> ## Documentation Index
> Fetch the complete documentation index at: https://docs.browsernode.com/llms.txt
> Use this file to discover all available pages before exploring further.

# CLI

> Start using the Browsernode CLI

# CLI Usage

The `browsernode-cli` command-line interface provides multiple modes of operation for browser automation.

## Installation

Get started with browsernode-cli immediately using `npx`:

```bash theme={null}
npx browsernode-cli --help
```

## Modes of Operation

### 1. Interactive TUI Mode (Default)

Launch an interactive terminal UI where you can chat with the browser automation agent:

```bash theme={null}
npx browsernode-cli
```

This opens a chat interface where you can:

* Type natural language commands to control the browser
* See real-time feedback from the agent
* View browser state and actions being performed

### 2. One-Shot Mode

Execute a single task without entering interactive mode:

```bash theme={null}
npx browsernode-cli -p "Search for OpenAI documentation and take a screenshot" --headless
```

Options:

* `-p, --prompt`: The task to execute
* `--headless`: Run browser in headless mode
* `--model`: Specify LLM model (default: gpt-4o)

## Configuration

Browsernode can be configured through environment variables and a configuration file.

### Configuration File Location

The default configuration file is located at:

* `~/.config/browsernode/config.json`

You can override this location with:

* `BROWSERNODE_CONFIG_PATH` environment variable
* `BROWSERNODE_CONFIG_DIR` environment variable (directory containing config.json)

### Configuration File Format

The configuration uses a database-style format with UUID entries:

```json theme={null}
{
  "browser_profile": {
    "550e8400-e29b-41d4-a716-446655440000": {
      "id": "550e8400-e29b-41d4-a716-446655440000",
      "default": true,
      "createdAt": "2024-01-01T00:00:00",
      "headless": false,
      "userDataDir": null,
      "allowedDomains": ["example.com"],
      "downloadsPath": "~/Downloads/browsernode"
    }
  },
  "llm": {
    "6ba7b810-9dad-11d1-80b4-00c04fd430c8": {
      "id": "6ba7b810-9dad-11d1-80b4-00c04fd430c8",
      "default": true,
      "createdAt": "2024-01-01T00:00:00",
      "apiKey": "your-openai-api-key-here",
      "model": "gpt-4o",
      "temperature": 0.7
    }
  },
  "agent": {
    "6ba7b812-9dad-11d1-80b4-00c04fd430c8": {
      "id": "6ba7b812-9dad-11d1-80b4-00c04fd430c8",
      "default": true,
      "createdAt": "2024-01-01T00:00:00",
      "maxSteps": 100,
      "useVision": true
    }
  }
}
```

Each configuration type (browserProfile, llm, agent) can have multiple entries, with one marked as `default: true`.

### Environment Variables

Environment variables always override config.json values:

#### General Settings

* `BROWSERNODE_LOGGING_LEVEL`: Logging level (debug, info, warning, error)
* `BROWSERNODE_CONFIG_PATH`: Full path to config.json file
* `BROWSERNODE_CONFIG_DIR`: Directory containing config.json

#### Browser Profile Settings

* `BROWSERNODE_HEADLESS`: Run browser in headless mode (true/false)
* `BROWSERNODE_ALLOWED_DOMAINS`: Comma-separated list of allowed domains
* `BROWSERNODE_USER_DATA_DIR`: Chrome user data directory path

#### LLM Settings

* `OPENAI_API_KEY`: OpenAI API key
* `ANTHROPIC_API_KEY`: Anthropic API key
* `BROWSERNODE_LLM_MODEL`: LLM model to use (e.g., gpt-4o, claude-3-opus)

#### MCP-Specific Settings

When running in MCP mode, these environment variables are particularly useful:

* `BROWSERNODE_HEADLESS`: Control browser visibility
* `OPENAI_API_KEY`: Required for agent-based tools

### Browser Profiles Directory

Browser profiles are stored in:

```
~/.config/browsernode/profiles/
├── default/           # Default browser profile
├── work/             # Custom profile example
└── research/         # Another custom profile
```

Each profile directory contains Chrome user data, allowing you to:

* Maintain separate browser sessions
* Keep cookies and local storage isolated
* Use different extensions per profile

## Examples

### Basic Usage

```bash theme={null}
# Interactive mode
npx browsernode-cli

# One-shot task
npx browsernode-cli -p "Go to github.com and search for browsernode"

# Headless one-shot
npx browsernode-cli --headless -p "Extract prices from example.com/products"

# One-shot task with headless false
npx browsernode-cli -p "Go to github.com and search for browsernode" --headless false

```

### With Configuration

```bash theme={null}
# Use specific config file
BROWSERNODE_CONFIG_PATH=~/my-config.json npx browsernode-cli

# Override settings via environment
BROWSERNODE_HEADLESS=true OPENAI_API_KEY=sk-... npx browsernode-cli -p "Check my email"

# Use different LLM model
BROWSERNODE_LLM_MODEL=gpt-4-turbo npx browsernode-cli
```

## Troubleshooting

### Common Issues

1. **Browser not launching**: Ensure Chrome/Chromium is installed
2. **API key errors**: Set appropriate API key environment variables
3. **Permission errors**: Check file permissions in `~/.config/browsernode/`

### Debug Mode

Enable debug logging for troubleshooting:

```bash theme={null}
BROWSERNODE_LOGGING_LEVEL=debug npx browsernode-cli
```

## See Also

* [Getting Started](/quickstart)
* [MCP Server Documentation](/customize/mcp-server)
* [MCP Client Documentation](/customize/mcp-client)
* [Browser Settings](/customize/browser-settings)