Signals can be interpreted as composed of a rapidly varying component modulated by a slower varying envelope. Identifying this envelope is an essential operation in signal processing, with applications in areas ranging from seismology to medicine. Conventional envelope detection approaches based on classic methods tend to lack generality, however, and need to be tailored to each specific application in order to yield reasonable results. Taking inspiration from geometric concepts, most notably the theory of alpha-shapes, we introduce a general-purpose library to efficiently extract the envelope of arbitrary signals.