Delineation of agricultural management zones (MZs) is the delimitation, within a field, of a number of sub-areas with high internal similarity in the topographic, soil and/or crop characteristics. This approach can contribute significantly to enable precision agriculture (PA) benefits for a larger number of producers, mainly due to the possibility of reducing costs related to the field management. Two fundamental tasks for the delineation of MZs are the variable selection and the cluster analysis. There are several methods proposed to execute them, but due to their complexity, they need to be run by computer systems. In this context, the objective of this paper is to present two computational modules developed to enable an efficient execution of these tasks. The variable selection module provides 5 algorithms, based on spatial correlation analysis of crop and field variables, principal component analysis (PCA), and multivariate spatial analysis based on Moran’s index and PCA (MULTISPATI-PCA). The data clustering module provides 17 clustering algorithms: average linkage, bagged clustering, centroid linkage, clustering large applications, complete linkage, fuzzy analysis clustering, fuzzy c-means, hard competitive learning, hybrid hierarchical clustering, k-means, McQuitty’s method, median linkage, neural gas, partitioning around medoids, spherical k-means, unsupervised fuzzy competitive learning, and Ward’s method. The algorithms were programmed in R statistical software routines, with the main objective of guaranteeing flexibility and speed in execution. This software was tested for the delineation of management zones for several agricultural fields. However, to exemplify its use in this paper, we consider data obtained from 2012 to 2015 in an agricultural area in the municipality of Céu Azul, Brazil, where soybean crop was cultivated. The computational modules developed proved to be adequate and efficient to define MZs. In addition, they are more comprehensive than other free-to-use software in terms of the diversity of variable selection and data clustering methods.