At present, the development of smart agriculture in facility cultivation focuses heavily on environmental data monitoring and collection, yet lacks downstream value-added applications. Furthermore, foreign-developed crop models often struggle to be directly applied to domestic conventional greenhouse cultivation due to variations in cultivation practices and crop cultivars. Based on the classic TOMGRO model, this technology incorporates multi-year cumulative growth and environmental parameters of indeterminate large-fruit tomatoes from the Taiwan Agricultural Research Institute (TARI) for equation calibration, with its accuracy thoroughly validated across multiple years, greenhouse environments, and varieties. Developed in Python, this program allows users to simply input the temperature and light intensity data of the simulation period in a standardized format to accurately simulate the tomato's daily number of main stem nodes, leaf area index (LAI), fruit load, and yield. By transforming environmental data into a highly flexible digital decision-making tool for cultivation management, this program delivers substantial practical value to the agricultural industry.