Myrrix is a complete, real-time, scalable recommender system, evolved from Apache Mahout. Just as we take for granted easy access to powerful, economical storage and computing today, Myrrix will let you take for granted easy access to large-scale learning from data.
It can ingest new information, compute recommendations, similar items and more in real-time, via a REST API exposed by Serving Layer instances. At the same time, it can leverage Hadoop to efficiently refine recommender models in the background.
Myrrix runs on any platform, can use clusters from most Hadoop distributions, and is specially designed to use Amazon EC2 and EMR for instant deployment if desired.
A "miniature" stand-alone version, which is limited to one machine and does not require Hadoop, is provided as a free and open source download.
To access the API from the complete system now, create an instance now on Amazon:
Or, download or run the stand-alone system for a simpler, smaller trial: