The paper introduces CDMamba, a novel model designed for change detection (CD) tasks in remote sensing images. CDMamba combines the strengths of global and local features to enhance the accuracy of CD. The model is composed of two main components: the Scaled Residual ConvMamba (SRCM) block and the Adaptive Global Local Guided Fusion (AGLGF) block. The SRCM block integrates the global feature extraction capabilities of Mamba with the local detail enhancement of convolution, addressing the issue of detailed feature extraction in dense prediction tasks. The AGLGF block facilitates bi-temporal feature interaction guided by other temporal global/local features, enhancing the discriminative power of change features. Extensive experiments on three datasets (WHU-CD, LEVIR-CD, and LEVIR+CD) demonstrate that CDMamba outperforms state-of-the-art methods in terms of overall accuracy, precision, recall, F1 score, and intersection over union (IoU). The code for CDMamba is open-sourced at https://github.com/moka-zht/CDMamba.The paper introduces CDMamba, a novel model designed for change detection (CD) tasks in remote sensing images. CDMamba combines the strengths of global and local features to enhance the accuracy of CD. The model is composed of two main components: the Scaled Residual ConvMamba (SRCM) block and the Adaptive Global Local Guided Fusion (AGLGF) block. The SRCM block integrates the global feature extraction capabilities of Mamba with the local detail enhancement of convolution, addressing the issue of detailed feature extraction in dense prediction tasks. The AGLGF block facilitates bi-temporal feature interaction guided by other temporal global/local features, enhancing the discriminative power of change features. Extensive experiments on three datasets (WHU-CD, LEVIR-CD, and LEVIR+CD) demonstrate that CDMamba outperforms state-of-the-art methods in terms of overall accuracy, precision, recall, F1 score, and intersection over union (IoU). The code for CDMamba is open-sourced at https://github.com/moka-zht/CDMamba.