Querying and linking distributed and heterogeneous databases is increasingly needed, as plentiful data resources are published over the Web. This work describes the design of a versatile query system named KGRAM that supports (i) multiple query languages among which the SPARQL 1.1 standard, (ii) federation of multiple heterogeneous and distributed data sources, and (iii) adaptability to various data manipulation use cases. KGRAM provides abstractions for both the query language and the data model, thus delivering unifying reasoning mechanisms. It is implemented as a modular software suite to ease architecting and deploying dedicated data manipulation platforms. Its design integrates optimization concerns to deliver high query performance. Both KGRAM's software versatility and performance are evaluated.