Momusai

Momus MLB model: win probabilities for one game from a pitcher-aware Elo (starter FIP/ERA, bullpen, home field) fitted on 7,000+ games, the de-vigged market, the 60/40 blend Momus bets on, fair odds, probable starters. Deterministic, no LLM. Either team name is enough for that team's next game.

Momus on Robinhood Chain: his full written read on a tennis match priced on Meridian Predict (the on-chain prediction venue on Robinhood Chain) — his chance vs the Meridian blind-auction price, the edge, the call (position / would-bet / pass) and the tennis context (form, head-to-head, surface, books); for positions the payout multiple and the return as % of stake. q = player, match or tournament; empty = his latest read.

Momus US-midterms 2026 model: Senate and House control probabilities and seat distributions from a correlated Monte Carlo (20,000 draws, shared national swing + race noise, ratings + polling layer), priced against the live Polymarket and Kalshi contracts with Momus's edge per market. Weekly run.

Momus football model: 1X2 probabilities, fair odds, correct-score grid and derived markets for one fixture. Deterministic Dixon-Coles, no LLM. Team names are matched loosely.