Stroke is one of the leading diseases of the ageing world population where about half of the stroke survivors are left with some degree of physical or cognitive impairment. Impairment of walking is mentioned most frequently as the most important disability. Furthermore, reduced locomotor mobility worsens metabolic fitness, which is one of the leading factors of morbidity in these patients, and imposes an enormous economic burden. Therefore, innovative methodologies for stroke neurorehabilitation are required to reduce long-term disability by physiologically-relevant and evidencebased treatments. With regard to motor rehabilitation, neuroplasticity, which is the ability of the nervous system to respond to intrinsic or extrinsic stimuli by reorganizing its structure, function and connections is of utmost importance for re-gaining functions. Post-stroke neuroplasticity can be facilitated with non-invasive multi-level electrotherapy such as neuromuscular electrical stimulation (NMES) and noninvasive brain stimulation (NIBS), thus improving restitution of locomotor function and alleviating the burden of stroke. In this connection, the translation of insights gained from animal and human basic studies to address the complexity of rational multi-level electrotherapy protocols and to customize such novel electrotherapy protocols, which has only recently become possible with advanced computational tools, is an important challenge. Advanced computational modeling to design and customize innovative electrotherapy protocols to patientspecific needs might help to reach this aim. Here, we provide an overview of the computational methods available to drive individualized multi-level non-invasive electrotherapy programs for gait therapy following stroke based on rationale insights gained from neurophysiological studies.