Video-on-demand (VoD) is becoming a popular service for commercial content distribution by offering end users the freedom to access recorded programmes. The management of on-demand assets is essential to maximise the efficiency of storage and network utilisation as well as advertisement. This paper introduces our recent efforts in design and implementation of an adaptive VoD archive system in an IPTV infrastructure. The system exploits live statistics on the user behaviours as well as the dynamic popularity of VoD programmes. Using the modelled programme popularity function, the VoD archive is capable of managing the VoD repository by adapting to the most recent user requests. The design has greatly improved the activity of VoD repository and user experience in on-demand services.