A MapReduce-based framework for processing data at edges, includingnodes on the Internet of Things (IoT), is presented in this paper. Although MapReduce processing and its clones have been designed forhigh-performance server clusters, the processing itself is simple andgeneralized, so it should be used in non-high-performance computingenvironments, e.g., IoT and sensor networks. The proposed frameworkdeploys programs for data processing at the nodes that contain thetarget data as a map step and executes the programs with the localdata. Finally, it aggregates the results of the programs to certainnodes as a reduce step. The architecture of the framework, its basicperformance, and its application are also described here.