Go SDK

This documentation is automatically synced from the Go SDK GitHub repository.

What is Stagehand?

Stagehand is a browser automation framework used to control web browsers with natural language and code. By combining the power of AI with the precision of code, Stagehand makes web automation flexible, maintainable, and actually reliable.

Why Stagehand?

Most existing browser automation tools either require you to write low-level code in a framework like Selenium, Playwright, or Puppeteer, or use high-level agents that can be unpredictable in production. By letting developers choose what to write in code vs. natural language (and bridging the gap between the two) Stagehand is the natural choice for browser automations in production.

Choose when to write code vs. natural language: use AI when you want to navigate unfamiliar pages, and use code when you know exactly what you want to do.
Go from AI-driven to repeatable workflows: Stagehand lets you preview AI actions before running them, and also helps you easily cache repeatable actions to save time and tokens.
Write once, run forever: Stagehand’s auto-caching combined with self-healing remembers previous actions, runs without LLM inference, and knows when to involve AI whenever the website changes and your automation breaks.

Installation

import (
	"github.com/browserbase/stagehand-go" // imported as stagehand
)

Or to pin the version:

go get -u 'github.com/browserbase/stagehand-go@v0.17.1'

Requirements

This library requires Go 1.22+.

Usage

The full API of this library can be found in api.md.

package main

import (
	"context"
	"fmt"

	"github.com/browserbase/stagehand-go"
	"github.com/browserbase/stagehand-go/option"
)

func main() {
	// Create a new Stagehand client with your credentials
	client := stagehand.NewClient(
		option.WithBrowserbaseAPIKey("My Browserbase API Key"), // defaults to os.LookupEnv("BROWSERBASE_API_KEY")
		option.WithModelAPIKey("My Model API Key"),             // defaults to os.LookupEnv("MODEL_API_KEY")
	)

	// Start a new browser session
	startResponse, err := client.Sessions.Start(context.TODO(), stagehand.SessionStartParams{
		ModelName: "gpt-5-nano",
	})
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("Session started: %s\n", startResponse.Data.SessionID)

	sessionID := startResponse.Data.SessionID

	// Navigate to a webpage
	_, err = client.Sessions.Navigate(
		context.TODO(),
		sessionID,
		stagehand.SessionNavigateParams{
			URL: "https://news.ycombinator.com",
		},
	)
	if err != nil {
		panic(err.Error())
	}
	fmt.Println("Navigated to Hacker News")

	// Use Observe to find possible actions on the page
	observeResponse, err := client.Sessions.Observe(
		context.TODO(),
		sessionID,
		stagehand.SessionObserveParams{
			Instruction: stagehand.String("find the link to view comments for the top post"),
		},
	)
	if err != nil {
		panic(err.Error())
	}

	actions := observeResponse.Data.Result
	fmt.Printf("Found %d possible actions\n", len(actions))

	if len(actions) == 0 {
		fmt.Println("No actions found")
		return
	}

	// Take the first action returned by Observe
	action := actions[0]
	fmt.Printf("Acting on: %s\n", action.Description)

	// Pass the structured action to Act
	// The action contains selector, description, method, and arguments
	actResponse, err := client.Sessions.Act(
		context.TODO(),
		sessionID,
		stagehand.SessionActParams{
			Input: stagehand.SessionActParamsInputUnion{
				OfAction: &stagehand.ActionParam{
					Description: action.Description,
					Selector:    action.Selector,
					Method:      stagehand.String(action.Method),
					Arguments:   action.Arguments,
				},
			},
		},
	)
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("Act completed: %s\n", actResponse.Data.Result.Message)

	// Extract structured data from the page using a JSON schema
	extractResponse, err := client.Sessions.Extract(
		context.TODO(),
		sessionID,
		stagehand.SessionExtractParams{
			Instruction: stagehand.String("extract the text of the top comment"),
			Schema: map[string]any{
				"type": "object",
				"properties": map[string]any{
					"commentText": map[string]any{
						"type":        "string",
						"description": "The text content of the top comment",
					},
					"author": map[string]any{
						"type":        "string",
						"description": "The username of the comment author",
					},
				},
			},
		},
	)
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("Extracted: %+v\n", extractResponse.Data.Result)

