This paper is a summary of the work published at the CIKM 2022 conference, Cugny et al. (2022). A large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed in recent years. Recently, thanks to new XAI evaluation methods, it has become possible to compare them. However, selecting the most relevant XAI solution remains a tedious task, especially if the user has specific needs and constraints. In this paper, we propose to introduce AutoXAI, a framework that recommends the best XAI solution and its hyperpa-rameters while taking into account the user's context (dataset, learning model, XAI needs and constraints). Our approach draws on work related to the field of context-based recommender systems as well as AutoML (Automated Machine Learning) for our optimization and evaluation strategies. In this summary paper, we illustrate our approach through a use case showing that AutoXAI recommends the most suitable solution (with the best hyperparameters) to the user's needs and constraints.