> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-mintlify-cli-docs-1773354647.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CLI

> Control browsers from the command line with navigation, interaction, cookies, JavaScript execution, and agent tasks.

The Browser Use CLI provides direct browser control without writing Python code. Install the package and run commands to navigate, interact, manage cookies, and execute agent tasks.

## Installation

```bash theme={null}
pip install browser-use
```

Verify the installation:

```bash theme={null}
browser-use --help
```

## Commands

### Navigation

Navigate to a URL:

```bash theme={null}
browser-use navigate --url "https://example.com"
```

Go back or forward:

```bash theme={null}
browser-use back
browser-use forward
```

Refresh the current page:

```bash theme={null}
browser-use refresh
```

### Interaction

Click an element by selector:

```bash theme={null}
browser-use click --selector "#submit-button"
```

Type text into an input field:

```bash theme={null}
browser-use type --selector "#search" --text "browser automation"
```

Scroll the page:

```bash theme={null}
browser-use scroll --direction down --amount 500
```

Take a screenshot:

```bash theme={null}
browser-use screenshot --output screenshot.png
```

### Cookies

Export cookies to a file:

```bash theme={null}
browser-use cookies export --output cookies.json
```

Import cookies from a file:

```bash theme={null}
browser-use cookies import --input cookies.json
```

Clear all cookies:

```bash theme={null}
browser-use cookies clear
```

### Wait

Wait for an element to appear:

```bash theme={null}
browser-use wait --selector "#loading" --state hidden
```

Wait for a specific duration (in milliseconds):

```bash theme={null}
browser-use wait --timeout 3000
```

### JavaScript

Execute JavaScript in the browser:

```bash theme={null}
browser-use js --code "document.title"
```

Execute JavaScript from a file:

```bash theme={null}
browser-use js --file script.js
```

## Agent tasks

Run an AI agent to complete a task:

```bash theme={null}
browser-use agent --task "Find the top post on Hacker News"
```

Specify a model:

```bash theme={null}
browser-use agent --task "Search for flights to Paris" --model gpt-4.1-mini
```

Use a custom prompt:

```bash theme={null}
browser-use agent --task "Fill out the contact form" --system-prompt "Be concise and efficient"
```

## Cloud sessions

Connect to a Browser Use Cloud session:

```bash theme={null}
browser-use cloud connect --session-id <session-id>
```

Create a new cloud session:

```bash theme={null}
browser-use cloud create
```

List active sessions:

```bash theme={null}
browser-use cloud list
```

<Note>
  Cloud sessions require a `BROWSER_USE_API_KEY`. Set it in your environment or `.env` file.
</Note>

## Tunnels

Expose your local browser to the cloud:

```bash theme={null}
browser-use tunnel start
```

Stop an active tunnel:

```bash theme={null}
browser-use tunnel stop
```

Check tunnel status:

```bash theme={null}
browser-use tunnel status
```

## Profile management

Create a browser profile:

```bash theme={null}
browser-use profile create --name "work"
```

List available profiles:

```bash theme={null}
browser-use profile list
```

Use a specific profile:

```bash theme={null}
browser-use navigate --url "https://example.com" --profile "work"
```

Delete a profile:

```bash theme={null}
browser-use profile delete --name "work"
```

## Usage examples

### Complete workflow

Navigate, interact, and extract data:

```bash theme={null}
# Start browser and navigate
browser-use navigate --url "https://news.ycombinator.com"

# Click on a link
browser-use click --selector ".titleline a"

# Take a screenshot
browser-use screenshot --output page.png

# Extract page title with JavaScript
browser-use js --code "document.title"
```

### Authentication with cookies

Save and restore login state:

```bash theme={null}
# Navigate and log in manually or with agent
browser-use agent --task "Log in to example.com with username demo"

# Export cookies for later use
browser-use cookies export --output auth-cookies.json

# In a new session, restore cookies
browser-use cookies import --input auth-cookies.json
browser-use navigate --url "https://example.com/dashboard"
```

### Cloud-based automation

Run tasks in the cloud:

```bash theme={null}
# Create a cloud session with a profile
browser-use cloud create --profile "authenticated-user"

# Run an agent task in the cloud
browser-use agent --task "Extract data from dashboard" --cloud
```

## Environment variables

| Variable               | Description                                   |
| ---------------------- | --------------------------------------------- |
| `BROWSER_USE_API_KEY`  | API key for cloud features                    |
| `BROWSER_USE_HEADLESS` | Run browser in headless mode (`true`/`false`) |
| `BROWSER_USE_PROFILE`  | Default profile to use                        |