AbstractBayesPy is an open-source Python software package for performing variational Bayesianinference. It is based on the variational message passing framework and supports conjugateexponential family models. By removing the tedious task of implementing the variationalBayesian update equations, the user can construct models faster and in a less error-proneway. Simple syntax, flexible model construction and efficient inference make BayesPysuitable for both average and expert Bayesian users. It also supports some advancedmethods such as stochastic and collapsed variational inference.Keywords: variational Bayes, probabilistic programming, Python