Integration · Developer
AI agents for Browserless
Read the web through Browserless's cloud browsers: scrape any page to Markdown, text, links or AI-extracted JSON.
- Actions
- 8
- Read
- 6
- Write
- 2
Actions
What your agents can do in Browserless
Read the web through Browserless's cloud browsers: scrape any page to Markdown, text, links or AI-extracted JSON (getting past bot checks and captchas when needed), pull elements by CSS selector, search the web, list a site's pages, and give a browser agent a task in plain words and read its answer.
Read 6
Look things up. Nothing changes.
Scrape a page
Reads one web page, escalating by itself from a plain fetch to a proxy, a real browser and captcha solving as needed.
Scrape elements by CSS selector
Loads a page in a real browser, runs its JavaScript, waits for the selectors you give and returns, for each selector, every matching element's text, html, attributes and position.
Search the web
Searches the web (and optionally news or images) and returns results with title, url, description and position under data.web (and data.news, data.images).
List a website's pages
Discovers the pages of a website from its sitemap and links and returns their addresses in links, each with url and, when known, title and description.
Get an agent run
Reads one agent run: its status (pending, running, needs_human, succeeded, failed, timed_out, stopped), the answer in data once it succeeded, error when it failed.
List agent runs
Lists the account's agent runs, newest first, optionally by status, each with id, status and when it was created.
Write 2
Create, change or send.
Run a browser agent
Starts a managed AI agent that does a task, written in plain words, in a real browser: navigating, clicking, typing and reading.
Cancel an agent runDeletes data
Stops a pending, running or waiting agent run (it ends as stopped), or deletes a finished run and its result.
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 Browserless account.
What you enter
- API token
Settings
- Region
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 Browserless data
Ask a question in plain words. The agent can scrape a page, scrape elements by CSS selector or search the web in Browserless, then answers with what it found.
- 02
Let an agent update Browserless
Have the agent run a browser agent or cancel an agent run in Browserless 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 Browserless and Slack: it can scrape a page in Browserless 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
Browserless and MyDeepAgents
Can MyDeepAgents connect to Browserless?
Yes. The Browserless connector has 8 actions: 6 read and 2 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Browserless?
Paste an API key from your Browserless account. You'll need: API token. The connection also asks for: Region. 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 Browserless 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 Browserless in workflows as well as agents?
Yes. Every Browserless action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Browserless to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.