The purpose of this paper is to formulate a functional architecture that supports the e-learning objectives: study individually and cooperatively, anytime and anywhere, guide specific individuals to their most relevant community or communities of knowledge. The proposed architecture is based on using mobile agent technology integrated with Case-Based Reasoning (CBR) approach. This architecture gives users the ability to collect, share, distribute and reuse e-learning knowledge from heterogenous knowledge bases. The mobile agent technology is particularly suitable for developing distributed e-learning systems because it supports intelligent and distributed storage, allows an optimal personalized e-learning environment, and enhances modularity, reusability, flexibility and reliability. The model is employing CBR method to find a case in case base that is similar to the current problem.