One console for every orbital mission.
Plan a workload, deploy it to your own satellite or constellation, and watch the fleet, live. Mission Control is the operational console where orbital compute actually runs - built and running, and rolling out through early access.
Bring your own satellite. Or your whole constellation.
Target any of 14,610 cataloged objects by NORAD ID, or define a custom asset, its altitude, inclination, period, and bus class, and Mission Control plans against it. Group satellites into constellations and run one workload across the whole fleet.
- Any NORAD-cataloged satellite, or your own orbital definition
- Constellations spanning multiple orbital planes
- One plan, coordinated across every asset in the fleet
Describe a workload. Get a feasible plan, or an honest no.
$ curl https://api.rotastellar.com/v1/plan \ -H "Content-Type: application/json" \ -d '{ "satellite_id": "25544", "preset_id": "onboard-ml-inference" }' # CAE returns a constraint-aware plan { "satellite": { "name": "ISS (ZARYA)", "altitude_km": 408 }, "preset": { "id": "onboard-ml-inference", "steps": 4 }, "orbital_environment": { "eclipse_fraction": 0.35 }, "plan": { "total_duration_s": 2700, "windows_used": 8, "status": "scheduled" }, "error_budget": { "delivery_confidence": 0.98 } }
Everything you need to run a mission.
Missions & plans
Create a mission against a satellite or a whole constellation, pick a preset, and the constraint-aware planner returns a feasible plan, or names the binding constraint.
Constellations & assets
Group satellites into fleets, import from the catalog or define custom orbital assets, and coordinate workloads across the whole constellation.
Simulated and live deploys
Validate a plan on a simulated run, then deploy to real agents over the pull-based protocol and watch typed events stream back as the workload executes.
Fleet monitoring
A 3D globe of 500+ tracked objects, live agent telemetry (battery, thermal, eclipse state), and ground-station contact windows, refreshing in real time.
Stay ahead of hazards
Watchlist the satellites you care about and get conjunction and hazard alerts ranked by risk, with manual re-checks on demand.
Developer access
Issue live and test API keys, track per-key usage, and build on the same APIs the console runs on, with SDKs for Python, Rust, and Node.
Read the docs →Pass predictions, link budgets, and compute capacity, per satellite.
| Station | AOS (UTC) | Duration | Max el |
|---|---|---|---|
| Svalbard | 14:02:31 | 9m 12s | 78° |
| Awarua | 14:51:08 | 7m 04s | 41° |
| Hartebeesthoek | 15:38:55 | 8m 21s | 62° |
| Punta Arenas | 16:20:12 | 6m 47s | 33° |
Where Mission Control is going.
Today the console plans, deploys, and monitors real missions. Next, it closes the loop end to end. These are previews of what we're building, not live yet.
Hand the console a model and a target; it plans, deploys, and runs inference on-orbit, the full "run AI in orbit" loop without leaving Mission Control.
Plans already meter Orbital Compute Units under the hood. Next, a dollar figure on each plan so you know the cost before you commit.
Organizations and roles are live for teams today; richer approvals, shared watchlists, and audit trails are next.
Put your first workload in orbit.
Tell us what you want to run and the satellite you want to run it on. We'll come back with a feasible plan - or an honest reason it can't be done yet.