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 › Physical Interfaces
Physical Interfaces

Physical Interface Taxonomy

Every place the Kronos control stack touches metal, gas, or plasma is a typed interface with an owning layer, a latency budget, and a calibration record.

STRATEGY / SLOW ▲ ▼ MICROSECOND REAL-TIMEL7Ecosystem & Strategytelemetry ▲ control ▼open ▸L6Experience & Visualizationtelemetry ▲ control ▼open ▸L5Applications & Copilotstelemetry ▲ control ▼open ▸L4Orchestrationtelemetry ▲ control ▼open ▸L3Twin Modeling & AItelemetry ▲ control ▼open ▸L2Data Fabrictelemetry ▲ control ▼open ▸L1Control Planetelemetry ▲ control ▼open ▸L0Foundationtelemetry ▲ control ▼open ▸PHYSICAL S.M.A.R.T. GENERATOR PLANTBREEDER · HYPERION1R0 1.2 m · A 2.5 · 16.84 T · δ −0.30BURNER · TANDEM MIRROR2317 T throat · 26.49 T plug · fₙ 5.44% · DEC1 center stack + plasma · 2 high-field plug · 3 expander → direct converterCOLOR GRAMMAR strategy AI-workflow infra/data models reactor/DECLINE SEMANTICStelemetry (µs)controlKRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORMASTER BLUEPRINTSHEET 01REV. 2026-08L0-L7 · 2 MACHINES
The AI-Native S.M.A.R.T. Generator Master Blueprint — eight layers (L0→L7), one control stack, wired to both machines. Telemetry rises in microseconds; control descends the same path.

What a physical interface is

A physical interface is the boundary where a software layer of the AI-native stack reads a sensor or drives an actuator on real hardware. On the breeder (Hyperion, a D–T spherical tokamak) and the burner (Aegis / MetroVolt, a D–3He tandem-mirror generator) these interfaces span magnets, fueling, the fuel cycle, the vessel, the divertor / first wall, the burner direct-energy-conversion (DEC) train, and 60+ diagnostic ports.

Each interface is documented with the same five attributes so that any layer — and any AI agent reading this repo — can reason about it: signal set, owning layer, direction (sense / actuate / bidirectional), latency class, and calibration source.

The interface classes

Ownership rule

Latency decides ownership. Anything that can move energy or open a fault inside µs–ms is owned by the hard real-time L1 control plane; slower supervisory, campaign, and accountancy interfaces are owned by L3/L4/L7. The hardware-abstraction contracts make the boundary explicit and testable. This taxonomy is a design-and-simulation map: the machines are not yet built, and no hardware net-gain is claimed before FOAK first tritium (~2030).

Latency classOwnerExample interface
usL1quench trip
msL1shape coil supply
sL3tritium plant setpoints
min+L7isotope accountancy
Content reviewed August 2026 · design-and-simulation stage