Patent: Split AI

Optimize available bandwidth for efficient video processing

Split AI is a patented technology that enables Dragonfruit to provide WAN optimization for high-resolution video processing and uploads. Traditional video analytics required either expensive on-premise GPU capacity for local processing or large network bandwidth capacity for uploading videos to the cloud. Dragonfruit's patented Split AI solves this dilemma by deploying a zero-cost HaaS Base Station on premise. This revolutionary hardware runs on the Apple M1 chipset, which was built for video and ML processing. The AI models deployed on the Base Station work in tandem with their counterparts int the cloud, ensuring low bandwidth usage (as low as 20kbps!) while simultaneously delivering superior AI performance.

Why Dragonfruit patented Split AI

Bandwidth is a challenge

Bandwidth is one of the greatest challenges for uploading video to the cloud.

WAN optimization

WAN optimization is critical to leverage the power of the cloud

Cloud x On-prem

Dragonfruit’s Split AI technology runs AI in the cloud as well as on-premise

Example of How Split AI Works


Let’s Talk