Tool flank wear and surface roughness are considered as the most impactful parameters that influence the quality of the workpiece. However, those parameters must be measured directly after the machining process is complete. Therefore, this study proposes an online monitoring application with flank wear and surface quality prediction system to monitor them in real-time. Unlike other monitoring systems widely available in the market, the designed monitoring system was created using open-source software without needing any subscription. Moreover, the prognosis system was built with the combination of multilayer perceptron (MLP) and k-nearest neighbors (kNN) algorithms. The MLP was established to predict the flank wear value, resulting a model with accuracy of 0.982. Furthermore, the result will be normalized and later used to classify the surface quality into three different classes using kNN, resulting in 100% accuracy. Afterward, those algorithms were explicitly implemented into the monitoring application. The system was evaluated in real-time for different machining parameters and can achieve a 88.2% accuracy. This study is expected to improve the possibility of advanced technology implementation, especially in small and medium-sized manufacturing enterprises.