We introduce a tool able to automatically extract the timing of gait events during unconstrained locomotion across neuromotor disorders. Our approach relies only on inertial sensors placed on the feet, and has been validated on people with normal and pathological kinematic patterns. The algorithm achieved an average accuracy of 99.23% when tested on healthy participants, either with average weight or overweight , and a performance of 94.84% when evaluated on patients with Parkinson’s disease. G.A.I.T. is conceived as an assistant for gait assessment studies, both in healthy participants or in people with neuromotor impairments affecting gait symmetry, regularity, or balance, as usually encountered in patients with Neurological disorders.