I built emlearn, a Machine Learning inference engine for microcontrollers and embedded systems. It allows converting traditional ML models to simple and portable C99, following best practices in embedded software (no dynamic allocations etc). https://github.com/emlearn/emlearn At the time of creation, there were not many open source libraries for that niche. Now there are also deep learning frameworks like TensorFlow Lite for microcontrollers, but emlearn is a nice complement because it focuses on the simpler models RandomForest, Gaussian Naive Bayes etc.