This is a really interesting direction. RTS games are a much better testbed for agent capability than most static benchmarks because they combine partial observability, long-term planning, resource management, and real-time adaptation.
It reminds me a bit of OpenAI Five — not just because it played a complex game, but because the real value wasn’t “AI plays Dota,” it was observing how coordination, strategy formation, and adaptation emerged under competitive pressure. A controlled RTS environment like this feels like a lightweight, reproducible version of that idea.
What I especially like here is that it lowers the barrier for experimentation. If researchers and hobbyists can plug different models into the same competitive sandbox, we might start seeing meaningful AI-vs-AI evaluations beyond static leaderboards. Competitive dynamics often expose weaknesses much faster than isolated benchmarks do.
Curious whether you’re planning to support self-play training loops or if the focus is primarily on inference-time agents?
Android is code-only "open source" but not actually open since if you make an app and put it in apk it automatically makes the file look dangerous making developers pay for Google Play store
I like that this is targeting forgotten games with low player counts (since im new and not famous)
Have you considered gamifying session creation (e.g., showing estimated wait times or crowd-sourced player counts) to make join-up easier?
And I also like your 98.css style!