> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/hyperbrowser.md).

# HyperBrowser

Hyperbrowser provides cloud browsers for AI agents. Connect to drive a browser, run authenticated crawls, and manage sessions and profiles from your AI workflows.

### Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector    | Authentication |
| ------------ | -------------- |
| Hyperbrowser | API Key        |

#### Hyperbrowser

Connect to Hyperbrowser to use their browser automation service.

**Set up in HyperBrowser**

1. Sign up for [Hyperbrowser](https://app.hyperbrowser.ai) and open your dashboard.
2. Find your API key on the dashboard (create one if prompted).
3. Copy the API key and store it securely.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Hyperbrowser**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                            |
| ------------- | -------- | -------------------------------------------------------------------------------------------------------- |
| API Key       | Yes      | Find your API key in your Hyperbrowser dashboard. [Provider instructions](https://app.hyperbrowser.ai/). |

**Provider documentation:** [Setup reference](https://docs.hyperbrowser.ai/get-started/quickstart).

#### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

#### Detailed setup guides

* [Connect HyperBrowser](https://docs.stackai.com/integrations/catalog/hyperbrowser/connect-hyperbrowser.md)

## Use an action

1. Add the required **HyperBrowser** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

### Actions

#### Use Browser

Use this tool for browser automation: This means the AI agent will open a web browser and complete tasks that require interacting with websites like a human would. With this tool, the LLM can click buttons, fill forms, navigate pages, and extract information from websites.

**Inputs**

| Field             | Type    | Required | Description                                                                            |
| ----------------- | ------- | -------- | -------------------------------------------------------------------------------------- |
| Task              | string  | Yes      | The task to perform in the browser. Default: .                                         |
| Session ID        | string  | No       | The ID of the session to use for the browser. If empty, a new session will be created. |
| Max Failures      | integer | No       | The maximum number of failures to allow before stopping the browser. Default: 1.       |
| Max Steps         | integer | No       | The maximum number of steps to allow before stopping the browser. Default: 25.         |
| Keep Browser Open | boolean | No       | Whether to keep the browser open after the task is completed. Default: false.          |
| Solve Captchas    | boolean | No       | Whether to automatically solve CAPTCHAs during the session. Default: false.            |
| Use Stealth       | boolean | No       | Whether to enable stealth mode to avoid bot detection. Default: false.                 |

**Outputs**

| Field           | Type    | Description                                                                                                  |
| --------------- | ------- | ------------------------------------------------------------------------------------------------------------ |
| Job ID          | string  | The ID of the job that was created.                                                                          |
| Live URL        | string  | The URL of the live browser session.                                                                         |
| Session ID      | string  | The ID of the browser session. Use this ID to continue using the same session in subsequent browser actions. |
| Status          | string  | The status of the job.                                                                                       |
| Final Result    | string  | The final result of the browser use task.                                                                    |
| Error           | string  | The error message if the browser use task failed.                                                            |
| Session Stopped | boolean | Whether the browser session was stopped after completion.                                                    |

#### Authenticated Crawl

Use this tool to crawl a website that requires authentication.

**Inputs**

| Field            | Type    | Required | Description                                                                                                         |
| ---------------- | ------- | -------- | ------------------------------------------------------------------------------------------------------------------- |
| URL              | string  | Yes      | The URL to start crawling from. Default: .                                                                          |
| Profile ID       | string  | Yes      | Hyperbrowser profile ID to use for the authenticated crawl. Docs: <https://docs.hyperbrowser.ai/sessions/profiles>. |
| Max Pages        | integer | No       | The maximum number of pages to crawl. Default: 10.                                                                  |
| Include Patterns | array   | No       | The patterns to include in the crawl.                                                                               |
| Exclude Patterns | array   | No       | URL patterns to exclude (e.g. \*/logout\*, \*/signout\*).                                                           |

**Outputs**

| Field               | Type    | Description                            |
| ------------------- | ------- | -------------------------------------- |
| Job ID              | string  | The ID of the crawl job.               |
| Status              | string  | The status of the crawl job.           |
| Total Crawled Pages | integer | Total number of pages crawled.         |
| Pages               | string  | The pages crawled.                     |
| Error               | string  | Error message if the crawl job failed. |

#### Create Session

Create a new HyperBrowser session with custom configuration.

