Expert locators and repository-based knowledge management systems (KMS) are different architectures proposed to perform different kinds of knowledge management functions. While expert locators can recommend an expert to perform a task, repository- based KMS can share a learned strategy to solve a given problem. In this paper, we describe a framework to develop KMS that can perform multifunctional tasks, usually performed by repository-based and expert locators separately, in one single architecture. The proposed framework follows principles from knowledge engineering and from the management literature on how to prevent failure in KMS. We illustrate the proposed framework with an implementation to support a community of science.