Integration · Developer
AI agents for Hyperbrowser
Give an agent the web through Hyperbrowser's cloud browsers.
- Actions
- 9
- Read
- 7
- Write
- 2
Actions
What your agents can do in Hyperbrowser
Give an agent the web through Hyperbrowser's cloud browsers: fetch a page as Markdown, links or AI-extracted JSON (with stealth and captcha solving), search the web, crawl a site, extract structured data from several pages, and hand a Browser Use agent a task in plain words, then read its result.
Read 7
Look things up. Nothing changes.
Fetch a page
Opens one web page in a cloud browser and returns, in data, the requested formats.
Search the web
Searches the web and returns results in data.results, each with title, url and description.
Start crawling a site
Starts reading a website from a starting address, following its links and sitemap, up to max_pages pages (at most 100), each as Markdown (or links).
Get crawl results
Reads a crawl job: status (pending, running, completed, failed, stopped), how many pages it found (totalPages) and one batch of pages in data, each with url, status, markdown, links and metadata.
Start extracting data
Starts an AI extraction of structured data from up to 10 pages: describe what you want in prompt, give a JSON Schema in schema, or both.
Get extracted data
Reads an extraction job: status (pending, running, completed, failed, stopped), the extracted data once completed, and error when it failed.
Get a browser agent task
Reads a Browser Use task: status (pending, running, completed, failed, stopped), its answer in data.finalResult, the data.steps it took, error when it failed and the liveUrl.
Write 2
Create, change or send.
Run a browser agent task
Starts a Browser Use agent that does a task written in plain words in a cloud browser: navigating, clicking, typing and reading.
Stop a browser agent taskDeletes data
Stops a running Browser Use task and closes its browser.
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Paste an API key from your Hyperbrowser account.
What you enter
- API key
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your Hyperbrowser data
Ask a question in plain words. The agent can search the web, start crawling a site or get crawl results in Hyperbrowser, then answers with what it found.
- 02
Let an agent update Hyperbrowser
Have the agent run a browser agent task or stop a browser agent task in Hyperbrowser as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent Hyperbrowser and Slack: it can search the web in Hyperbrowser and post a summary to a Slack channel in the same run.
Works well with
More Developer tools
- GitHub4 actionsOpen and comment on issues, and start GitHub Actions workflows, in the repositories a personal access token can reach.
- GitLab4 actionsOpen and comment on issues, and start CI/CD pipelines, in the GitLab.com projects an access token can reach.
- Bitbucket3 actionsComment on and read pull requests, and start Bitbucket Pipelines, in the Bitbucket Cloud repositories your Atlassian API token can reach.
- Sentry3 actionsList, read, resolve and ignore error issues in a sentry.io organization, in its US or EU (Germany) data region.
- Datadog2 actionsPost events to the Datadog Event Explorer and send custom metric points, on any Datadog site, with an API key.
- PagerDuty4 actionsOpen, acknowledge and resolve PagerDuty incidents, add notes to them, and see who is on call for a schedule.
FAQ
Hyperbrowser and MyDeepAgents
Can MyDeepAgents connect to Hyperbrowser?
Yes. The Hyperbrowser connector has 9 actions: 7 read and 2 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Hyperbrowser?
Paste an API key from your Hyperbrowser account. You'll need: API key. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in Hyperbrowser without asking?
Only if you let it. Each of the 2 actions that change data can be set to wait for a person's approval before it runs, and the one that deletes data asks first by default.
Can I use Hyperbrowser in workflows as well as agents?
Yes. Every Hyperbrowser action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Hyperbrowser to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.