A few AI researchers have created, and recently published, a "Neural MMO" exclusively designed for reinforcement learning agents. The MMO's structure is loosely based on Runescape, which seemingly inspired the project, and the code itself contains numerous references to the Jagex game. However, the client and server are standalone pieces of software, and can be installed with a few commands on Linux (or Windows with the WSL feature enabled). The researchers claim the environment is complex and open-ended enough to effectively train large populations of AI agents, and that it contains many features you'd expect to find in regular MMOs designed for human meatbags, as well as a framework for future upgrades. Check out a video of the AI MMO here. This environment is the first neural MMO; it attempts to create agents that scale to real world complexity. Simulating evolution on Earth is computationally infeasible, but we can construct a reasonable and efficient facsimile. We consider MMORPGs (Massive Multiplayer Online Role Playing Games) the best proxy for the real world among human games: they are complete macrocosms featuring thousands of agents per persistent world, diverse skilling systems, global economies, and ad-hoc high stakes single and team based conflict... There is almost certainly still a complexity gap from MMOs to the real world, but we believe it is much smaller than that in environments currently available. While our environment is nowhere near the level of complexity of a real MMO yet, it does contain key properties of persistence, population scale, and open-endedness. As agents begin to reach the ceiling of the current environment, we plan on continuing development to raise the ceiling.