Stagehand is the SDK for browser agents
Docs · Quickstart · ⭐ Star this repo
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
}pnpm add @browserbasehq/stagehand 'zod@~4.4.3'Python
pip install stagehandGo
go get github.com/browserbase/stagehand/packages/sdk-go/v4@v4.0.0Local runs need Chrome installed. Full setup: Quickstart.
Using a coding agent? (Claude Code, Cursor, Codex)
Install the browse CLI and skill instead of using the SDK directly:
npm install -g browse
npx skills add browserbase/stagehand --skill browse
browse open https://example.com --local
browse snapshot
browse get titleNo LLM key or Browserbase account needed for local use. See CLI vs SDK vs hosted MCP for when to use each.
| 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. |
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.
The hosted Browserbase MCP server puts navigate, act, observe, and extract in any MCP client — no install, no local browser. Requires a Browserbase API key.
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" }
}
}
}For local browsing without an API key, use the browse CLI instead.
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);| 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 | Mastra, Deep Agents, Vercel AI SDK, Claude Code, Codex |
| Python SDK · Go SDK | Language-specific guides |
| Ask DeepWiki | Ask questions about this codebase |
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