vaaya / discover / browser automation

Browser automation for AI agents

A real browser your agent drives — sign up to your app, test the flow, screenshot what confused it, and report back.

What it's for

Drive a real remote browser to act on a page — click, type, navigate.
Sign up to your app, run through a flow, or fill a multi-step form.
Takes screenshots along the way so you can see what happened.
For acting on a page, not just reading it — sign-ups, logins, checkouts.

How to ask your agent

Connect Vaaya, then just say it in plain language. For example:

❯Sign up to my staging app as a new user and tell me where the flow confuses.

❯Log into this dashboard and screenshot the billing page.

What you get back

{
  "session_id": "bb_9f2e1c04",
  "paidMinutes": 10,
  "result": {
    "signed_up": true,
    "stuck_at": "plan-selection screen — no visible \"skip\" option",
    "screenshot_url": "https://…/stuck-plan-select.png"
  }
}

Pricing

0.2¢ per minute reserved (~$0.12/hour). Billed per call in cents, capped by your max, every call on the ledger. Failed calls are not billed.

Give your agents this.

Connect Vaaya once, then describe the outcome. It picks the right capability, runs it, and pays per call.

npx @vaaya/mcp install