Personal information agents emerged in the last decade as an alternative to assist users to cope with the increasing volume of information available on the Web. In order to provide personalized assistance, these agents rely on user profiles modeling user information preferences, interests and habits. Inserted in communities of people with similar interests, personal agents can improve their assistance by gathering knowledge extracted from the observed common behaviors of single users. In this paper we propose an agent-based recommender system for supporting collaborative Web search in groups of users with partial similarity of interests. Empirical evaluation demonstrates that the interaction among personal agents increases the performance of the overall recommender system.