Easily generate optimized ML libraries
for STM32 and smart sensors
Book a demo!
NanoEdge* AI Studio embeds an automatic search engine for AI libraries, which enables developers to generate an  optimal ML library for their project  in a few steps, based on a  minimal amount of data.
Once you have created the library, you can easily load it into the microcontroller  to train and infer directly at the edge for improved  security and reduced  latency.
contextual signals
from your application
Create an
anomaly detection ML
library for STM32
Deploy on STM32 and
Learn directly on the
* is a registered and/or unregistered trademark of STMicroelectronics International NV or its affiliates in the EU and/or elsewhere
A proven solution
Schneider electric
“Using Machine Learning libraries developed with Cartesiam’s NanoEdge AI Studio, we were able to anticipate behaviors that were previously difficult to detect.”
Lacroix electronics
“We have used Cartesiam’s NanoEdge AI Studio to develop a very promising preventive maintenance solution on our production sites.”
“Within a couple of weeks after we bought NanoEdge AI Studio, we launched « Wales », a water leakage detector with embedded Edge AI technology from Cartesiam.”
Discover more about NanoEdge AI Studio
  • Generate Machine learning libraries for event detection, classification, or regression
  • Explore millions of possible algorithms to find the right library for you in terms of accuracy, confidence, inference time, and memory footprint
  • Generate very small footprint libraries running on the smallest Arm® Cortex®-M0 microcontrollers
  • PC-based, push-button development studio for developers, which runs on Windows® or Linux® Ubuntu®
  • New support for sensors featuring an ISPU (intelligent sensor processing unit) with on-device learning capabilities.
Tell us more about your design challenges.
We’ll show you how NanoEdge AI Studio can help you overcome them.