Edge intelligence
Small Language Models and decision engines that run on the device.
Distilled, quantized and pruned models sized for mobile NPUs and ARM64 nodes — inference in milliseconds, no cloud round-trip.
ANEMOD designs the hardware and software that let embedded systems think, save energy and defend themselves — from edge energy arbitration appliances to TLS 1.3 servers inside secure elements.
Designing embedded and edge systems without AI, frugality and security working together will soon be inconceivable. ANEMOD builds them as one.
Small Language Models and decision engines that run on the device.
Distilled, quantized and pruned models sized for mobile NPUs and ARM64 nodes — inference in milliseconds, no cloud round-trip.
Intelligence that fits a sub-10 W envelope.
From model compression to edge energy arbitration of PV, batteries, EVs and HVAC — frugality is the design constraint, not the afterthought.
TLS 1.3 inside the secure element.
H2S, HSM grids, signed firmware and zero-trust architectures — assurance up to EAL6+ / EAL7 for the systems that cannot fail.
Decides locally. Keeps the data home.
A sub-10 W ARM64 edge appliance running ANEMOD’s energy arbitration engine. It reads and actuates residential PV, batteries, EV chargers and HVAC in real time — sovereign, offline-capable and secure by design.
CELTIC-NEXT RAI-6Green
Real-time arbitration of residential energy assets on the nYOI Energy Arbiter, federated learning between appliances, data sovereignty by design.
Small Language Models optimized for embedded systems — AI that runs on the device, without a cloud round-trip, and keeps its accuracy through knowledge distillation.
A secure element combining HSM functions with a TLS 1.3 server, for the secure distribution of cryptographic keys — the first TLS 1.3 server embedded in a secure element.
Pilots, integrations, quotes for the nYOI Energy Arbiter or the pNHSM range, research collaborations — write to us.
ANEMOD 4, résidence de Galande92320 ChâtillonFrance contact@anemod.fr