Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added public/images/browser-rendering/liveview.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added public/images/browser-rendering/webMCP.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added public/images/browser-rendering/webMCPagent.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
---
title: "Browser Run adds Live View, Human in the Loop, and Session Recordings"
description: "See what your agent sees in real time with Live View, let humans step in when automation needs help, and replay any session after it ends with Session Recordings."
products:
- browser-rendering
date: 2026-04-15T11:00:00Z
publish_future_dated_entry: true
---

When browser automation fails or behaves unexpectedly, it can be hard to understand what happened. We are shipping three new features in [Browser Run](/browser-rendering/) (formerly Browser Rendering) to help:

- **[Live View](/browser-rendering/features/live-view/)** for real-time visibility
- **[Human in the Loop](/browser-rendering/features/human-in-the-loop/)** for human intervention
- **[Session Recordings](/browser-rendering/features/session-recording/)** for replaying sessions after they end

### Live View

[Live View](/browser-rendering/features/live-view/) lets you see what your agent is doing in real time. The page, DOM, console, and network requests are all visible for any active browser session. Access Live View from the Cloudflare dashboard, via the hosted UI at `live.browser.run`, or using native Chrome DevTools.

### Human in the Loop

When your agent hits a snag like a login page or unexpected edge case, it can hand off to a human instead of failing. With [Human in the Loop](/browser-rendering/features/human-in-the-loop/), a human steps into the live browser session through Live View, resolves the issue, and hands control back to the script.

Today, you can step in by opening the Live View URL for any active session. Next, we are adding a handoff flow where the agent can signal that it needs help, notify a human to step in, then hand control back to the agent once the issue is resolved.

![Browser Run Human in the Loop demo where an AI agent searches Amazon, selects a product, and requests human help when authentication is needed to buy](/images/browser-rendering/liveview.gif)

### Session Recordings

[Session Recordings](/browser-rendering/features/session-recording/) records DOM state so you can replay any session after it ends. Enable recordings by passing `recording: true` when launching a browser. After the session closes, view the recording in the Cloudflare dashboard under **Browser Run** > **Runs**, or retrieve via API using the session ID. Next, we are adding the ability to inspect DOM state and console output at any point during the recording.

![Browser Run session recording showing an automated browser navigating the Sentry Shop and adding a bomber jacket to the cart](/images/browser-rendering/sessionrecording.gif)

To get started, refer to the documentation for [Live View](/browser-rendering/features/live-view/), [Human in the Loop](/browser-rendering/features/human-in-the-loop/), and [Session Recordings](/browser-rendering/features/session-recording/).
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
---
title: "Browser Rendering is now Browser Run"
description: "We are renaming Browser Rendering to Browser Run and shipping Live View, Human in the Loop, Session Recordings, WebMCP, 4x higher limits, and more."
products:
- browser-rendering
date: 2026-04-15T12:00:00Z
publish_future_dated_entry: true
---

We are renaming Browser Rendering to **[Browser Run](/browser-rendering/)**. The name Browser Rendering never fully captured what the product does. Browser Run lets you run full browser sessions on Cloudflare's global network, drive them with code or AI, record and replay sessions, crawl pages for content, debug in real time, and let humans intervene when your agent needs help.

Along with the rename, we have increased limits for Workers Paid plans and redesigned the Browser Run dashboard.

We have 4x-ed concurrency limits for Workers Paid plan users:

- **Concurrent browsers per account**: 30 → **120 per account**
- **New browser instances**: 30 per minute → **1 per second**
- **REST API rate limits**: recently increased from [3 to 10 requests per second](/changelog/post/2026-03-04-br-rest-api-limit-increase/)

Rate limits across the [limits page](/browser-rendering/limits/) are now expressed in per-second terms, matching how they are enforced. No action is needed to benefit from the higher limits.

The [redesigned dashboard](https://dash.cloudflare.com/?to=/:account/browser-rendering) now shows every request in a single Runs tab, not just browser sessions but also quick actions like screenshots, PDFs, markdown, and crawls. Filter by endpoint, view target URLs, status, and duration, and expand any row for more detail.

![Browser Run dashboard Runs tab with browser sessions and quick actions visible in one list, and an expanded crawl job showing its progress](/images/browser-rendering/BRdashboardredesign.png)

We are also shipping several new features:

- **[Live View, Human in the Loop, and Session Recordings](/changelog/post/2026-04-15-br-observability/)** - See what your agent is doing in real time, let humans step in when automation hits a wall, and replay any session after it ends.
- **[WebMCP](/changelog/post/2026-04-15-br-webmcp/)** - Websites can expose structured tools for AI agents to discover and call directly, replacing slow screenshot-analyze-click loops.

For the full story, read our Agents Week blog [Browser Run: Give your agents a browser](https://blog.cloudflare.com/browser-run-for-ai-agents).
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
---
title: "Browser Run adds WebMCP support"
description: "AI agents can now discover and execute website tools directly using WebMCP, enabling faster and more reliable browser automation."
products:
- browser-rendering
date: 2026-04-15T10:00:00Z
publish_future_dated_entry: true
---

[Browser Run](/browser-rendering/) (formerly Browser Rendering) now supports [WebMCP](https://webmachinelearning.github.io/webmcp/) (Web Model Context Protocol), a new browser API from the Google Chrome team.

The Internet was built for humans, so navigating as an AI agent today is unreliable. WebMCP lets websites expose structured tools for AI agents to discover and call directly. Instead of slow screenshot-analyze-click loops, agents can call website functions like `searchFlights()` or `bookTicket()` with typed parameters, making browser automation faster, more reliable, and less fragile.

![Browser Run lab session showing WebMCP tools being discovered and executed in the Chrome DevTools console to book a hotel](/images/browser-rendering/webMCP.gif)

With WebMCP, you can:

- **Discover website tools** - Use `navigator.modelContextTesting.listTools()` to see available actions on any WebMCP-enabled site
- **Execute tools directly** - Call `navigator.modelContextTesting.executeTool()` with typed parameters
- **Handle human-in-the-loop interactions** - Some tools pause for user confirmation before completing sensitive actions

WebMCP requires Chrome beta features. We have an experimental pool with browser instances running Chrome beta so you can test emerging browser features before they reach stable Chrome. To start a WebMCP session, add `lab=true` to your `/devtools/browser` request:

```bash
curl -X POST "https://api.cloudflare.com/client/v4/accounts/{account_id}/browser-rendering/devtools/browser?lab=true&keep_alive=300000" \
-H "Authorization: Bearer {api_token}"
```

Combined with the recently launched [CDP endpoint](/browser-rendering/cdp/), AI agents can also use WebMCP. Connect an [MCP client](/browser-rendering/cdp/mcp-clients/) to Browser Run via CDP, and your agent can discover and call website tools directly. Here's the same hotel booking demo, this time driven by an AI agent through OpenCode:

![Browser Run Live View showing an AI agent navigating a hotel booking site in real time](/images/browser-rendering/webMCPagent.gif)

For a step-by-step guide, refer to the [WebMCP documentation](/browser-rendering/features/webmcp/).
Loading