How does the browser get into the right account?
Website authentication crosses several boundaries: the user who authorizes access, the system that holds credentials, the browser that submits them, and any model or code driving the page. Reusing a login and collecting a new identity are separate workflows.
For a customer-facing app, associate each stored connection with the correct application user before opening a browser. Reusing another user's profile can produce a technically successful run in the wrong account.
Compare the login path
Kernel: Managed Auth handles website login and eligible connection recovery. Vault fill is a separate flow for applications that control navigation and form submission; the reviewed vault documentation labels that surface as preview.
Steel: Steel's Credentials API stores credentials for users or agents. Its cookbook demonstrates using stored credentials with Playwright, while profiles and auth contexts preserve signed-in browser state.
Sources: kernel.sh [1] ↗docs.steel.dev [2] ↗
Compare saved state
Kernel: Profiles preserve browser user-data-directory state, including cookies, site data, tabs and preferences. Profile sharing and save behavior need explicit treatment when parallel workers use seeded state.
Steel: The Profiles API documents reusable browser context, cookies, extensions, credentials and browser settings. Steel also documents lighter auth-context reuse, which should not be confused with a complete profile.
Sources: kernel.sh [1] ↗docs.steel.dev [2] ↗
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.
Steel: Steel documents live and past sessions as well as Agent Traces. Browser recordings answer what happened on the page; traces add context around the agent or application driving it.
Sources: kernel.sh [1] ↗docs.steel.dev [2] ↗
How to evaluate this choice
Compare the concrete login path. A vault can fill a secret while your code controls the workflow; a managed connection may own more of the login process. Neither should be described as a universal guarantee that every website remains signed in.
- Identify whether the task uses an existing account or creates an approved new identity.
- Separate profile restoration from credential fill and connection readiness.
- Document which component can access credential values and which only handles references.
- Verify the expected tenant and account after login.
- Provide a human handoff when the website requires user interaction.
Requirements side by side
| Requirement | Kernel | Steel |
|---|---|---|
| Saved browser state | Documented | Documented |
| Credential handling | Vaults (preview) | Credentials API |
| Website sign-in | Documented | Profile / credential flows |
Sources: kernel.sh [1] ↗kernel.sh [2] ↗kernel.sh [3] ↗kernel.sh [4] ↗kernel.sh [5] ↗kernel.sh [6] ↗docs.steel.dev [7] ↗docs.steel.dev [8] ↗docs.steel.dev [9] ↗docs.steel.dev [10] ↗docs.steel.dev [11] ↗docs.steel.dev [12] ↗
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 Steel when you want browser infrastructure that can fit a self-hosted deployment, with profiles and credentials available through browser-focused APIs.
Steel tradeoff: Hosted and self-hosted Steel are different operating choices. A cloud feature's documentation does not establish identical packaging, retention or operational support in a self-hosted installation.
Sources: kernel.sh [1] ↗docs.steel.dev [2] ↗
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.
Steel's managed and self-hosted choices make infrastructure ownership a concrete deciding factor. Keep that option on the shortlist when operating the browser is intentional; evaluate Notte when owning fewer execution and authentication components is the actual goal.
Notte: Vaults substitute credential placeholders in supported browser actions outside the model context. Managed Auth checks requested saved connections before automation. Personas supply an inbox and optional phone number for verification workflows.
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.steel.dev [2] ↗docs.notte.cc [3] ↗