Web automation for AI agents that can act in the browser
browser-use helps you build agents that interact with websites, fill forms, and complete web tasks. It supports both a self-hosted open-source library and a cloud option for faster setup and scaling.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 8 November 2026.
Is this your tool? Claim this listing to manage your content and analytics.
What it decides by itself, and when it asks you
Mapped from the code in browser-use/browser-use.
In browser-use, the AI model chooses the actions on each of its steps (code may first open a web address named in the task) and decides the task is finished by calling done. Among the decisions this map shows, nobody is asked before an action runs, so a form submit or a script the model writes goes ahead on its own, and code clicks OK on alerts and confirm dialogs. The built-in limits on how long a run goes are counts, not judgments (500 steps, or 5 failed steps in a row), and the run's success flag is the model's value when it gives one and true when it does not; a second model call grades the run without changing that flag.
Read the full map: the judgments it shows and who holds each oneBefore the agent submits, buys, sends, deletes or runs page JavaScript, does anyone approve it?
Decided by: Plain codeNobody is asked: the model's actions run as soon as they are parsed. An integrator can add a check in their own code through the step callback, which sees the proposed actions before they run.
Which actions is the model offered this step?
Decided by: Plain codeEvery built-in action on every page, including evaluate, which runs JavaScript the model writes, except screenshot at the default vision setting and any the integrator excluded, plus custom actions whose site filter matches. On the last step or after repeated failures, only done.
When a page opens a JavaScript dialog, who decides OK or Cancel?
Decided by: Plain codeCode clicks OK on every alert, confirm and leave-page dialog the moment it opens, and Cancel on every text prompt, before the model sees it; the model is told afterwards.
Which browser permissions are granted to the sites the agent visits?
Decided by: Plain codeWhen the browser connects, code grants clipboard read/write and notifications to every site; any other permission a page asks for is left to Chrome.
Three problems the map found
A run can be reported successful when the model never said so
Fix proposedA program reads the success flag in the model's done call at the end of a run. If the model leaves the flag out, code records success. When the developer asks for a structured result, that field is hidden from the model, so such a run normally reads as successful unless the model sets it anyway. An open pull request in browser-use's tracker proposes a fix.
After a step times out, the model is not told which of its actions already ran
No tracker issue foundA whole step gets 180 seconds by default. If it runs over, it is cut off, the record of which of the step's actions finished is dropped, and the step's result is only a timeout error. If the run takes another step, the model sees the page as it now is, which may show some effects, but it is not told which of its actions already ran. We found no report of this in browser-use's tracker.
Pressing Enter does not resume a paused run, though the message says it will
No tracker issue foundOn Mac and Linux, pressing Ctrl+C pauses the run and prints "Press [Enter] to resume or [Ctrl+C] again to quit". Pressing Enter does not resume it; only code that calls agent.resume() does, so a person at the terminal can quit with a second Ctrl+C but cannot continue the run from there. In tracker searches on 2026-11-08 we found no issue tracking this; a 2025 pull request comment reported the same symptom.
Not checked: This card was taken from the published map of browser-use at one commit and covers only decisions shown there; it did not look at the beta agent, the sandbox runner, the MCP server, the command line, Browser Use's cloud browsers or features that are off until a setting turns them on, and no browser-use code was run to make it.
Mapped by agent-ops-patterns (open source) from browser-use/browser-use at commit b49a68e. Mapped Oct 29, 2026. Last updated Nov 8, 2026.
What's happened with Browser Use lately
- Score changeRubric upgrade v3_0 → v3.1: score 13/32 → 19/3613 → 19/36(+6)
Rubric upgrade: agenticness v3.0 (8 dims, /32) → v3.1 (9 dims, /36). Adds Dim 9 (Operator Sovereignty), splits Dim 6 into 6a/6b lenses, tightens Dim 4 autonomous-retry distinction. Not a product change — score shift reflects new dimension + recalibrated rubric, not a change in the tool. Fanout suppressed.
See the news that prompted this
News mentions sourced from our news feed; score changes from periodic re-evaluations.
Ask about Browser Use
Get answers based on Browser Use's actual documentation
Try asking:
About
browser-use is an open-source browser automation framework for AI agents. It is aimed at developers who want to build agents that can navigate websites, click, type, take screenshots, and complete multi-step browser workflows with an LLM in the loop.
This is more of an agent framework than a consumer app. It looks strongest for developers building browser-based automations, especially when you need custom tools or deeper code-level control. The cloud offering is positioned as easier to start and...
Proposes and executes multi-step plans with your approval.
Dimension Breakdown
Categories
Ask about Browser Use
Try asking:
- Free: Open-source library available; pricing not publicly available in the crawled content.
- Cloud: Available via Browser Use Cloud; exact pricing not publicly available in the crawled content.
- Enterprise: Not clearly documented in the crawled content.
When Browser Use changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.