The decision
Start with the product contracts for browser control, saved browser state, credential handling, website sign-in. Different labels do not establish different functionality; compare the implementation and conditions behind each one.
Kernel provides cloud browsers and an app platform for TypeScript or Python code. App actions run alongside Kernel browsers, while profiles and Managed Auth handle retained state and sign-in connections.
Amazon Bedrock AgentCore Browser provides isolated managed browser sessions with live interaction and AWS observability. Browser automation libraries use its streaming endpoints; the surrounding AWS execution layer is a separate choice.
At a glance
| Requirement | Kernel | AWS AgentCore Browser |
|---|---|---|
| Browser control | Documented | Browser automation endpoint |
| Saved browser state | Documented | Explicit state design |
| Credential handling | Vaults (preview) | AWS / application composition |
| Website sign-in | Documented | Separate identity design |
| Code execution | TypeScript / Python Apps | External AWS compute |
| Scheduled execution | App invocation path | External scheduler |
| Live view | Documented | Documented |
| Recordings / replay | Documented | Custom browser + S3 |
| Deployment choice | Check deployment offering | AWS service |
Sources: kernel.sh [1] ↗kernel.sh [2] ↗kernel.sh [3] ↗kernel.sh [4] ↗kernel.sh [5] ↗kernel.sh [6] ↗docs.aws.amazon.com [7] ↗
What survives a session
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.
AWS AgentCore Browser: The Browser Tool documentation describes ephemeral sessions that reset after use. State that must outlive a session needs an explicit storage or authentication design rather than an assumption of permanent browser state.
Website login
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.
AWS AgentCore Browser: AWS credentials and IAM control access to the Browser Tool. Website login remains a separate concern: the identity used to authorize an AWS API call does not automatically sign the browser in to a third-party application.
Where the code runs
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.
AWS AgentCore Browser: The Browser Tool supplies the browser environment. An external process or another AWS execution service runs the application code that controls it. Identify that service and its runtime before comparing it with a deployed browser Function.
Published browser measurements
These are the latest provider runs in the saved BrowserArena snapshot checked on October 18, 2026. Dates and runner environments can differ. A lifecycle test opens, connects, navigates and releases a browser; the throughput test runs a separate browser action sequence. Neither measures managed authentication or deployed Function reliability.
Use these observations to choose what to test in your application. An account-configuration failure, an incompatible page action and a timed-out navigation require different interpretations. BrowserArena is maintained by Notte and publishes its source and methodology.
| Provider | Lifecycle median | Lifecycle P95 | Actions / second | Run dates |
|---|---|---|---|---|
| Kernel | 334 ms | 700 ms | 3.32 | 2026-10-18 / 2026-10-17 |
| AWS AgentCore Browser | 2791 ms | 3472 ms | 0.72 | 2026-10-18 / 2026-10-17 |
Sources: browserarena.ai [1] ↗browserarena.ai [2] ↗github.com [3] ↗
Pricing model
Kernel: Use the plan and browser configuration in Kernel's pricing documentation. Managed networking, account allowances and app execution make a browser-hour comparison only one part of the decision.
AWS AgentCore Browser: A complete AWS workflow may include browser use, the controlling compute service, storage and other metered services. Price the selected architecture and region instead of treating a browser benchmark rate as the final invoice.
Sources: kernel.sh [1] ↗aws.amazon.com [2] ↗
Capacity and limits
Kernel: Kernel documents concurrent browsers, browser creation rate and per-browser resources separately. Standby browsers can still consume concurrency. Pools change how browsers are acquired; they do not erase account limits.
AWS AgentCore Browser: AgentCore Browser supports multiple simultaneous sessions. Review AWS quotas and the chosen tool/session configuration; the browser session's timeout and the controller's execution timeout are separate limits.
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 AWS AgentCore Browser when your application already uses AWS identity, logging and storage, and browser workflows need to fit those systems.
AWS AgentCore Browser tradeoff: The browser tool is not the entire AgentCore platform. Do not assign capabilities from unrelated AgentCore execution or identity products to a browser session without specifying the composition.
Check the browser connection
Install playwright-core in your application and provision a session through the provider's documented creation flow. Run this smoke test from the intended controller region with the returned CDP endpoint. It checks connection and navigation, not login, rendering parity or a complete business workflow.
Keep browser connection URLs on your backend. After the test, release the owned session through the provider's API. Product-specific lifecycle APIs and profile identifiers are not portable between providers.
import { chromium } from "playwright-core";
// Provision the owned browser using the provider's documented session API.
// Keep the connection URL in your backend's secret environment.
const endpoint = process.env.BROWSER_CDP_URL;
if (!endpoint) throw new Error("Set BROWSER_CDP_URL for an owned session");
const browser = await chromium.connectOverCDP(endpoint);
try {
const context = browser.contexts()[0] ?? await browser.newContext();
const page = context.pages()[0] ?? await context.newPage();
await page.goto("https://example.com", { waitUntil: "domcontentloaded" });
if ((await page.title()) !== "Example Domain") {
throw new Error("The browser did not reach the expected page");
}
console.log({ connected: true, expectedPage: true });
} finally {
await browser.close();
// Release the owned session with the provider's documented API as well.
// A disconnected socket alone is not a portable session-cleanup contract.
}Sources: playwright.dev ↗
Before you switch
Keep the same target workflow when evaluating both products. Separate infrastructure facts from measurements and test the required account state, action sequence and artifacts. A successful connection test does not establish that a long or authenticated task will complete.
Use the focused guides for Kernel and AWS AgentCore Browser below when the deciding requirement is pricing, persistence or code execution. Provider-owned resources such as session IDs, profiles and managed connections need a new mapping during migration.
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.
AgentCore Browser's AWS integration can matter more than moving a browser endpoint. Retain AWS identity and observability requirements in the evaluation, and separately account for the code runner and website login before comparing Notte's integrated workflow.
Notte: Create an owned browser session, connect Playwright or Puppeteer over CDP, and stop the session when the work finishes. Browser lifecycle management remains necessary even when the control socket disconnects.
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.aws.amazon.com [2] ↗docs.notte.cc [3] ↗