Despite the wide and intensive research efforts focused on web prediction and prefetching techniques aimed to re- duce user?s perceived latency, few attempts to implement and use them in real environments have been done, mainly due to their complexity and supposed limitations that low user available bandwidths imposed few years ago. Nev- ertheless, current user bandwidths open a new scenario for prefetching that becomes again an interesting option to improve web performance. This paper presents Delfos, a framework to perform web predictions and prefetching on a real environment that tries to cover the existing gap between research and praxis. Delfos is integrated in the web archi- tecture without modifying the standard HTTP 1.1 protocol, and acts inserting predictions in the web server side, while prefetchs are carried out by the client. In addition, it can be also used as a flexible framework to evaluate and com- pare existing prefetching techniques and algorithms and to assist in the design of new ones because it provides detailed statistics reports.