Fall detection without surveillance.

Ilonai is building automatic fall detection for people living at home and for care facilities. Powerful AI runs locally inside the home or building — not in a video cloud.

No live camera access. No audio. No daily activity profile. If nothing happens, no image leaves the system.

In development. First home pilot being prepared.

Banner image

The problem is not only falling. It is falling when nobody knows.

An unwitnessed fall can leave someone unable to get help. A wearable only works if it is worn and can be activated. A normal indoor camera only helps if someone is watching it.

Ilonai is designed to notice a possible fall automatically and alert the right person — without giving anyone a permanent view into the home.

In Switzerland, the BFU reports that more than 1,700 people die from falls each year, 95% of them aged 65+, with nearly 6,500 serious injuries and around CHF 1.8 billion in economic costs.

On a normal day

  • • AI processes locally
  • • A short rolling buffer is overwritten
  • • No image leaves
  • • No one can watch live
  • • No activity history is created
  • • Only a tiny system-health heartbeat leaves

If nothing happens, no image leaves the system.

If a possible fall happens

  • • AI flags an emergency locally
  • • One confirmation image can go to a designated guardian or caregiver
  • • A short pre/post incident clip can stay on the local box
  • • That person decides what to do

A human is brought in only when help may be needed.

We deliberately do less.

Ilonai does not need to know how you spend your day to detect a possible fall.

Other care technology can measure sleep, movement, routines and room activity. Ilonai is being designed around a narrower purpose: detect a possible fall, get help, otherwise leave the person’s life alone.

No live feed
No audio
No face recognition
No sleep or activity reports
No cloud video
No Ilonai staff viewing

Read the privacy promise

Powerful AI. Kept local.

Typical network cameras must run very small models inside the camera, or send imagery to a cloud service. Ilonai uses a dedicated local AI computer, so the detector can use richer context while camera images remain inside the home or building.

This is not “smarter surveillance.” It is more capable visual reasoning with a tighter purpose.

Local AI computer, watercolor illustration

Its own private safety network.

Approved PoE cameras connect to a local AI appliance over a dedicated wired network. An independent cellular connection is intended to carry only system status and emergency alerts.

No camera cloud account. No dependence on household Wi-Fi. No port forwarding.

Core detection is designed to keep running locally even if the external connection is unavailable.

PoE cameras to a private switch, then local AI, then 5G for alert and heartbeat.
PoE cameras → private switch → local AI → 5G/eSIM → alert / heartbeat

A safety system should tell you when it stops working.

Silence should mean “everything is fine,” not “the system stopped working.”

Ilonai is designed to monitor camera availability, valid image delivery, AI-computer health, cellular heartbeat, and extended power loss. If protection is interrupted, guardians or staff should know.

Why Ilonai is different

 Wearable buttonNormal smart cameraIn-camera fall AIIlonai
No action required after a fallNoDependsYesYes
No wearable to charge or rememberNoYesYesYes
No live human surveillanceYesUsually not the designVariesYes, by design
No normal cloud videoYesVariesVariesYes
Dedicated local AI computeNoUsually cloud/vendorLimitedYes
Does not build a daily behavior profileYesVariesVariesYes, by design

“Varies” means products in that category differ. We do not claim every competing product works the same way.

Choose your setting

For someone living at home

Independence without constant checking. Family cannot open a live camera feed. They are brought in only when the system believes help may be needed.

For home

For a care facility

Scale fall detection without scaling surveillance. Standard PoE cameras, shared local AI, event-only visual access.

For care facilities

In development — and we will show the evidence as we earn it.

Ilonai is not installed in homes or facilities today. We are preparing a first real-home pilot. We will publish real-world detection sensitivity, false alerts, latency and uptime once those results exist.

We will not present development targets as clinical results.

Evidence Pilot program

All the detail

Marcell and Ilona

Inspired by Ilona

Ilonai is named after my grandmother, Ilona. She passed out twice last year while on the street, and I realized how much peace of mind could be lost if something like that happened at home, unnoticed. The question wasn’t how to watch her more. It was how to know if she needed help without taking away her privacy.

— Marcell Simon, Founder