The efficacy of standard rehabilitation for improving upper limb functionality after stroke is limited; thus, alternative strategies are needed. Vagus nerve stimulation (VNS) combined with rehabilitation is a promising approach, but the invasiveness of this technique reduces its clinical application. Recently, a non-invasive technique for stimulating vagus nerve has been developed. Aim of this study is to evaluate safety, feasibility, and efficacy of noninvasive VNS combined with robotic rehabilitation for improving upper limb functionality in chronic stroke. We designed a proof-of-principle, double-blind, semi-randomized, sham-controlled trial. Fourteen patients with either ischemic or haemorrhagic chronic stroke were randomized to robot-assisted therapy associated with real or sham VNS, delivered for 10 consecutive working days. Efficacy was evaluated by change in upper extremity Fugl-Meyer score. After intervention, there were no adverse events and Fugl-Meyer scores were significantly better in the real group compared to the sham group. Our pilot study confirms that VNS is feasible in chronic stroke patients and can produce a slight clinical improvement in association to robotic rehabilitation. Compared to traditional stimulation, noninvasive VNS seems to be safer and more tolerable. Further studies are needed to confirm the efficacy of this innovative approach.