ABSTRACT Spatial stratified heterogeneity (SSH) is a prevalent characteristic of geospatial data, which can be effectively modeled and analyzed using the geographical detector and other models from the SSH family. Various related models have been developed, focusing primarily on spatial data discretization, addressing spatial dependence, and capturing complex spatial interactions. Moreover, models incorporating discrete dependent variables have also emerged. These diverse models significantly enhance the ability to analyze and model SSH. However, the lack of a comprehensive and user‐friendly software tool has greatly limited their broader application in geospatial analysis and environmental modeling. To address this gap, an R package gdverse has been developed to integrate various SSH models, leveraging R's rich statistical and spatial data processing capabilities while natively supporting multicore parallel computing in the widely used R environment. A case study on the determinants of trace element Zn demonstrates the application of the gdverse package, showcasing its effectiveness and convenience.