# Hyperbrowser integration

> Cloud headless-browser platform for AI agents: managed Chrome sessions with stealth/proxy/CAPTCHA solving, async scrape/crawl/extract jobs, web fetch and search, and autonomous browser-agent tasks (Browser Use, Claude/Gemini/Grok computer use, OpenAI CUA, HyperAgent).

- Authentication: apiKey

## Tools (56)

- **Create Profile**: Creates a browser profile that persists cookies, auth state, and storage across sessions.
- **Create Session**: Launches a cloud browser session.
- **Delete Profile**: Delete profile by ID.
- **Evaluate CAPTCHA**: Triggers a bounded CAPTCHA evaluation on an active session.
- **Fetch Web Page**: Fetches a single page synchronously and returns content in the requested formats (markdown, HTML, links, screenshot, AI-extracted JSON, branding profile).
- **Get Batch Scrape Job Result**: Get batch scrape job status and results.
- **Get Batch Scrape Job Status**: Get batch scrape job status.
- **Get Browser Use Task Result**: Get browser use task status and results.
- **Get Browser Use Task Status**: Get browser use task status.
- **Get Claude Computer Use Task Result**: Get claude computer use task status and results.
- **Get Claude Computer Use Task Status**: Get claude computer use task status.
- **Get Crawl Job Result**: Get crawl job status and results.
- **Get Crawl Job Status**: Get crawl job status.
- **Get Extract Job Result**: Get extract job status and results.
- **Get Extract Job Status**: Get extract job status.
- **Get Gemini Computer Use Task Result**: Get gemini computer use task status and results.
- **Get Gemini Computer Use Task Status**: Get gemini computer use task status.
- **Get Grok Computer Use Task Result**: Get grok computer use task status and results.
- **Get Grok Computer Use Task Status**: Get grok computer use task status.
- **Get HyperAgent Task Result**: Get HyperAgent task status and results.
- **Get HyperAgent Task Status**: Get HyperAgent task status.
- **Get OpenAI CUA Task Result**: Get CUA task status and results.
- **Get OpenAI CUA Task Status**: Get CUA task status.
- **Get Profile**: Get profile by ID.
- **Get Scrape Job Result**: Get scrape job status and result.
- **Get Scrape Job Status**: Get scrape job status.
- **Get Session**: Get session by ID.
- **Get Session Downloads URL**: Get session downloads URL.
- **Get Session Recording URL**: Get session recording URL.
- **Get Session Video Recording URL**: Get session video recording URL.
- **Get Web Crawl Job Result**: Retrieves the status and results of a web crawl job.
- **Get Web Crawl Job Status**: Retrieves just the status of a web crawl job without the full results.
- **List Extensions**: List all extensions.
- **List Profiles**: Get list of profiles.
- **List Sessions**: Get list of sessions.
- **Search Web**: Performs a web search and returns results with titles, URLs, and descriptions.
- **Start Batch Scrape Job**: Starts an asynchronous scrape job for up to 1,000 URLs with shared scrape/session options.
- **Start Browser Use Task**: Starts an autonomous Browser Use framework task from a natural-language instruction.
- **Start Claude Computer Use Task**: Starts an autonomous browser task driven by Anthropic Claude computer use.
- **Start Crawl Job**: Starts an asynchronous crawl that follows links from a starting URL and scrapes each page.
- **Start Extract Job**: Starts an asynchronous AI extraction job: provide URLs plus a `prompt` and/or JSON `schema`, and the AI returns structured data from the pages.
- **Start Gemini Computer Use Task**: Starts an autonomous browser task driven by Google Gemini computer use.
- **Start Grok Computer Use Task**: Starts an autonomous browser task driven by xAI Grok computer use.
- **Start HyperAgent Task**: Starts an autonomous HyperAgent (Playwright-based) browser task from a natural-language instruction.
- **Start OpenAI CUA Task**: Starts an autonomous browser task driven by OpenAI's Computer-Using Agent.
- **Start Scrape Job**: Starts an asynchronous scrape job for a single URL and returns formatted page content (markdown, HTML, links, screenshot).
- **Start Web Crawl Job**: Starts an asynchronous crawl using the fetch-family options (`outputs`, `browser`, `navigation`, `cache`) plus `crawlOptions` for link-following rules.
- **Stop Browser Use Task**: Stop a browser use task.
- **Stop Claude Computer Use Task**: Stop a claude computer use task.
- **Stop Gemini Computer Use Task**: Stop a gemini computer use task.
- **Stop Grok Computer Use Task**: Stop a grok computer use task.
- **Stop HyperAgent Task**: Stop a HyperAgent task.
- **Stop OpenAI CUA Task**: Stop a CUA task.
- **Stop Session**: Stops a running session and ends billing.
- **Update Session**: Updates a setting on an active session.
- **Upload Extension**: Uploads a zipped Chrome extension.

Connect Hyperbrowser in General Input: https://www.generalinput.com/apps/hyperbrowser