The LINCS (Learn and Infer Non Compensatory Sortings) library is a software tool making available to a wide community of users a range of techniques for learning non-compensatory sorting models from training data and providing robust, interpretable classifications. In particular, the aim is to make the LOGIMICS team's methodological and computational contributions to the field of algorithmic decision theory accessible to as many people as possible, concerning a class of preference models that is remarkable from the point of view of ease of appropriation by users, but arduous from the point of view of learning.