Skip to content
Technology How it works Breeder — Hyperion Burner — Aegis Burner — MetroVolt AI-Native Architecture Magnets Fuel cycle Safety Roadmap
Solutions AI & Data Centers Defense & Government Grid & Baseload Neutron Detection Quantum
Learn Technical Library
Proof Publications Whitepapers Technical Library Open Science & Reproducibility The Honest Gates
Company About / Mission Leadership Environment Health & Safety Investors Careers Press Contact
3D Model
AI Architecture › L7 · Ecosystem & Strategy
L7 · Ecosystem & Strategy

The Digital-Twin Fleet Registry

A registry holds a live twin for every unit, tagged by machine type, generation, and configuration, forming the addressable model of the whole fleet.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L7 · ECOSYSTEM & STRATEGYThe plant in its world — integrated through one unified API.1Unified API Layerone door in/out2Grid Integrationdispatch & firm supply3Supply Chainfuel, parts, isotopes4Maintenanceservice & spares loops5Regulatorycompliance & reporting6Fleet Strategymulti-unit planningMACHINE TIEConnects the machine to grid, suppliers, and regulators — the outermost loop.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORECOSYSTEM & STRATEGYSHEET 09REV. 2026-08L7 · AI-NATIVE STACK
L7 · Ecosystem & Strategy — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

Every unit has a twin; the registry holds them all

Each Kronos unit runs its own L3 KRONOS-CTRL twin. The fleet registry is the L7 index of all of them: a directory that maps each unit to its live twin, its machine type (breeder or burner), its housing (Aegis or MetroVolt for burners), its generation (FOAK/NOAK/BOAK), and its configuration (for the breeder, the active TBR lever; for the burner, the plug operating point). The registry is how fleet-level services address individual units.

What the registry enables

python
# registry entry per unit
{
  'unit': 'metrovolt-noak-03',
  'type': 'burner', 'housing': 'MetroVolt',
  'generation': 'NOAK',
  'config': {'plug_field_T': 26.49, 'throat_field_T': 17.0,
             'neutron_fraction': 0.0544},
  'twin_endpoint': 'internal://twin/metrovolt-noak-03',
  'status': 'design-stage',        # -> commissioned at build-out
}

The registry is the join point for the other fleet services. Multi-unit coordination iterates the registry to read state and issue intents; fleet learning uses the type/generation/config tags to decide where a model update is compatible; spare-parts lifecycle uses configuration to match a spare to a unit. Without the registry, fleet-scale services would have no consistent way to know what they are acting on.

Configuration is part of identity because it changes physics. A breeder at TBR lever 1.8 breeds and consumes differently from one at 1.1; a burner at its nominal 26.49 T plug behaves differently from one de-rated for maintenance. The registry carries the active configuration so fleet decisions use each unit's true operating point, not a nominal one.

The registry today lists design-stage units backed by their twins in simulation. As units are built from Q2 2027 and commissioned from FOAK ~2030, their status advances in the registry, and fleet services extend to them automatically because they are already addressable.

Content reviewed August 2026 · design-and-simulation stage