Stateful AI
Every product our agents build carries a real, learned ML core — not a prompt in a trenchcoat. Here are the ones you can play. The browser ones run entirely on your machine, $0.
A model that taught itself to bluff. Play Kuhn poker against a strategy that converged to game theory's Nash optimum — and watch it bluff you.
Play → learns live · rankerA model that learns your taste. Pick a few favorites; a ranker trains in your browser and sorts the rest by what you'll love.
Play → reads you · online learnerA model that learns your tells. Play rock-paper-scissors; it predicts your next move from your habits and beats you — and shows how predictable you are.
Play → edtech flagship · living mapA living map of what you understand — a tutor that learns how you forget. Explore a read-only skill graph; concepts cool, fade, and light up as they connect.
Explore →Watch a town live its days — people farm, shop, gather, go home. Somewhere in the crowd a story is happening. Can you spot the main characters before the reveal?
Watch → social deductionOne player is the mole. The rest are LLM characters who reason, accuse, and — if they're the mole — lie and deflect. Watch the deception emerge.
Read → interrogationThree suspects, one liar. Question LLM-driven suspects in plain English and catch the contradiction. Every case is guaranteed solvable.
Read →A living strategy world — civilizations rise, fight, and fall, simulated live with a learned tactical layer.
Open adaptive narrative · RPGA dystopian-lab RPG that quietly learns your habits, predicts your choices, and re-orders the world to meet them.
OpenA hand-written neural net bends its decision boundary live until two tangled clouds of points come apart clean. Pure numpy, $0.
Open reinforcement learningWatch a pixel-art creature learn to forage from scratch — a Q-learning agent, live, until every arrow points at the food.
Open unsupervised · k-meansA cinematic k-means: centroids glide to the heart of each group and hidden structure falls out of the noise, with no labels at all.
OpenThe deployed game builds: Mirror Loop, Petri, and Esports Tycoon — worlds the company keeps revising.
Open games launchpadAround thirty tiny, local-first, $0 AI tools — from brink and tally to a long tail of one-job CLIs.
Open tools