nanoedge ai studio

NanoEdge AI Studio - Automated Machine Learning tool for STM32 developers

nanoedge ai studio

With NanoEdge AI Studio, find the best AI library for your embedded project, and start incorporating machine learning capabilities into the C code in your MCU, regardless of your level of expertise in AI!

NanoEdge* AI Studio embeds an automatic search engine for AI libraries that enables developers to generate an optimal ML library for their project in a few steps, based on a minimal amount of data. Once created, the library is loaded into the microcontroller to train and infer directly at the edge for improved security and reduced latency.

With NanoEdge AI Studio, ST makes AI more accessible: software developers can now create optimal ML libraries from the tool’s user-friendly environment, without needing specific data science skills or expertise in Artificial Intelligence (AI).

NanoEdge AI Studio can generate very small footprint libraries for all the STM32 portfolio, including the smallest Arm® Cortex®-M0-based microcontrollers.

*is a registered and/or unregistered trademark of STMicroelectronics International NV or its affiliates in the EU and/or elsewhere

video nanoedge ai studio

Key features of 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 down to the smallest Arm® Cortex®-M0 microcontrollers
  • PC-based, push-button development studio for developers, which runs on Windows® or Linux® Ubuntu®

What's new in the release of NanoEdge AI Studio V3:

  • New, more user-friendly interface.
  • Improved support for anomaly detection, particularly useful for predictive maintenance applications to anticipate wear and tear phenomena or to better deal with equipment obsolescence.
  • Added regression algorithms to extrapolate data and predict future data patterns for energy management or to forecast remaining equipment life.
  • New high-speed data acquisition and management on the STWIN development board allow users to easily manage all industrial-grade sensors without having to write a single line of code.

Application examples

anomaly detection Anomaly detection
predictive maintenance Predictive maintenance
Condition monitoring
asset tracking Asset tracking
people counting People counting
activity recognition Activity recognition

How to test & prototype with NanoEdge AI Studio

Choose a development kit to start testing the capabilities and features of NanoEdge AI Studio:

steval stwinkt1b wireless industrial node reference design


STWIN SensorTile Wireless Industrial Node development kit and reference design for industrial IoT applications.

Jump-start the implementation and development for sensor-monitoring-based applications with FP-AI-MONITOR1 software package which covers the entire design of the Machine Learning cycle from the data set acquisition to the integration on this industrial-grade sensors and ultra-low-power physical node.


Discovery kit with STM32L562QE MCU and sensors.

The FP-AI-NANOEDG1 software example simplifies the implementation of condition monitoring applications powered by NanoEdge AI Studio libraries.