We developed a website which predicts the energy consumption for various buildings at UConn. We have trained a machine learning model on historical data from Energy Stats, a website which is maintained by UConn's Facilities Operations. Our website allows users to select a building, time range, and energy type and then displays the forecasted energy usage from our model. The model is trained on data from multiple energy types; electricity, steam, and chilled water. We also incorporated weather conditions in training the model to improve the prediction accuracy and generate more dynamic forecasts. The goal of this website is to provide insights into building energy patterns and help to identify trends, anomalies, and opportunities for improved energy efficiency. By combining data analysis and predictive modeling, our website can be used as a tool to support better informed decision-making for energy management and sustainability on campus.