The concept of object can be employed to achieve tolerance to hardware faults in distributedsystems.Replication by introducing several copies for each object allows a continuous service even in case offailure.In particular,the paper describes an object model,PROM,which exploits replication by defining sev-eral passive back-up copies for any object.The system automatically recovers any failure of a copy in execu-tion by activating a spare copy and restarting it from a previous checkpoint.The aim of the paper is the analysis of the effective support for PROM.This support is organized instructured levels on a distributed architecture.The services that the support should include to guarantee the de-sired replication model are described. The concept of object can be employed to achieve tolerance to hardware faults in distributed systems. Replication by introducing several copies for each object allows a continuous service even in case offailure. In particular, the paper describes an object model, PROM, which exploits replication by defining sev-eral passive back-up copies for any object. The system automatically recovers any failure of a copy in execu- tion by activating a spare copy and restarting it from a previous checkpoint. The aim of the paper is the analysis of the effective support for PROM.This support is organized instructured levels on a distributed architecture. The services that the support should include to guarantee the de-sired replication model are described.