CodeReady is two people. We met writing bots for a puzzle game ladder and stayed for the arguing about whether a greedy strategy counts as cheating.
The idea is simple. Reinforcement learning tutorials all use the same three environments, and none of them are fun to watch. So we built six small games that are quick to simulate, easy to score, and awkward enough that a naive strategy plateaus fast.
Your function gets a game state and returns a move. We run it a few thousand times, score it, and hand back the log. No GPU, no setup, no framework to learn. If you can write an if statement you can put a bot on the ladder.
Runs and strategies have to save somewhere. That is the whole reason. We do not ask for a name, an address or a card, because there is nothing to charge you for.
We do not sell player data. We do not run advertising trackers. We do not put a paywall in front of a ground we already released free.
Credits are points that buy longer runs. They cannot be bought, cannot be cashed out, and have no value outside the site. If that ever changes we will say so here first.