Bagapit Chess (Catur Bagapit) is a traditional strategy board game originating from the Kalimantan region of Indonesia. Despite its rich cultural heritage and strategic depth comparable to international Chess, Bagapit Chess remains largely unstudied from a computational intelligence perspective. This paper presents the development of an Artificial Intelligence (AI) model for the Bagapit Chess engine using the Random Forest Regressor (RFR) algorithm. The AI model is trained to evaluate board positions and generate competitive move decisions through a heuristic evaluation function augmented by machine learning. A dataset of 15,000 annotated game positions was constructed from expert gameplay, encoding board features including piece Material Advantage, Chess Movement, Defense Stance, mobility, and Attack Coverage across the 8×8 Bagapit board. The Random Forest Regressor model was integrated with a Negamax search tree enhanced by Alpha-Beta Pruning to achieve efficient and intelligent move selection. The trained model achieved an R² score of 0.9134, a Mean Absolute Error (MAE) of 0.0872, and a Root Mean Squared Error (RMSE) of 0.1104 on the test set. In engine evaluation against a rule-based baseline, the AI model won 84.2% of games under standard time control. This study contributes to the digitalization and preservation of Indonesian traditional games and demonstrates the applicability of ensemble machine learning to non-standard board game engines.