Browser Use

Python browser agent, CLI controls for your existing agent, and a separate fully hosted agent API.

Choose it when

You want to customize a Python browser agent, give your existing agent browser controls, or hand a task to the hosted V4 agent.

Skip it when

You need guaranteed approval before every external action or want cloud browser infrastructure to supply the agent logic for you.

01 / Classification

Autonomy evidence

This is our classification, not a vendor badge. The record says what the product normally does. The gaps stay visible.

How we classify it

Tool use + multi-step plans, still human-gated per session.

Runs unattended

Yes — that capability is documented in this brief.

Trigger

Submit a hosted V4 prompt, run the Python agent in your application, or have an existing agent call the CLI.

State

For V4, a session holds conversation, a workspace holds files and a profile holds browser login state; these IDs aren't interchangeable.

Tools

CLI browser actions can use local Chrome, cloud browsers or an existing CDP endpoint; infrastructure alone doesn't run the agent.

Human control

Design human checkpoints and use live-browser takeover, then continue the session. This isn't automatic approval before each action; the task owner must reconcile important writes.

02 / Operations

Control reality

Useful agents eventually touch something real. This is the operational picture we have, not a promise hidden in a sales page.

Where it runs

Python/CLI can run with your own agent infrastructure; the fully hosted V4 path runs agent and browser off your computer.

Data boundary

Explicit Profile Sync copies selected local Chrome cookies to a cloud profile. A local client alone isn't a guarantee that browser context stays off providers.

Identity & permissions

An attached local Chrome profile can reuse existing logins; cloud profiles hold separate browser login state.

What it can write

browser via CDP

Surfaces

Python library · CLI · Browser Use cloud

Export / lock-in

Cloud workspace output files can be listed and downloaded after completion; local browser cookies/localStorage can be exported as storage state. No full account-export guarantee.

03 / Receipts

Evidence ledger

Here is what this brief is built on. “Documented” means we found a source. “Tested” means this desk actually ran it. Those are different things.

Evidence status

documented

Source set

9 primary sources

Evidence review

2026-10-16

Sources on file

Corrections

2026-10-13 · Replaced the June CLI/CDP desk-report timestamp with library 0.13.11 publication. Separated hosted V4 agent, existing-agent CLI and Python library from browser-only infrastructure. Corrected unattended:false to documented optional hosted continuation, not autonomous reliability. Retained historical payloads; added SDK availability and checkpoint/data-boundary limits.
2026-10-16 · Refreshed the Python library release to 0.13.13, not Cloud API V4. The release supersedes 0.13.12, whose PyPI publication was cancelled before approval. Added OpenAI driver prerequisites and the current integration guide's optional application-host Bash boundary; a remote browser isn't a host-tool sandbox. The prior 0.13.11 Anthropic SDK warning is historical, not a current compatibility finding. Documented, not runtime-tested.

04 / Change log

Related coverage

The brief tells you what the product is. Payloads track the changes that may alter the decision.