I have been working on this even before I was aware of the paper. Feels a bit weird to have something almost identical released. Stay tuned, I guess. I plan to keep working on my version.
Their approach to memory is interesting. I had been considering a tiered command-based approach -- "short-term memory" being an automatic summary of recent sensory inputs/command outputs; "long-term memory" being a detailed database queryable by the agent.
Yes I plan to make it open source.