HyperBrowser

Learn how to automate browser tasks with the HyperBrowser node in StackAI. Discover available actions, required inputs, configurations, and output details.

HyperBrowser is a StackAI integration that enables you to automate and control browser-based tasks programmatically. It is ideal for scenarios such as web automation, scraping, testing, and simulating user interactions on websites.


How to use HyperBrowser

First, create a connection to HyperBrowser if you are using it for the first time. You must have a HyperBrowser account.

In HyperBrowser, select Settings and then select API Keys. Create a new key and copy/paste the key into the new connection window in your StackAI workflow. Your connection will now be saved and can be reused across different workflows.

There are two ways to include HyperBrowser in your workflow:

  1. As a tool: Allow your LLM to decide when a query necessitates searching the web. Click on your LLM, and choose "Add Tool". Select HyperBrowser. Make sure to reference this tool in your prompt for best results.

  2. As a node: Enforce Hyperbrowser usage every run. To set up HyperBrowser as a Node, make sure to reference all the Hyperbrowser actions in your LLM prompt.

You can monitor the job status and retrieve results or errors upon completion.


Available Actions

1. Use Browser

Automate a browser session to perform a specific task.

Inputs

  • Task (Required)

    • Description: The task to perform in the browser (e.g., "Log in to example.com and scrape the dashboard data").

    • Example:

      Log in to https://example.com with username 'user' and password 'pass', then extract the text from the dashboard.
  • Session ID (Optional)

    • Description: The ID of an existing browser session to use.

    • Example:

      "session_abc123"
  • Max Failures (Optional, default: 1)

    • Description: The maximum number of failures allowed before stopping the browser.

    • Example:

      2
  • Max Steps (Optional, default: 25)

    • Description: The maximum number of steps to allow before stopping the browser.

    • Example:

      10
  • Keep Browser Open (Optional, default: false)

    • Description: Whether to keep the browser open after the task is completed.

    • Example:

      true

Configurations

All configuration options are provided as part of the input parameters above. No additional required configurations.

Outputs

  • Job ID (Required)

    • Description: The unique identifier for the browser automation job.

    • Example:

      "job_456def"
  • Live URL (Required)

    • Description: The URL to view the live browser session.

    • Example:

      "https://hyperbrowser.live/session/job_456def"
  • Status (Required)

    • Description: The current status of the job. Possible values: pending, running, completed, failed, stopped.

    • Example:

      "completed"
  • Final Result (Optional)

    • Description: The final result or output of the browser task.

    • Example:

      "Dashboard data: { ... }"
  • Error (Optional)

    • Description: Error message if the task failed.

    • Example:

      "Login failed: Invalid credentials"
  • Session Stopped (Optional, default: false)

    • Description: Indicates if the browser session was stopped after completion.

    • Example:

      true

Summary Table

Input Name
Required
Description
Example

Task

Yes

The browser task to perform

"Log in and scrape dashboard"

Session ID

No

Use an existing browser session

"session_abc123"

Max Failures

No

Max failures before stopping (default: 1)

2

Max Steps

No

Max steps before stopping (default: 25)

10

Keep Browser Open

No

Keep browser open after task (default: false)

true

Output Name
Required
Description
Example

Job ID

Yes

Unique job identifier

"job_456def"

Live URL

Yes

URL to view live browser session

",https://hyperbrowser.live/session/job_456def,"

Status

Yes

Job status (,pending,, ,running,, etc.)

"completed"

Final Result

No

Final result of the task

"Dashboard data: { ... }"

Error

No

Error message if failed

"Login failed: Invalid credentials"

Session Stopped

No

Was the session stopped after completion?

true


Best Practices

  • Always provide a clear and specific task description.

  • Use session management for multi-step or persistent workflows.

  • Monitor the job status and handle errors gracefully in your workflow.


HyperBrowser in StackAI empowers you to automate and control browser tasks efficiently, making it a powerful tool for web automation and data extraction.

Last updated

Was this helpful?