HSIMamba is a novel framework designed for hyperspectral image (HSI) classification, leveraging bidirectional state space modules to efficiently extract spectral features. The model combines the operational efficiency of convolutional neural networks (CNNs) with the dynamic feature extraction capabilities of attention mechanisms found in Transformers, while avoiding the high computational demands associated with Transformers. HSIMamba processes data bidirectionally, enhancing spectral feature extraction and integrating it with spatial information for comprehensive analysis. This approach improves classification accuracy and addresses computational inefficiencies, making it suitable for contexts with limited computational resources. The model was tested on three widely recognized datasets—Houston 2013, Indian Pines, and Pavia University—and demonstrated superior performance compared to existing state-of-the-art models. HSIMamba redefines the standards of efficiency and accuracy in HSI classification, enhancing the capabilities of remote sensing applications. The method's practical implications highlight its value in environmental surveillance, agriculture, and other critical areas requiring detailed analysis of the Earth's surface.HSIMamba is a novel framework designed for hyperspectral image (HSI) classification, leveraging bidirectional state space modules to efficiently extract spectral features. The model combines the operational efficiency of convolutional neural networks (CNNs) with the dynamic feature extraction capabilities of attention mechanisms found in Transformers, while avoiding the high computational demands associated with Transformers. HSIMamba processes data bidirectionally, enhancing spectral feature extraction and integrating it with spatial information for comprehensive analysis. This approach improves classification accuracy and addresses computational inefficiencies, making it suitable for contexts with limited computational resources. The model was tested on three widely recognized datasets—Houston 2013, Indian Pines, and Pavia University—and demonstrated superior performance compared to existing state-of-the-art models. HSIMamba redefines the standards of efficiency and accuracy in HSI classification, enhancing the capabilities of remote sensing applications. The method's practical implications highlight its value in environmental surveillance, agriculture, and other critical areas requiring detailed analysis of the Earth's surface.