The term runtime logic verification defines a field that ranges from software verification for compliance with a set of specifications to assuring the adoption of good coding practices. Under this scope, we created lovpy, a novel metaprogramming library for python, that introduces to its ecosystem the capabilities of runtime logic verification. Definition of expected behavior is performed using the intuitive specifications language Gherkin, while using the library requires no code modifications. For its implementation we utilized a broad set of tools, ranging from the domains of graph theory, formal languages theory and temporal logic to deep learning, with specific focus on graph neural networks. We also, provided the mathematical foundation for a new type of graph, designed for representing temporal specifications. Based on it, we defined a set of mathematically proved logic algorithms. Then, we used these structures for implementing a novel theorem proving system, located at the heart of lovpy and ensuring the absolute validity of reported violations. We evaluated five different proving architectures, consisting from heuristics and simple neural models, to deep graph neural networks. For the training of neural systems, we implemented a mechanism for generating synthetic theorems, utilizing a series of mathematical properties. Finally, we used lovpy for detecting bugs in two popular open-source libraries, Django and Keras.