	// Run an autonomous agent to accomplish a goal
	// The agent can navigate, click, type, and interact with pages
	executeResponse, err := client.Sessions.Execute(
		context.TODO(),
		sessionID,
		stagehand.SessionExecuteParams{
			ExecuteOptions: stagehand.SessionExecuteParamsExecuteOptions{
				Instruction: "Find the profile page for the top commenter",
				MaxSteps:    stagehand.Float(10),
			},
			AgentConfig: stagehand.SessionExecuteParamsAgentConfig{
				// Model config with provider/model format and API key
				Model: stagehand.ModelConfigUnionParam{
					OfModelConfigModelConfigObject: &stagehand.ModelConfigModelConfigObjectParam{
						ModelName: "openai/gpt-4.1-mini",
						APIKey:    stagehand.String("sk-your-api-key"),
					},
				},
				Cua: stagehand.Bool(false),
			},
		},
	)
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("Agent result: %s\n", executeResponse.Data.Result.Message)

	// End the session to clean up resources
	_, err = client.Sessions.End(
		context.TODO(),
		sessionID,
		stagehand.SessionEndParams{},
	)
	if err != nil {
		panic(err.Error())
	}
	fmt.Println("Session ended")
}

Running the example

A complete working example is available in examples/basic.go. To run it:

Set up environment variables by creating a .env file in the repository root:

BROWSERBASE_API_KEY=your_browserbase_api_key
MODEL_API_KEY=your_openai_api_key

You can get your Browserbase API key from the Browserbase dashboard.

Install dependencies:

go mod tidy

Run the example:

go run examples/basic.go

The example demonstrates the full Stagehand workflow: starting a session, navigating to a page, observing actions, clicking elements, extracting data, and running an autonomous agent.

Request fields

The stagehand library uses the omitzero semantics from the Go 1.24+ encoding/json release for request fields. Required primitive fields (int64, string, etc.) feature the tag json:"...,required". These fields are always serialized, even their zero values. Optional primitive types are wrapped in a param.Opt[T]. These fields can be set with the provided constructors, stagehand.String(string), stagehand.Int(int64), etc. Any param.Opt[T], map, slice, struct or string enum uses the tag json:"...,omitzero". Its zero value is considered omitted. The param.IsOmitted(any) function can confirm the presence of any omitzero field.

p := stagehand.ExampleParams{
	ID:   "id_xxx",                // required property
	Name: stagehand.String("..."), // optional property

	Point: stagehand.Point{
		X: 0,                // required field will serialize as 0
		Y: stagehand.Int(1), // optional field will serialize as 1
		// ... omitted non-required fields will not be serialized
	},

	Origin: stagehand.Origin{}, // the zero value of [Origin] is considered omitted
}

To send null instead of a param.Opt[T], use param.Null[T](). To send null instead of a struct T, use param.NullStruct[T]().

p.Name = param.Null[string]()       // 'null' instead of string
p.Point = param.NullStruct[Point]() // 'null' instead of struct

param.IsNull(p.Name)  // true
param.IsNull(p.Point) // true

Request structs contain a .SetExtraFields(map[string]any) method which can send non-conforming fields in the request body. Extra fields overwrite any struct fields with a matching key. For security reasons, only use SetExtraFields with trusted data. To send a custom value instead of a struct, use param.Override[T](https://github.com/browserbase/stagehand-go/blob/main/value).

// In cases where the API specifies a given type,
// but you want to send something else, use [SetExtraFields]:
p.SetExtraFields(map[string]any{
	"x": 0.01, // send "x" as a float instead of int
})

// Send a number instead of an object
custom := param.Override[stagehand.FooParams](https://github.com/browserbase/stagehand-go/blob/main/12)

Request unions

Unions are represented as a struct with fields prefixed by “Of” for each of its variants, only one field can be non-zero. The non-zero field will be serialized. Sub-properties of the union can be accessed via methods on the union struct. These methods return a mutable pointer to the underlying data, if present.

// Only one field can be non-zero, use param.IsOmitted() to check if a field is set
type AnimalUnionParam struct {
	OfCat *Cat `json:",omitzero,inline`
	OfDog *Dog `json:",omitzero,inline`
}

animal := AnimalUnionParam{
	OfCat: &Cat{
		Name: "Whiskers",
		Owner: PersonParam{
			Address: AddressParam{Street: "3333 Coyote Hill Rd", Zip: 0},
		},
	},
}

// Mutating a field
if address := animal.GetOwner().GetAddress(); address != nil {
	address.ZipCode = 94304
}

Response objects

All fields in response structs are ordinary value types (not pointers or wrappers). Response structs also include a special JSON field containing metadata about each property.

