well, trivially - really. Machines can communicate via TCP and UDP, pretty much the same way you communicate with a web server - but more efficiently (than http). There are tons of protocols/frameworks for replicated and distributed maps which are significantly more effective than redis, esp when hitting the local one.
Writing one such yourself, is sort of, rite of passage.
While redis is well understood and (relatively) easy to use - it's just a TCP offloaded map (and few other datastructures), all well implemented and with non-blocking IO but nothing groundbreaking. Heck, it's even single threaded by design - no vertical scaling, and no L3 cache communication.
