In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance. Existing approaches often struggle to capture and represent the essential characteristics of evolving visual concepts, hindering their applicability to dynamic graphics tasks. In this paper, we propose Ancestral Mamba, a novel approach that integrates online prototype learning into a selective discriminant space model for efficient and robust online continual learning. The key components of our approach include Ancestral Prototype Adaptation (AP A), which continuously refines and builds upon learned visual prototypes, and Mamba Feedback (MF), which provides targeted feedback to adapt to challenging visual patterns. AP A enables the model to continuously adapt its prototypes, building upon ancestral knowledge to tackle new challenges, while MF acts as a targeted feedback mechanism, focusing on challenging classes and refining their representations. Extensive experiments on graphics-oriented datasets, such as CIF AR-10 and CIF AR-100, demonstrate the superior performance of Ancestral Mamba compared to state-of-the-art baselines, achieving significant improvements in accuracy and forgetting mitigation. 1. Introduction Online continual learning (OCL) aims to learn continuously from a non-stationary data stream while adapting to new data and mitigating catastrophic forgetting [1, 11, 17, 21]. Recently, online prototype Learning (OnPro) [22] has attracted a lot of attention with its brilliant performance in the OCL field. This paradigm holds immense potential for real-world applications, particularly in the realm of computer graphics, where the ability to process and adapt to evolving visual patterns, shapes, and colours is of paramount importance. Catastrophic forgetting [7, 22, 23, 25] stands as a major hurdle in online continual learning, akin to a visual artist abruptly losing previously acquired skills when adapting to new styles.