Melaya Browser Control + Extension - Let any AI drive your browser. You watch and approve.

by•
Let AI agents drive a real browser you watch, approve, and stop. Two ways in: launch a dedicated Chrome, Edge, or Brave profile via the Melaya runner, or add the extension and attach one tab in your own browser, cloud-driven, no runner. Run any model, including open-weight local ones through Ollama or LM Studio, private with no per-message limits. Every action streams live, site allowlists and signed single-use grants keep it scoped, and it stops for approval before anything that matters.

Add a comment

Replies

Best
Maker
📌
Hey Product Hunt 👋 I'm building Melaya. This one started from a small, daily frustration: my AI could write a perfect plan, then I'd spend the next 20 minutes clicking, pasting, and screenshotting on its behalf. The model was the brain and I was the mouse. So we gave it hands, in the one place work actually happens: a real browser. You describe a task, and a Melaya agent navigates, clicks, fills forms, pulls what you need, and can even QA-test a web app end to end. You watch every action live, and it stops for your approval before anything consequential. The two hard parts were trust and freedom, and they shaped the whole build: • Trust: signed single-use, scoped grants, site allowlists, visible tool calls, secret fields that need a human handoff, and a stop button that actually stops. The agent can't approve its own consequential actions. • Freedom: run any model, including open-weight local models through Ollama or LM Studio, so it's private and free of per-message limits. Use a clean dedicated browser through the runner, or add the extension to drive one tab in your own browser with no runner. Would love your honest feedback, especially on where an agent should ask before it acts. Try it free: melaya.org/register