COMPUTER USE / PROFILE

Browser Use: capabilities, evidence & fit

An open-source browser agent library with managed agents and cloud browser sessions.

Agent & orchestrationlive

Choose the open-source agent library when you own the loop, the hosted agent API when you want task execution, or cloud browser sessions when your own Playwright/Puppeteer code drives the browser. These are distinct deployment paths.

Last verified: Sep 27, 2026
Primary sources: 5
Evidence state: Fresh
Benchmark records: 2

Where it fits

CONSIDER IT FOR

Natural-language browser tasks
Python teams choosing local or managed execution

LOOK ELSEWHERE WHEN

You need native desktop application control
A deterministic script already solves a stable task

Fit recommendations are editorial interpretations of the documented architecture.

Documented capabilities

CAPABILITY	DOCUMENTED STATE	SOURCE
Managed tasks	Hosted runs accept a task and expose completion results	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Managed tasks: Hosted runs accept a task and expose completion results Verified Sep 27, 2026 · verified docs.browser-use.com
Cloud browser	Launch a browser and connect over CDP	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Cloud browser: Launch a browser and connect over CDP Verified Sep 27, 2026 · verified docs.browser-use.com
SDK languages	Python and TypeScript SDK quickstarts	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs SDK languages: Python and TypeScript SDK quickstarts Verified Sep 27, 2026 · verified docs.browser-use.com
Local agent	Open-source library supports a local agent path	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official repo Local agent: Open-source library supports a local agent path Verified Sep 27, 2026 · verified github.com
Browser observation	Configurable screenshots and DOM state guide agent actions	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Browser observation: Configurable screenshots and DOM state guide agent actions Verified Sep 27, 2026 · verified docs.browser-use.com
Session lifecycle	Stop the managed browser explicitly after a run	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Session lifecycle: Stop the managed browser explicitly after a run Verified Sep 27, 2026 · verified docs.browser-use.com

Environment, deployment & control

Environment

browser: Full
desktop: Unknown
mobile: Unknown

Deployment

cloud: Full
local: Full
self Hosted: Full

Extensibility

api: Full
sdk: Full
mcp: Unknown
bring Your Own Model: Full

Control method

screenshots: Full
mouse Keyboard: Full
dom Or Accessibility: Full
code Execution: Unknown

Unknown = insufficient public evidence; No evidence = an explicit negative record; N/A = does not apply to this layer.

Trust, oversight & limitations

Documented oversight

human Approval: Unknown
audit Logs: Unknown
sandboxing: Unknown
prompt Injection Defense: Unknown
credential Controls: Unknown

Know the boundary

Cloud sessions continue running after CDP disconnect; explicitly stop them to end usage.
An open-source library does not imply that the managed cloud service is self-hostable.

Design human approval →

Pricing snapshot

$0.02 / browser hour + traffic + model

Verified Sep 27, 2026 · USD · usage. Hosted services and software licensing can have different terms.

Cost inputs & calculator →

Compare the tradeoffs

Browser Use vs Skyvern

Both are candidates for adaptive browser workflows. Compare the specific open-source or managed product path and how much orchestration you want to own.

Browser Use vs Stagehand

Browser Use supplies an agent-oriented task path; Stagehand supplies browser control primitives that can sit inside your own agent. Choose the boundary you want to program.

Browser Use vs Browserbase

This can be an agent-versus-runtime comparison, but both vendors now have broader managed offerings. Name the product surface before treating them as substitutes.

Browser Use vs Playwright

Browser Use adds a task-planning layer; Playwright is a deterministic browser automation foundation. The right split depends on which decisions the workflow actually needs.

Explore Browser Use alternatives

Relevant use cases

Computer use for finance operations

Collect portal evidence and prepare reconciliations while keeping payment authority outside the agent.

Computer use for accounting workflows

Bridge document retrieval and draft entry with explicit reconciliation and duplicate checks.

Computer use for healthcare portals

A constrained architecture for authorized administrative retrieval, with explicit data handling and review.

Computer use for insurance operations

Gather claim-status evidence across permitted portals without delegating adjudication.

Computer use for recruiting operations

Prepare source-linked candidate records and scheduling drafts while leaving employment decisions to people.

Benchmark context

BrowserBench / Browser Use run · 2026-03-21; upstream revision undisclosed

Browser Use Internal Bench Hard / 106-task snapshot · updated 2026-08-01

RESEARCH NOTES

Sources & verification

Reviewed Sep 27, 2026. Architecture recommendations are editorial analysis; linked vendor documentation supports the underlying capability and safety facts.

How we verify evidence →