**Inputs**

| Field             | Type    | Required | Description                                                                   |
| ----------------- | ------- | -------- | ----------------------------------------------------------------------------- |
| Use Stealth       | boolean | No       | Whether to use stealth mode to avoid detection. Default: false.               |
| Use Proxy         | boolean | No       | Whether to use a proxy for the session. Default: false.                       |
| Proxy Country     | string  | No       | Country code for proxy (e.g., 'US', 'GB'). Only used when use\_proxy is True. |
| Device Types      | array   | No       | Device types to emulate (desktop, mobile).                                    |
| Browser Platform  | array   | No       | Browser platforms to use (chrome, firefox, safari, edge).                     |
| Screen Width      | integer | No       | Screen width in pixels. Default: 1280.                                        |
| Screen Height     | integer | No       | Screen height in pixels. Default: 720.                                        |
| Solve Captchas    | boolean | No       | Whether to automatically solve captchas. Default: false.                      |
| Accept Cookies    | boolean | No       | Whether to automatically accept cookies. Default: false.                      |
| Profile ID        | string  | No       | Profile ID to use for the session.                                            |
| Persist Changes   | boolean | No       | Whether to persist profile changes. Default: true.                            |
| Timeout (minutes) | integer | No       | Session timeout in minutes (1-720). Default: 60.                              |

**Outputs**

| Field              | Type   | Description                           |
| ------------------ | ------ | ------------------------------------- |
| Session ID         | string | The ID of the created session.        |
| Session URL        | string | The URL to access the session.        |
| Live URL           | string | The live browser session URL.         |
| Status             | string | The status of the session.            |
| Token              | string | Authentication token for the session. |
| WebSocket Endpoint | string | WebSocket endpoint for the session.   |

#### Get Sessions

Get a list of HyperBrowser sessions with optional filtering and pagination.

**Inputs**

| Field          | Type    | Required | Description                                          |
| -------------- | ------- | -------- | ---------------------------------------------------- |
| Page Number    | integer | No       | Page number for pagination (default: 1). Default: 1. |
| Session Status | string  | No       | Filter sessions by status (active, closed, error).   |

**Outputs**

| Field        | Type    | Description                                   |
| ------------ | ------- | --------------------------------------------- |
| Sessions     | string  | List of sessions.                             |
| Total Count  | integer | Total number of sessions matching the filter. |
| Current Page | integer | Current page number.                          |
| Page Size    | integer | Number of sessions per page.                  |

#### Stop Session

Stop a running HyperBrowser session.

**Inputs**

| Field      | Type   | Required | Description                               |
| ---------- | ------ | -------- | ----------------------------------------- |
| Session ID | string | Yes      | The ID of the session to stop. Default: . |

**Outputs**

| Field   | Type    | Description                                    |
| ------- | ------- | ---------------------------------------------- |
| Success | boolean | Whether the session was successfully stopped.  |
| Message | string  | Additional message about the operation result. |

#### List Profiles

Get a list of HyperBrowser profiles with optional filtering and pagination.

**Inputs**

| Field | Type    | Required | Description                                                    |
| ----- | ------- | -------- | -------------------------------------------------------------- |
| Page  | integer | No       | Page number for pagination (default: 1). Default: 1.           |
| Limit | integer | No       | Limit number of profiles to return (default: 10). Default: 10. |
| Name  | string  | No       | Name of the profile to filter by.                              |

**Outputs**

| Field       | Type          | Description                  |
| ----------- | ------------- | ---------------------------- |
| Profiles    | object\_array | List of profiles.            |
| Total Count | integer       | Total number of profiles.    |
| Page        | integer       | Page number.                 |
| Per Page    | integer       | Number of profiles per page. |

#### Create Profile

Create a new HyperBrowser profile.

**Inputs**

| Field | Type   | Required | Description                                   |
| ----- | ------ | -------- | --------------------------------------------- |
| Name  | string | Yes      | The name of the profile to create. Default: . |

**Outputs**

| Field      | Type   | Description                      |
| ---------- | ------ | -------------------------------- |
| Profile ID | string | The ID of the created profile.   |
| Name       | string | The name of the created profile. |

### Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/hyperbrowser.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
