Docs
Combo blends three families of automated decision making into one configuration surface: a constraint programming solver to keep choices feasible, bandit optimization for online traffic where every request is a draw, and Bayesian optimization for offline sweeps where each trial is expensive. The constraint side comes from klause, the optimization and streaming statistics come from kumulant, and combo wires them together.
combo
Kotlin + K8s tool for improving LLM prompts and UIs through live user feedback.
★ 6Built on
klause
Kotlin solver for Boolean and integer constraint problems. Finds and samples satisfying solutions, picks the best under a weighted objective, and exports to CNF for external SAT engines.
★ 7kumulant
Streaming ML for Kotlin/KMP: online regression, bandits, sketches, calibration, and statistics.
0.3.0 · ★ 11