: In this paper, we present an agent-based approach for the improvement of searching in an ontology-based knowledge management system. The system implements a libraryscenario in which users querythe repository for knowledge resources. Consequently, the so-called Librarian Agent plays the role of the human librarian in the traditional library – it uses all possible information, about the domain vocabulary, the behaviour of previous users and the capacity of the knowledge repository, in order to help users find the resources they are interested in. We partially implemented the approach in the Web Portal of our Institute and some initial evaluation results are shown.