Wearable devices are becoming a cornerstone for personalized and long-term health monitoring, enabling early intervention and data-driven medical decisions. In this work, we present e-Glass , a state-of-the-art smart wearable device that enables unobtrusive real-time electroencephalography (EEG) monitoring. Our evaluation shows that e-Glass adheres to the established international guidelines for clinical EEG recordings. Moreover, the acquired data presents a Pearson’s correlation of 0.93 relative to recordings obtained from the Biopac research-grade EEG system . The proposed EEG acquisition device concept is evaluated in two application domains: epileptic seizure detection and cognitive workload monitoring (CWM). First, we present a lightweight edge machine-learning scheme, designed specifically for e-Glass , achieving overall sensitivity of 64% (100% sensitivity in 11 out of 24 subjects) and 2.35 false-alarms per day, when tested on 982.9 hours of EEG data from the CHB-MIT dataset. Similarly, an CWM strategy with e-Glass reaches an accuracy of 74.5% on unseen data. These results demonstrate that e-Glass is capable of unobtrusive and real-time subject monitoring in outpatient conditions, not only in epileptic seizure detection but also in monitoring the subject’s cognitive state.