Our Story

We are two computer engineers who met on a latency optimization Discord in 2014. Since then, we’ve been obsessed with building something that leverages multi-threaded LLM orchestration layered on top of a recursive vector-indexed caching system using our proprietary (patent-pending) inference prefetching algorithm. After 9 years of stealth R&D in our parents' basements, we realized no one had yet attempted this exact approach to semantic context reshaping, which to us was…insane.

So we built it. We call it Strokify™.

We haven’t launched yet, and we haven’t talked to any users (we’ve both been heads-down), but we’re confident this is 10–50x better than anything else out there. You wouldn’t understand the math, but trust us—it works. Our dog uses it every day.

Strokify™: The future is now.