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.
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.
Lightpanda is a browser engine built for automation, with a hosted cloud offering. It is an engine choice as well as a hosting choice, so evaluate the site's behavior and the browser APIs your workflow uses.
At a glance
| Requirement | AWS AgentCore Browser | Lightpanda |
|---|---|---|
| Browser control | Browser automation endpoint | Compatibility-dependent |
| Saved browser state | Explicit state design | Not established |
| Credential handling | AWS / application composition | Application-owned |
| Website sign-in | Separate identity design | Not established |
| Code execution | External AWS compute | External worker |
| Scheduled execution | External scheduler | External scheduler |
| Live view | Documented | Check engine support |
| Recordings / replay | Custom browser + S3 | Not established |
| Deployment choice | AWS service | Engine available |
What survives a session
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.
Lightpanda: The reviewed cloud documentation does not establish a durable profile contract covering cookies and web storage. Determine how the required browser state is saved and restored before moving an authenticated workflow.
Website login
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.
Lightpanda: Browser engine compatibility and website authentication are separate requirements. The reviewed sources do not establish a managed website-auth connection equivalent; verify the login and verification flow on the target sites.
Where the code runs
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.
Lightpanda: The reviewed documentation establishes a browser engine and hosted access, not a deployed Python Function contract. A separate automation process must have its own deployment, triggers and monitoring design.
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 |
|---|---|---|---|---|
| AWS AgentCore Browser | 2791 ms | 3472 ms | 0.72 | 2026-10-18 / 2026-10-17 |
| Lightpanda | 488 ms | 550 ms | 3.61 | 2026-10-18 / 2026-10-18 |
Sources: browserarena.ai [1] ↗browserarena.ai [2] ↗github.com [3] ↗
Pricing model
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.
Lightpanda: Use the cloud billing unit and account limits for hosted access. A lower rate only helps if the target pages and required actions complete correctly on the selected engine.
Capacity and 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.
Lightpanda: Use Lightpanda Cloud's limits and billing documentation for hosted capacity. Self-operated engine instances have a different capacity model and should not inherit cloud account assumptions.
Which approach fits?
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.
Choose Lightpanda when your workflow can use Lightpanda's supported browser APIs and you want to evaluate that engine on the pages you actually automate.
Lightpanda tradeoff: CDP connectivity does not establish complete Chromium compatibility. Validate rendering-dependent steps, downloads and browser features with the selected engine before a migration.
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 AWS AgentCore Browser and Lightpanda 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
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.
Lightpanda introduces a browser-engine decision. Keep it on the shortlist when its supported actions fit the real pages you use; a successful CDP connection or text task does not establish visual or full-browser equivalence with the proposed Notte 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: docs.aws.amazon.com [1] ↗lightpanda.io [2] ↗docs.notte.cc [3] ↗