Getting started
Four steps from nothing to your agent driving your logged-in browser.
1. Install the CLI
$ npm i -g @karnstack/reinsThis installs reins. Its daemon starts on its own when you run any command, and reins kill stops it. Nothing to configure.
2. Teach your agent
$ npx skills add karnstack/reinsThis teaches your agent the commands. Skip it and your agent will still say it cannot open a browser. No skill support? Point it at reins help.
3. Add the extension
Add the reins extension to each Chromium browser you want agents to reach: Chrome, Brave, Edge, Arc, Dia. Its icon turns green once it finds the daemon. No store access? See Install without the store.
4. Check
$ reins status # daemon state, port, connected browsers$ reins tabs # every tab across every connected browser$ reins doctor # diagnostic checks when something looks off
The loop agents use
Look, act, check.
$ reins snapshot e3: input "Email" e7: button "Sign in"$ reins type --ref e3 --text "you@work.dev"$ reins click --ref e7$ reins text
Page commands act on the active tab unless you pass --tab <id>. Add --json for raw output.