Where does the browser automation code run?
An external worker, a hosted browser Function, a browser-local app action and a hosted agent are different execution models. The choice determines who deploys the code, starts the browser, records the result and stops the run.
A scheduled job should return a verified result and stop its owned browser even when an action fails. The scheduler's successful HTTP trigger is not proof that the browser completed the business operation.
Compare the execution model
Kernel: Deploy a TypeScript or Python App and expose Actions that callers invoke. Kernel co-locates code with the browser environments the app creates. An Action invocation is the execution unit rather than a bare CDP connection.
Browser Use: The cloud offers hosted-agent runs and separately created browsers. The reviewed browser documentation does not establish a deploy-your-own Python Function equivalent. Keep an external script runner separate from a hosted agent when comparing execution ownership.
Compare deployment ownership
Kernel: Kernel Apps move the automation process next to the browser. Alternatively, an external process can control a browser through the browser API. Choose based on execution locality and deployment ownership.
Browser Use: Use the hosted browser from your own process or send a task to the hosted agent. The open-source local framework is another deployment option and should not be equated with the cloud subscription.
Compare the evidence from a run
Kernel: Live browser URLs support an embedded view and a read-only option. Replays and browser telemetry are separate observability surfaces; app invocation logs add execution context.
Browser Use: Browser Use documents live preview and recording. Recording availability follows the browser lifecycle and processing state; a live URL is for an active browser rather than a permanent replay link.
How to evaluate this choice
Keep an external runner when you already operate one and need portability. A native execution layer can remove deployment work; browser-local code can reduce repeated network calls. Compare actual workload behavior before assuming either always wins.
- Confirm the supported language, entry point and dependency packaging.
- Trace deployment, version selection, invocation and cancellation.
- Keep the handler runtime limit separate from browser session duration.
- Decide whether scheduling is native or supplied by another service.
- Associate results and logs with both the code version and browser session.
Requirements side by side
| Requirement | Kernel | Browser Use |
|---|---|---|
| Code execution | TypeScript / Python Apps | External worker or hosted agent |
| Scheduled execution | App invocation path | Check execution setup |
| Recordings / replay | Documented | Recording option |
Sources: kernel.sh [1] ↗kernel.sh [2] ↗kernel.sh [3] ↗kernel.sh [4] ↗kernel.sh [5] ↗kernel.sh [6] ↗docs.browser-use.com [7] ↗docs.browser-use.com [8] ↗docs.browser-use.com [9] ↗docs.browser-use.com [10] ↗
Which approach fits?
Choose Kernel when your code makes many browser calls and you want to deploy it beside the browser, or you need Kernel's managed sign-in flow.
Kernel tradeoff: Browser-local code changes the deployment model. Check app action behavior, account limits and persistent-state ownership before moving an external worker into it.
Choose Browser Use when you use Browser Use's framework or want its hosted browsers while retaining the option of a hosted browser agent.
Browser Use tradeoff: A hosted-agent run is a different execution unit from your deployed browser script. Keep comparisons focused on the browser path when measuring session speed and price.
A useful acceptance check
Write a pass/fail result for the real task before running the evaluation. Record the account, configuration and code version next to that result. Repeat failures need an explanation, not an automatically different browser configuration.
When Notte belongs on this shortlist
Kernel's browser-local Apps make execution placement part of the decision. Compare the repeated action path with the proposed Notte controller or Function deployment before concluding that a lifecycle or hourly-rate difference decides the workflow.
Browser Use's hosted-agent offering and standalone browser infrastructure are separate options. Keep the comparison at the browser layer when your application already owns its controller; compare execution ownership separately if the hosted agent is part of the requirement.
Notte: Functions deploy Python code with a run() entry point. Invoke them over HTTP or with an SDK, inspect run history, and roll back code by redeploying an earlier version as the latest version.
Consider this third option when its documented mechanism addresses a requirement left open by the two providers above. A working configuration on either original provider can still be the better choice; compare the task and ownership cost before switching.
Sources: kernel.sh [1] ↗docs.browser-use.com [2] ↗docs.notte.cc [3] ↗