Li-ion or lithium-ion batteries are essential for charging electric-powered automobiles, supplying power to electronic gadgets, and supporting the storage of energy generated from renewable sources. It is critical to correctly determine the batteries’ SOH and RUL. This research explored and assessed the use of NeuralProphet model in terms of RMSE and MAE about predicting the battery's SOH and calculates its RUL, enabling effective use and maintenance. The experiment was carried out in Heroku using Flask. Heroku is a Platform-as-a-Service (PaaS) tool by Salesforce. The evaluation involved assessing the NeuralProphet model’s performance through metrics such as RMSE and MAE. The results show that NeuralProphet delivered strong prediction accuracy for SOH with RMSE values of 0.006269 for B0005, 0.011711 for B0006, 0.005539 for B0007, and 0.011775 for B0018. It also proved to be robust in estimating the RUL of lithium-ion batteries across different units. The model allows real-time monitoring, enabling timely maintenance and replacement decisions, enhancing efficiency, and reducing costs. This research contributed to battery management by introducing a novel approach for predicting SOH and estimating the RUL of lithium-ion batteries. NeuralProphet provides a reliable solution for augmenting battery performance and encompassing its lifespan in various applications, supporting a sustainable future.