RecycleRite addresses the pressing issue of e-waste detection by employing a groundbreaking fusion of computer vision and deep learning methodologies. We aim to revolutionize the detection process, mitigating these risks while enhancing efficiency and accuracy. Harnessing efficiency of convolutional neural networks (CNNs) and single-shot detectors (SSDs), the system automates the detection process by analyzing images of electronic devices. Multi-label detection identifies e-waste by both its name and type and optimized single-label multi-class detection, which focuses solely on identifying e-waste by its names. YOLOv8, a state-of-the-art object detection framework, excels in identifying multiple objects within an image, attaining a remarkable mean average precision at 50 (mAP@50) score of 0.97. For name-based single label detection, RTDETR, emerges as the top performer with an impressive mAP@50 score of 0.96. These methodologies not only accurately classify e-waste items but also streamline the detection process, thereby promoting sustainable waste management practices and environmental conservation.