BackgroundSleep dysfunction is disabling in people with Parkinson’s disease and is linked to worse motor and non-motor outcomes. Sleep-specific adaptive Deep Brain Stimulation has the potential to target pathophysiologies of sleep. ObjectiveDevelop an adaptive Deep Brain Stimulation algorithm that modulates stimulation parameters in response to intracranially classified sleep stages. MethodsWe performed at-home, multi-night intracranial electrocorticography and polysomnogram recordings to train personalized linear classifiers for discriminating the N3 NREM sleep stage. Classifiers were embedded into investigational Deep Brain Stimulators for N3 specific adaptive DBS. ResultsWe report high specificity of embedded, autonomous, intracranial electrocorticography N3 sleep stage classification across two participants and provide proof-of-principle of successful sleep stage specific adaptive Deep Brain Stimulation. ConclusionMulti-night cortico-basal recordings and sleep specific adaptive Deep Brain Stimulation provide an experimental framework to investigate sleep pathophysiology and mechanistic interactions with stimulation, towards the development of therapeutic neurostimulation paradigms directly targeting sleep dysfunction.