STERNA is EDGX’s AI-powered edge computer for satellites with space grade reliability.

BRUSSELS, April 9, 2026 /PRNewswire/ — Belgian spacetech EDGX has successfully launched its first in-orbit demonstration of STERNA, an AI-powered edge computer for satellite constellations aboard SpaceX’s Transporter-16 mission. With two hosted payloads now in orbit, EDGX enables real-time data processing directly in space, a critical capability for next-generation satellite constellations across commercial, governmental, and defence applications.

Through STERNA, the company brings high-performance, NVIDIA-based processing directly onboard satellites, allowing data to be analysed in orbit rather than relying solely on ground infrastructure. STERNA is an NVIDIA-powered computing platform, designed to run high-performance workloads directly in orbit. Engineered for real in-orbit constraints, it dynamically scales power between 10W and 45W, ensuring continuous data processing under varying power and thermal conditions. The system is designed for long-term reliability, with a target operational lifetime of 7 years in orbit.

The news is a key milestone for Europe’s space-based computing infrastructure and follows a €2.3 million seed funding round in June 2025.

Commenting on the news, EDGX CEO Nick Destrycker said: “This launch marks a key milestone for EDGX and for Europe’s position in space-based computing. By bringing high-performance compute directly into orbit, we’re enabling satellites to move from data collection platforms to real-time decision-making systems. Our focus is simple: deliver reliable, scalable compute infrastructure in space, and this mission is the first step.

“We believe the next phase of the space industry will be defined by compute in orbit. This mission is the first step in building that infrastructure, turning satellites into intelligent, software-defined systems capable of processing data where it is generated.”

By bringing NVIDIA-class compute performance into space, EDGX enables a new generation of software-defined satellites capable of running advanced AI workloads, from Earth observation analytics to real-time signal intelligence, directly where the data is generated. This reduces latency, cuts bandwidth usage, and supports faster decision-making for operators on the ground.

This capability eliminates the traditional bottleneck of sending massive raw datasets to Earth for processing, enabling satellite operators to deliver faster, more efficient, and data-driven services. In defence scenarios for example, this translates into a real operational advantage: reducing the time between detection and action on the battlefield.