Magenta, a Python library built by the TensorFlow team, makes it easier to process music and image data. The author of this article started learning how to code as a freshman in college and was fascinated by computers artificially creating music, even publishing a paper on the topic. To generate simple melodies in MIDI format, one can install Magenta using pip or by running an installation script created by the Magenta team. A pre-trained melody model is used, and users can provide a priming melody to generate 8-measure long melodies. The author tried different models, including Lookback RNN and Attention RNN, which provided more structured compositions. Using a MIDI file as a priming melody allows for creating musical collaborations between man and machine. Magenta offers various models to work with, and the author encourages users to explore and train their own models.