Cloudflare Browser Run vs AWS AgentCore Browser

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.

Cloudflare Browser Run provides headless browser sessions through CDP and browser code deployed in Workers. This comparison concerns sessions and their execution model, rather than the separate Quick Actions APIs.

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

Sources: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗

What survives a session

Cloudflare Browser Run: Cloudflare documents reuse of browser sessions and a Durable Objects integration. Keeping a session alive is different from exporting a portable authenticated profile; design the required state store explicitly.

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.

Sources: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗

Website login

Cloudflare Browser Run: Use browser code to implement the website's sign-in flow and retain the necessary session state. The reviewed overview does not establish a managed website connection that checks sign-in readiness before a workflow starts.

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.

Sources: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗

Where the code runs

Cloudflare Browser Run: Deploy browser automation within a Cloudflare Worker or connect to Browser Run from an external process over CDP. Workers provide the execution layer; compare their runtime and deployment model separately from browser access.

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.

Sources: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗

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.

Sources: browserarena.ai [1] ↗browserarena.ai [2] ↗github.com [3] ↗

Pricing model

Cloudflare Browser Run: Price browser usage and the Worker execution components required by the workload. The Browser Run pricing page, rather than a single browser-hour estimate, defines included allowances and applicable limits.

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: developers.cloudflare.com [1] ↗aws.amazon.com [2] ↗

Capacity and limits

Cloudflare Browser Run: Browser Run has its own limits and pricing alongside Workers. Account browser capacity, session creation limits and the Worker execution budget constrain different parts of a workflow.

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.

Sources: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗

Which approach fits?

Choose Cloudflare Browser Run when you already deploy Workers and want browser automation within that application's execution and scheduling model.

Cloudflare Browser Run tradeoff: A Worker and a browser session have separate resource and lifecycle constraints. Confirm the chosen browser library and binding path instead of assuming an unchanged local browser script will deploy directly.

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.

Sources: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗

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 Cloudflare Browser Run 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

Cloudflare can be an economical architectural choice when Workers and the surrounding scheduling already exist in your application. Notte is worth evaluating when a browser, deployed Python handler and authentication workflow should share a product rather than a Workers composition.

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: developers.cloudflare.com [1] ↗docs.aws.amazon.com [2] ↗docs.notte.cc [3] ↗

Keep comparing