type Animal struct {
	Name   string `json:"name,nullable"`
	Owners int    `json:"owners"`
	Age    int    `json:"age"`
	JSON   struct {
		Name        respjson.Field
		Owner       respjson.Field
		Age         respjson.Field
		ExtraFields map[string]respjson.Field
	} `json:"-"`
}

To handle optional data, use the .Valid() method on the JSON field. .Valid() returns true if a field is not null, not present, or couldn’t be marshaled. If .Valid() is false, the corresponding field will simply be its zero value.

raw := `{"owners": 1, "name": null}`

var res Animal
json.Unmarshal([]byte(raw), &res)

// Accessing regular fields

res.Owners // 1
res.Name   // ""
res.Age    // 0

// Optional field checks

res.JSON.Owners.Valid() // true
res.JSON.Name.Valid()   // false
res.JSON.Age.Valid()    // false

// Raw JSON values

res.JSON.Owners.Raw()                  // "1"
res.JSON.Name.Raw() == "null"          // true
res.JSON.Name.Raw() == respjson.Null   // true
res.JSON.Age.Raw() == ""               // true
res.JSON.Age.Raw() == respjson.Omitted // true

These .JSON structs also include an ExtraFields map containing any properties in the json response that were not specified in the struct. This can be useful for API features not yet present in the SDK.

body := res.JSON.ExtraFields["my_unexpected_field"].Raw()

Response Unions

In responses, unions are represented by a flattened struct containing all possible fields from each of the object variants. To convert it to a variant use the .AsFooVariant() method or the .AsAny() method if present. If a response value union contains primitive values, primitive fields will be alongside the properties but prefixed with Of and feature the tag json:"...,inline".

type AnimalUnion struct {
	// From variants [Dog], [Cat]
	Owner Person `json:"owner"`
	// From variant [Dog]
	DogBreed string `json:"dog_breed"`
	// From variant [Cat]
	CatBreed string `json:"cat_breed"`
	// ...

	JSON struct {
		Owner respjson.Field
		// ...
	} `json:"-"`
}

// If animal variant
if animal.Owner.Address.ZipCode == "" {
	panic("missing zip code")
}

// Switch on the variant
switch variant := animal.AsAny().(type) {
case Dog:
case Cat:
default:
	panic("unexpected type")
}

RequestOptions

This library uses the functional options pattern. Functions defined in the option package return a RequestOption, which is a closure that mutates a RequestConfig. These options can be supplied to the client or at individual requests. For example:

client := stagehand.NewClient(
	// Adds a header to every request made by the client
	option.WithHeader("X-Some-Header", "custom_header_info"),
)

client.Sessions.Start(context.TODO(), ...,
	// Override the header
	option.WithHeader("X-Some-Header", "some_other_custom_header_info"),
	// Add an undocumented field to the request body, using sjson syntax
	option.WithJSONSet("some.json.path", map[string]string{"my": "object"}),
)

The request option option.WithDebugLog(nil) may be helpful while debugging. See the full list of request options.

Errors

When the API returns a non-success status code, we return an error with type *stagehand.Error. This contains the StatusCode, *http.Request, and *http.Response values of the request, as well as the JSON of the error body (much like other response objects in the SDK). To handle errors, we recommend that you use the errors.As pattern:

_, err := client.Sessions.Start(context.TODO(), stagehand.SessionStartParams{
	ModelName: "openai/gpt-5-nano",
})
if err != nil {
	var apierr *stagehand.Error
	if errors.As(err, &apierr) {
		println(string(apierr.DumpRequest(true)))  // Prints the serialized HTTP request
		println(string(apierr.DumpResponse(true))) // Prints the serialized HTTP response
	}
	panic(err.Error()) // GET "/v1/sessions/start": 400 Bad Request { ... }
}

When other errors occur, they are returned unwrapped; for example, if HTTP transport fails, you might receive *url.Error wrapping *net.OpError.

Timeouts

Requests do not time out by default; use context to configure a timeout for a request lifecycle. Note that if a request is retried, the context timeout does not start over. To set a per-retry timeout, use option.WithRequestTimeout().

// This sets the timeout for the request, including all the retries.
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
defer cancel()
client.Sessions.Start(
	ctx,
	stagehand.SessionStartParams{
		ModelName: "openai/gpt-5-nano",
	},
	// This sets the per-retry timeout
	option.WithRequestTimeout(20*time.Second),
)

Retries

Certain errors will be automatically retried 2 times by default, with a short exponential backoff. We retry by default all connection errors, 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors. You can use the WithMaxRetries option to configure or disable this:

// Configure the default for all requests:
client := stagehand.NewClient(
	option.WithMaxRetries(0), // default is 2
)

// Override per-request:
client.Sessions.Start(
	context.TODO(),
	stagehand.SessionStartParams{
		ModelName: "openai/gpt-5-nano",
	},
	option.WithMaxRetries(5),
)

Accessing raw response data (e.g. response headers)

You can access the raw HTTP response data by using the option.WithResponseInto() request option. This is useful when you need to examine response headers, status codes, or other details.

