IoT · AI · Pet RecognitionamiSense
Know every pet by name — no tags, no collars, just AI.
An AI-powered IoT platform that visually identifies each of your pets with no collars, no microchips, no physical tags — and automatically takes personalized action for each one. Trained on your animals, running on a compact smart camera, managed from your phone.
One feeder. Three pets. Three very different needs.
Managing multiple pets individually is hard. Scheduled feeders don't know which pet showed up. Microchip feeders require expensive hardware on every animal. Cameras record everything but tell you nothing.
amiSense was born from a real problem: three cats with completely different dietary needs, all sharing the same space. The solution wasn't more collars or more chips — it was smarter software that sees the difference.
Activity Feed
Today's detections
Luna
Feeder opened
97%
2s ago
Mochi
Feeder opened
93%
4m ago
Shadow
Logged detection
89%
12m ago
Luna
Feeder opened
96%
1h ago
47
Detections
93%
Avg Conf.
3
Pets
Train it once. Let it work forever.
Train your model
Record short videos of each pet using the amiSense mobile app. Upload them to the cloud. Our AI training pipeline (EfficientNetV2B0 on Google Cloud) builds a personalized recognition model trained on your lighting, your environment, your animals.
Install the smart camera
The amiSense Smart Camera (ESP32-CAM) connects to your WiFi via Bluetooth provisioning from the mobile app. No complicated setup — point it at the feeding area and it starts streaming to our edge AI processor.
Automate any action
Define what happens when each pet is detected. Open the feeder for exactly 3 seconds. Log a recognition event. Trigger a GPIO output. Schedule actions by day and time. The system decides, the camera executes — you just watch the activity feed.
Everything you need. Nothing you don't.
Per-Pet AI Recognition
Trained on your pets, in your home
Powered by EfficientNetV2B0, amiSense builds a personalized recognition model exclusively for your animals. It learns your pets' appearance in your specific lighting and environment — not a generic model that guesses from a database.
- EfficientNetV2B0 — state-of-the-art lightweight deep learning
- Trained on your environment, not a generic dataset
- Background class suppresses false-positive detections
- "Wrong pet?" tap triggers automatic model retraining
- 2-phase transfer learning: frozen base → fine-tune
- >90% validation accuracy per trained model
Built, tested, and heading to alpha.
All five components — backend, mobile, training, edge processor, and device firmware — have completed Phase 2 development.
Auth, devices, pets, activity feed, live streaming, BLE provisioning
AI training pipeline, catalog actions, scheduling, corrections feedback loop, push notifications
Alpha release, onboarding improvements, multi-device enhancements, public availability
Built on proven infrastructure
Ready to know your pets like never before?
Join the waitlist for early access. Be among the first to experience tag-free, AI-powered pet recognition in your home.
No spam. We'll only reach out when early access opens.