Factorsynth (current version: 2.3) is a Max For Live device that uses machine learning techniques to decompose any input sound into a set of temporal and spectral elements. By rearranging and modifying these elements you can do powerful transformations to your clips, such as removing notes or motifs, creating new ones, randomizing melodies or timbres, changing rhythmic patterns, remixing loops in real time, creating complex sound textures...
The free demo version showcases the decomposition capabilities of the Factorsynth engine. For a feature comparison between the full and demo versions, see https://www.jjburred.com/software/factorsynth/index.html#versions
Ableton Live 9 (64 bit), 10 or 11
Max For Live 7.3 or newer
Mac OS or Windows