Introducing Stagehand

​

The problem with browser automation

• Too brittle: Traditional selectors break when websites change
• Too agentic: AI agents are unpredictable and impossible to debug

​

Enter Stagehand

// Act: execute natural language actions
await stagehand.act("click the login button");

// Extract: pull structured data
const { data } = await stagehand.extract(
  "extract the price",
  z.object({ price: z.number() }),
);

// Observe: discover available actions
const { data: actions } = await stagehand.observe("find submit buttons");

# Act: execute natural language actions
await stagehand.act("click the login button")

# Extract: pull structured data
class Price(BaseModel):
    price: float

result = await stagehand.extract(
    "extract the price",
    Price,
)
price = result.data.price

# Observe: discover available actions
actions = (await stagehand.observe("find submit buttons")).data

// ctx and client come from the quickstart

// Act: execute natural language actions
actResult, err := client.Act(ctx, stagehand.ActInstruction("click the login button"), nil)
if err != nil {
	return err
}
fmt.Println(actResult.Data.Success)

// Extract: pull structured data
type price struct {
	Price float64 `json:"price"`
}
extracted, err := stagehand.Extract[price](ctx, client, "extract the price", nil)
if err != nil {
	return err
}
fmt.Println(extracted.Data.Price)

// Observe: discover available actions
instruction := "find submit buttons"
observed, err := client.Observe(ctx, &instruction, nil)
if err != nil {
	return err
}
fmt.Println(len(observed.Data), "candidate actions")

​

Why developers choose Stagehand

• Precise control: Mix AI-powered actions with deterministic code. You decide exactly how much AI to use.
• The engine runs inside the browser: Act, extract, and observe execute in an in-browser runtime instead of a Node process wrapping Playwright, and clients talk to it over a typed, bidirectional JSON-RPC protocol.
• First-class TypeScript, Python, and Go SDKs: Each client is generated from the same protocol, so every method and option matches across supported languages.
• The AI primitives live on Stagehand: act, extract, and observe are methods on stagehand. They run on the browser’s active page by default, or on a page you pass. Deterministic controls like goto, click, and type stay on page.
• Extraction is typed: extract validates results against a schema you define and hands back fully typed data.
• Models are flexible: Use a supported provider by name or supply your own client-side LLM callback.
• Metrics are built in: Read per-method token usage and inference timing with metrics().

​

Built for modern development

​

Get started in 60 seconds