Generally, in many households, offices, and private spaces it is common to have an aquarium. However, a major problem occurs when dealing with monitoring and feeding of fish in the absence of an aquarium caretaker. There are many automatic fish feeder devices that can be used by setting up it with specific instructions. These devices are not operated remotely. There is no specific mobile application for both water quality checking and feature of fish feeding. The research presents an innovative approach to the development of an automatic fish feeder system integrated with a mobile application. Taking data from temperature and turbidity sensors, the system uses advanced machine learning techniques, specifically Long Short-Term Memory (LSTM) networks, to analyze environmental conditions and adapt feeding schedules accordingly. This system allows users to schedule feeding sessions, adjust portion sizes, and ensure the well-being of their aquatic pets. Thus, this project brings up a modernistic approach by connecting fish feeders with IoT devices and mobile applications.