AI inference
from orbit to ground.
Run AI compute on the bus, at the dish, and inside facilities that will never route to the cloud. One platform across every link in your constellation.
[ The Constraint ]
The downlink is the bottleneck.
Every byte has a cost. Satcom is slow, contested, or metered. The data your operators need lives where the link is weakest. On the bus between passes. At the dish while the ground segment is under load. Inside a facility that will never route to the cloud.
The AI stack assumes a warm GPU in a hyperscaler region. None of that is true for space. Sector88 moves the compute to where the data already is.
[ Deployment Environments ]
Four environments. One platform.
One system. One API. Across every link your fleet has.
Fig 1.1
Compute on the bus
Jetson-class compute on the spacecraft. Tiered memory keeps models running on constrained boards. Onboard decisions happen between passes.
Fig 1.2
Process at the dish
Run analytics where the data lands. Triaged insights move to the analyst workflow. Raw telemetry stays on site. Bandwidth budgets recover and the ground segment stops being the bottleneck.
Fig 1.3
Inside the perimeter
Install from media. Built for zero egress. Metadata-only logs, built to feed your SIEM. Classified payloads stay inside the perimeter. No new vendor ingress to justify.
Fig 1.4
One control plane, many sites
Pin a model at one ground station, promote to the rest when clean, roll back from one place. No SSH into individual machines.
[ Day One ]
What changes when compute moves to the edge.
Fig 2.1
Downlink insight, not telemetry
Compute at the dish turns raw passes into decisions. The ground segment stops being rate-limited. You send decisions, not data.
Fig 2.2
Bigger models at the ground station
Tiered memory orchestration runs model classes that should not fit. One platform from a single Jetson to a rack of H100s.
Fig 2.3
Classified payloads stay classified
Air-gapped, ITAR-aware, built for zero egress. Deploy inside the perimeter you already have. No new attack surface.
[ Forward-Deployed ]
Audit. Install. Harden.
Our engineers sit alongside your team. They audit the site, install the platform on your ground segment, benchmark against your actual workloads, and harden it for production. Fixed scope. You own it when it runs.
Fig 3.1
Site audit
Hardware review on the bus, at the dish, and in the facility. Plan signed off before install.
Fig 3.2
Install and benchmark
Throughput, latency, and cost measured on your actual hardware. Scorecard delivered.
Fig 3.3
Harden for production
IdP, SIEM, secrets management, supervisor restart. Production-ready before we close the ticket.
Deploy in your environment.
Tell us your ground segment, link profile, and perimeter constraints. We will show you what is possible.