Hi Product Hunt, I’m Davide, the builder behind Scalebrowser. I built it because browser agents kept failing before they reached the useful part of the job. They were detected at the connection or control layer, came back as a different device, stopped at a login code or permission bubble, or spent their entire context reading the page. Scalebrowser is my attempt to solve that as one system instead of another patch on top of Playwright. It runs a patched Chromium fork on your own hardware and gives every agent an isolated profile with a persistent identity. Cookies, credentials, passkeys, memory, and tasks stay with that profile. Email and SMS codes, TOTP, captchas, and browser prompts can be handled without handing the session back to a person. The agent connects over MCP, REST, Node.js, Python, or direct CDP. It reads a compact map of the page and then only what changed. Every step is recorded with a screenshot, and secrets are filtered before page content reaches the model. One part I’m especially excited about: a completed run can become a polished product video with automatic camera movement, cursor motion, voiceover, subtitles, and channel-ready exports. The same recording can also be rendered as an unbroken proof trail. Scalebrowser is self-hosted, but not open source or offline: the browser data stays on your machines, while the paid account controls licensing. Every plan includes all features and unlimited profiles. Pricing starts at €19 per month, with a seven-day trial. I’d love to hear where your browser agents fail today: detection, login, context, or something I have not covered yet.

Scalebrowser

Human browser capabilities. Now for AI agents.

Human browser capabilities. Now for AI agents.