New in Osaurus: Browser Use, driven by a 9B local model
Osaurus agents can now drive a real browser. You give the agent a goal in plain language, and it navigates, clicks, reads pages, and reports back.
The demo we shipped it with: a 9B model checking an Amazon shopping cart. Real browser, real login, real cart. It signed in, read the page, and returned the items and prices. About 90 seconds, running locally on a Mac.
What makes it different from cloud browser agents:
The model runs on your machine. Each agent gets its own isolated browser profile, so sign-ins persist across sessions and never leak between agents or into your personal browser.
It is off by default and enabled per agent. Every action passes through an approval gate: reading and navigating are automatic, but typing, submitting forms, and anything that looks like a purchase asks you first. Sign-ins happen in a visible window you complete yourself. The model never touches credentials.
Osaurus is free, MIT licensed, and open source. Local models need 16GB RAM to get started, 24GB recommended.
If you try it, we want to hear what breaks. Negative feedback is the most useful kind.
Replies
This is one of the more compelling use cases for local models I have seen recently. Browser automation is powerful, but keeping the model and browser profile local changes the privacy equation completely. Curious what tasks surprised you most during testing?
Osaurus
@rehan_aslam6 I had it order stuff for me on Amazon, it arrived at my house. We ended up having extra sets of tissues
The isolated browser profile approach sounds very thoughtful. My biggest concern with browser agents is accidental access to unrelated sessions or data. How strict is the isolation, and can one agent ever access another agent’s profile?
Osaurus
@maya_boothman It's fully isolated per agent. Each agent gets their own sessions that requires individual logins.
This is the kind of automation I would actually feel comfortable experimenting with. Keeping credentials out of the model while still allowing local browser sessions is a smart design choice.
Osaurus
@sheik_born Absolutely! Local browsers are perfect for automation
How does the agent decide when something looks like a purchase? Is that based on specific browser actions, page context, or a model-level decision? That approval boundary seems technically fascinating.
Osaurus
@ibrahim_adamu2 You get to control it. It does open up a nice dialog before any confirmation, but I've had it order stuff for me on Amazon before
This feels like one of those projects that gets more interesting the more edge cases you throw at it. I’d love to try breaking it on random websites.
Osaurus
@maryam_nafees1 Please do!
I really like the “visible window + approval gate” approach. Fully autonomous browser agents sound exciting until they do something irreversible. This feels like a better progression toward trust.
Osaurus
@joseph_parker3 Absolutely. Fully private AI with fully private browsing experience
90 seconds on a local 9B model is honestly impressive. I’m curious how much faster this gets with a higher-end Apple Silicon machine.
Promomix
The technology is impressive, but the UX will decide adoption. The approval moments seem important — how are you making sure users don’t get overwhelmed with constant confirmations?