Clustering is a fundamental task in data analysis, aimed at grouping similar data points together. In this paper, we propose a novel clustering algorithm called CentroidLink that combines the strengths of centroid-based and linkage-based approaches to enhance the clustering process. The algorithm leverages the centroid concept to determine the initial cluster centers and then applies a linkage-based approach to iteratively refine the clusters. We conducted extensive experiments on various datasets to evaluate the performance of CentroidLink and compared it with existing clustering algorithms. The results demonstrate that CentroidLink outperforms state-of-the-art algorithms in terms of clustering accuracy, robustness, and scalability. This novel algorithm opens up new possibilities for more effective data clustering and has potential applications in various domains such as pattern recognition, data mining, and machine learning.