// Create a variable to store the HTTP response
var response *http.Response
response, err := client.Sessions.Start(
	context.TODO(),
	stagehand.SessionStartParams{
		ModelName: "openai/gpt-5-nano",
	},
	option.WithResponseInto(&response),
)
if err != nil {
	// handle error
}
fmt.Printf("%+v\n", response)

fmt.Printf("Status Code: %d\n", response.StatusCode)
fmt.Printf("Headers: %+#v\n", response.Header)

Making custom/undocumented requests

This library is typed for convenient access to the documented API. If you need to access undocumented endpoints, params, or response properties, the library can still be used.

Undocumented endpoints

To make requests to undocumented endpoints, you can use client.Get, client.Post, and other HTTP verbs. RequestOptions on the client, such as retries, will be respected when making these requests.

var (
    // params can be an io.Reader, a []byte, an encoding/json serializable object,
    // or a "…Params" struct defined in this library.
    params map[string]any

    // result can be an []byte, *http.Response, a encoding/json deserializable object,
    // or a model defined in this library.
    result *http.Response
)
err := client.Post(context.Background(), "/unspecified", params, &result)
if err != nil {
    …
}

Undocumented request params

To make requests using undocumented parameters, you may use either the option.WithQuerySet() or the option.WithJSONSet() methods.

params := FooNewParams{
    ID:   "id_xxxx",
    Data: FooNewParamsData{
        FirstName: stagehand.String("John"),
    },
}
client.Foo.New(context.Background(), params, option.WithJSONSet("data.last_name", "Doe"))

Undocumented response properties

To access undocumented response properties, you may either access the raw JSON of the response as a string with result.JSON.RawJSON(), or get the raw JSON of a particular field on the result with result.JSON.Foo.Raw(). Any fields that are not present on the response struct will be saved and can be accessed by result.JSON.ExtraFields() which returns the extra fields as a map[string]Field.

Middleware

We provide option.WithMiddleware which applies the given middleware to requests.

func Logger(req *http.Request, next option.MiddlewareNext) (res *http.Response, err error) {
	// Before the request
	start := time.Now()
	LogReq(req)

	// Forward the request to the next handler
	res, err = next(req)

	// Handle stuff after the request
	end := time.Now()
	LogRes(res, err, start - end)

    return res, err
}

client := stagehand.NewClient(
	option.WithMiddleware(Logger),
)

When multiple middlewares are provided as variadic arguments, the middlewares are applied left to right. If option.WithMiddleware is given multiple times, for example first in the client then the method, the middleware in the client will run first and the middleware given in the method will run next. You may also replace the default http.Client with option.WithHTTPClient(client). Only one http client is accepted (this overwrites any previous client) and receives requests after any middleware has been applied.

Semantic versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience. We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

Contributing

See the contributing documentation.

SDK Reference

API Reference

What is Stagehand?

Why Stagehand?

Installation

Requirements

Usage

Running the example

Request fields

Request unions

Response objects

Response Unions

RequestOptions

Errors

Timeouts

Retries

Accessing raw response data (e.g. response headers)

Making custom/undocumented requests

Undocumented endpoints

Undocumented request params

Undocumented response properties

Middleware

Semantic versioning

Contributing

​What is Stagehand?

​Why Stagehand?

​Installation

​Requirements

​Usage

​Running the example

​Request fields

​Request unions

​Response objects

​Response Unions

​RequestOptions

​Errors

​Timeouts

​Retries

​Accessing raw response data (e.g. response headers)

​Making custom/undocumented requests

​Undocumented endpoints

​Undocumented request params

​Undocumented response properties

​Middleware

​Semantic versioning

​Contributing

What is Stagehand?

Why Stagehand?

Installation

Requirements

Usage

Running the example

Request fields

Request unions

Response objects

Response Unions

RequestOptions

Errors

Timeouts

Retries

Accessing raw response data (e.g. response headers)

Making custom/undocumented requests

Undocumented endpoints

Undocumented request params

Undocumented response properties

Middleware

Semantic versioning

Contributing