BROWSER USE

- Browser Use Agents: give Browser Use a task and receive completed work. API V4 is current for new integrations.
- Browser Infrastructure: connect your agent or automation to managed browsers through SDK, REST, or CDP. Starts at $0.02/browser-hour.
- Developer tools: Open Source, Browser Harness, SDK, and MCP support the two products above.

[Developer Index](https://browser-use.com/index.md)
[Product Map](https://browser-use.com/llms.txt)
[Full Product Context](https://browser-use.com/llms-full.txt)
[Pricing](https://browser-use.com/pricing.md)
[Cloud Docs](https://docs.browser-use.com/cloud/quickstart)
[Open Source Docs](https://docs.browser-use.com/open-source/introduction)

---

# Hermes Uses Browser Use by Default

![Hermes Agent logo](https://browser-use.com/_next/image?url=%2Fhermes-agent-logo.png&w=128&q=75)

Hermes Agent × Browser Use

## The web now runs through one tool.

Hermes replaced 12 browser tools with one call. Browser Use handles the clicking, typing, waiting, and recovery behind it.

**12→1**browser tools

**48–66%**fewer task tokens

**204**live runs

Hermes's current browser guide makes Browser Use the default driver and puts Browser Use Cloud first. Its merged test measured the results above.

## One call sits between the agent and the web.

The agent keeps working on the task. Browser Use keeps the browser alive, acts on the page, and adapts when the site changes.

General agent

“Find the best flight and fill the form.”

One tool call

`browser_exec("...")`

Browser Use driver

Keeps tabs, page state, waits, retries, and screenshots.

Local

Your Chrome

Cloud

Managed browser

/login

DOM changed

/checkout

The agent sends

An instruction and, when needed, a starting URL.

The driver owns

Navigation, clicks, typing, tabs, waits, and recovery.

The agent gets back

A compact result, plus a screenshot when the task needs one.

One interface. Two places to run the browser.

Use a local browser when the agent needs your open tabs, cookies, or a browser you can watch.

Use a Cloud browser when the task needs managed sessions, profiles, proxies, or parallel browsers.

Any general agent can use the same browser layer.

## Browser Use is the default way to automate the web.

[Get an API key](https://cloud.browser-use.com/settings?tab=api-keys&new=1)Copy setup prompt
