deliberate.codes

Weblog of Marco N. - a software guy in data. I build with AI.

agent-browser: headless browser CLI for AI agents

agent-browser is a Rust-based CLI that gives AI agents browser control through simple commands. It uses accessibility trees for semantic element selection instead of brittle CSS selectors.

Install and set up:

npm install -g agent-browser
agent-browser install  # downloads Chromium

Basic workflow:

agent-browser open example.com
agent-browser snapshot              # get accessibility tree with refs
agent-browser click @e2             # click element by reference
agent-browser fill @e3 "email@test.com"
agent-browser screenshot page.png
agent-browser close

Find elements semantically:

agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "user@test.com"

The --profile flag persists login sessions across runs. The --session flag isolates browser instances.