Tabbed browsing can often become a counter-intuitive experience. After opening dozens of tabs, the user interface becomes cluttered, which can lead to a decrease in productivity, unnecessary cognitive load, and a detrimental user experience. This paper presents an exploratory web browser extension capable of organising tabs automatically, grouping them by the use of both K-means and DBSCAN clustering. A preliminary user survey (n = 40) was conducted to gain insights regarding browsing behaviours and assess the need for tab organisation. The Google Chrome extension developed employed a Python backend to apply the clustering methods to the tabs. After comparing the performance of both approaches through a final user survey (n = 41), no significant differences were found between preferences for the different grouping mechanisms. The work demonstrates how machine learning algorithms can be leveraged within the browser to create a tab management tool, with the potential to enhance the user experience.