing suite

Integrations CrewAI, Mastra, Deep Agents, Vercel AI SDK, Claude Code, Codex

Python SDK · Go SDK Language-specific guides

Ask DeepWiki Ask questions about this codebase

Join the community

Stagehand is built in the open, and the fastest way to shape it is to show up.

⭐ Star this repo — it is how most people find Stagehand

💬 Join the Discord — questions, support, and what we are building next

🐛 Open an issue — bug reports are the most useful contribution

𝕏 Follow @stagehanddev — releases and demos

Contributing

We're focused on improving reliability, extensibility, speed, and cost, in that order. Bug fixes and small improvements are the best way to get started. For anything larger, reach out to Miguel Gonzalez or Paul Klein on Discord first so we can make sure it lands.

Stagehand is a TypeScript, Python, and Go monorepo driven by just:

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

export OPENAI_API_KEY="your-openai-api-key" just example act # runs packages/sdk-ts/examples/act.ts

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

Acknowledgements

We'd like to thank the following people for their major contributions to Stagehand:

Paul Klein

Sean McGuire

Miguel Gonzalez

Sameel Arif

Thomas Katwan

Filip Michalsky

Anirudh Kamath

Jeremy Press

Navid Pour

Nick Sweeting

Sam Finton

Shrey Pandya

Shriya Lolabattu

Alyssa Maruyama

License

Licensed under the MIT License.

Copyright 2026 Browserbase, Inc.

"Stagehand" is a trademark of Browserbase, Inc.