Browser Tool

Headless Chrome automation for web browsing, form filling, and screenshots. Requires the browser feature.

Feature Flag

Build with cargo build --release --features browser to enable this tool.

Configuration

config.toml

[browser]
enabled = true
headless = true
screenshot_width = 1280
screenshot_height = 720
user_data_dir = "~/Library/Application Support/Google/Chrome"
profile = "Default"

Methods

Method	Parameters	Description
`navigate`	`url`	Navigate to URL, wait 2s for load
`screenshot`	`selector?`	PNG screenshot of page or element
`click`	`selector`	Click a page element
`fill`	`selector, value`	Fill an input field
`get_text`	`selector?`	Extract text content
`get_attribute`	`selector, attr`	Read an HTML attribute
`wait_for_selector`	`selector, timeout_ms`	Poll until element appears

Chrome Profile Reuse

Setting user_data_dir and profile lets the browser inherit an existing Chrome session — cookies, login state, and extensions. This allows the agent to interact with authenticated sites.

Screenshots

Screenshots are captured as PNG and sent to the user via Telegram as photo messages with captions describing the page content.

PreviousConfig Manager Tool NextSub-Agent Spawning