Content syndication has become a popular mean for timely delivery of frequently updated information on the Web. It essentially enhances traditional pull-oriented searching and browsing of web pages with push-oriented protocols. In such paradigm, publishers deliver brief information summaries on the Web, called news items, while information consumers subscribe to a number of feeds seen as information channels and get informed about the addition of recent items. However, many Web syndication applications imply a tight coupling between feed producers with consumers, and, they do not help users finding news items with interesting content. This demonstration shows a prototype which integrates the whole processus of thin filtering steps on numerous RSS feeds in memory, based on keyword-based subscriptions. Our system proposes to notify items related to set of keywords either by broad-match semantic, partial matching and a diversity/novelty filtering. In this demonstrate we discuss how our system integrates the three paradigms through dedicated indexes and a window-based structure for diversity/novelty filtering. We will demonstrate the management of notifications and global information on our system.