17/03/2026
Building AI has quietly become one of the most centralized technologies on the planet. Most assistants live in someone else’s cloud, run on someone else’s servers, and learn from data that users rarely control.
OLOS AI started with a simple idea: what if your AI actually belonged to you?
Not rented. Not locked behind a platform. But running on hardware you control.
That idea is what led to the creation of OSCAR.
Development is now well underway. The backend architecture is taking shape and we’re already running local AI models through Ollama as part of the core system. A persistent memory framework is being built so OSCAR can actually remember and organize information over time.
The system already includes early practical tools like a planner, to-do list, and shopping list, which are helping shape how OSCAR interacts with everyday tasks. We’re also experimenting with a portable version called Oscar USB — a private AI assistant that can run directly from a drive and travel with you.
There is still a lot of work ahead, but the foundations are now forming.
Long term, the goal isn’t just another chatbot. The vision is a personal AI operating system.
A system that can run on home hardware, connect to multiple AI models, route tasks intelligently between local and cloud intelligence, and eventually scale to private enterprise nodes for businesses that need secure AI capability.
In short: sovereign AI — AI that belongs to the user.
If you’re curious about where this goes next, follow along. This project is being built in the open, one piece at a time.