agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate…
- installs 8w
- 1,919
- 30-day movement
- starts with the next reading
- Related entries
- 32
- Connections
- 2
An agent skill that teaches an AI coding agent to drive a browser through the agent-browser CLI, which controls Chrome/Chromium over CDP. It covers navigation, forms, clicks, screenshots, data extraction, sessions, and opt-in security features like domain allowlists and content boundaries.
Reach for it when a task requires programmatic web interaction—opening sites, filling forms, scraping data, or testing web apps—so the agent uses a documented CLI workflow instead of improvising.
Use it to
- Automate form submission and login flows
- Scrape or extract data from web pages
- Take screenshots and record video of pages
- Test web apps including responsive and dark-mode rendering
- Run parallel named browser sessions
For AI coding agents and developers automating browser tasks
- Host repository
- brianlovin/agent-config
- Installs, lifetime
- 2,200
- Installs, 8 weeks
- 1,919
- Allowed tools
- Bash(npx agent-browser:*), Bash(agent-browser:*)
- Host stars
- 368
- Host language
- Shell