StarSpace is a library for efficient learning of entity representations from relations among collections of discrete entities. In the general case, it embeds objects of different types into a vectorial embedding space, hence the star ('*') and space in the name, and in that space compares them against each other. It learns to rank a set of entities/documents or objects given a query entity/document or object, which is not necessarily the same type as the items in the set. StarSpace builds on modern Mac OS and Linux distributions. Since it uses C 11 features, it requires a compiler with good C 11 support.