Researchers at the University of Ottawa have developed UbiMyTherapist, an artificial intelligence system designed to proactively detect emotional distress and deliver personalized mental health support via consumer-grade smartwatches, smartphones, and earbuds. Led by Dr. Karim Alghoul, part-time professor in the School of Electrical Engineering and Computer Science, the work was presented in the paper "UbiMyTherapist: A Digital Twin MultiModal LLM-based System with Emotion Detection" at the 2026 IEEE International Conference on Consumer Electronics. The system distinguishes itself from standard interactive chatbots by functioning as a proactive digital therapy assistant. It continuously monitors physiological and behavioral indicators, including heart rate variability, speech tone, and text input, to assess a user's emotional state in real time. To generate contextually appropriate responses, UbiMyTherapist maintains a dynamic digital twin profile for each user. This profile synthesizes medical history, a comprehensive clinical psychology knowledge base, and live affective data, allowing the model to tailor interventions based on both the user's personal context and immediate psychological condition. Evaluation of the prototype involved testing with volunteers and licensed psychotherapists. Results indicated that UbiMyTherapist achieved higher scores in empathy and personalization compared to commercial large language models, validating the efficacy of integrating real-time emotional context into therapeutic AI. The research aims to mitigate barriers to mental health care, such as cost, stigma, and availability, by providing accessible support outside clinical settings. Rather than replacing professionals, the system is intended to extend the reach of care and assist therapists with patient insights. Future iterations will focus on deploying live proactive interventions triggered by biosignals and expanding collaboration with mental health practitioners. The project was supervised by Dr. Hussein Al Osman and Dr. Abdulmotaleb El Saddik from the Faculty of Engineering, with support from psychology student Raina Sharma.