Hyperbrowser
for LuumenAI
Fetch pages, run crawls, and drive browser tasks from the terminal
Hyperbrowser gives Luumen a browser it can drive. Fetch a vendor status page as markdown, crawl a docs site, or hand a multi-step click-through to a browser-use task and poll it to completion. Reads come back right away. Starting jobs, creating sessions, and deleting profiles are previewed and held for approval first. Connected with an API key.
The Hyperbrowser toolbox
42 tools: 25 read, 17 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadFetch Web PageFetch a web page and return content in various formats (HTML, Markdown, JSON, screenshot, etc.).
- ReadGet browser-use task statusRetrieve the current status of a browser-use task.
- ReadGet Claude Computer Use Task ResultRetrieve the complete result and status of a Claude Computer Use task.
- ReadGet Claude Computer Use Task StatusPoll the execution status of a Claude Computer Use task.
- ReadGet Crawl Job StatusRetrieve the status and results of a specific crawl job.
- ReadGet Crawl StatusRetrieve the current status of a specific crawl job.
- ReadGet CUA Task ResultRetrieve the status and results of a CUA (Claude User Agent) task.
- ReadGet CUA Task StatusPoll the execution status of a CUA task.
- ReadGet Extract Job ResultFetch the status and results of a specific extract job.
- ReadGet Extract Job StatusRetrieve the status of an extract job.
- ReadGet Gemini Computer Use task resultRetrieve the current status and results of a Gemini Computer Use task.
- ReadGet HyperAgent Task ResultRetrieve the status and results of a HyperAgent task.
- ReadGet Profile By IDRetrieves details of a specific Hyperbrowser profile by its UUID.
- ReadGet Scrape Job ResultRetrieves the status and results of a scrape job.
- ReadGet Scrape Job StatusRetrieve the current status of a specific scrape job.
- ReadGet Session DetailsRetrieve detailed information about a Hyperbrowser session by its ID.
- ReadGet Session Downloads URLRetrieve the downloads URL for a session.
- ReadGet Session RecordingRetrieve the recording URL for a browser session.
- ReadGet Session Video Recording URLRetrieve the video recording URL for a browser session.
- ReadGet Web Crawl ResultRetrieve the status and results of a web crawl job.
- ReadGet Web Crawl StatusRetrieve just the status of a web crawl job without the full results.
- ReadList ExtensionsList all browser extensions.
- ReadList ProfilesList profiles.
- ReadList SessionsList sessions with optional status filter.
- ReadSearch WebPerform a web search and retrieve results with titles, URLs, and descriptions.
- WriteAdd ExtensionAdd a new browser extension to Hyperbrowser for use in sessions. Approval by default
- WriteCreate Hyperbrowser ProfileCreates a new persistent Hyperbrowser profile for storing browser state (cookies, sessions, etc.). Approval by default
- WriteCreate Scrape JobInitiate a new scrape job. Approval by default
- WriteCreate SessionCreate a new browser session with custom stealth, proxy, and privacy settings. Approval by default
- WriteDelete ProfileDelete a profile. Approval by default
- WriteStart Browser Use TaskStart an asynchronous browser-use task. Approval by default
- WriteStart Claude Computer Use TaskStart a Claude Computer Use task. Approval by default
- WriteStart Crawl JobStart a new crawl job for a specified URL. Approval by default
- WriteStart CUA TaskStart an OpenAI CUA (Computer-Using Agent) task. Approval by default
- WriteStart Extract JobStart an AI-powered data extraction job from one or more web pages. Approval by default
- WriteStart Gemini Computer Use TaskStart a Gemini Computer Use task for browser automation using Google's Gemini. Approval by default
- WriteStart Web CrawlStart an asynchronous web crawl job that follows links from a starting URL and returns content from each page. Approval by default
- WriteStop Browser Use TaskStop a running browser-use task. Approval by default
- WriteStop Claude Computer Use TaskStop a running Claude computer use task. Approval by default
- WriteStop CUA TaskStop a running CUA task. Approval by default
- WriteStop Gemini Computer Use TaskStop a running Gemini computer use task. Approval by default
- WriteStop SessionStop a running session by ID. Approval by default
One prompt, start to finish
What a governed Hyperbrowser run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — add extension, create hyperbrowser profile, create scrape job, create session, and more — is shown as a plan and requires approval by default, including the 6 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Hyperbrowser — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
PostgreSQLQuery PostgreSQL state safely; maintenance held for approval.
MySQLQuery MySQL state safely; maintenance held for approval.
Microsoft SQL ServerQuery Microsoft SQL Server state safely; maintenance held for approval.Oracle DatabaseQuery Oracle Database state safely; maintenance held for approval.Put Hyperbrowser to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.