Comment by keepamovin

WebCLI - screenshots are a dead end. MCP is too verbose and clunky. Agents native language is text. Web CLI is just a Unix-y CLI that pipes/translates the web to text. Run any task on a web browser, but don't do it yourself (only the parts you have to - MFA, Login, CAPTCHA, whatever). An agent + WebCLI does anything you throw at it.

  web go news.ycombinator.com
  cat reply.txt | web say -
  web find add comment
  web do 44

just. like. that. Super simple. CLI or REPL. You can do it by hand but you probably don't want to, just give it to an agent. Run web teach to imprint the SKILL.md files into the current directory tree and an agent can hit the ground running. It's the end of browser automation for everything but super scripted fixed path CI/testing etc (those latter things where pptr/playwright/et al are still ok). WebCLI is browser improvization. Try it - 5 days free. I sprinted on this the last few weeks. It's really good. So useful. https://webcli.sh/