With the widespread integration of large models into embodied intelligent agents, they are evolving from task executors to autonomous decision-makers and expanding into complex collaborative tasks. However, the increasing intelligence and autonomy of these agents pose significant challenges to the robustness of swarm intelligence collaboration. While blockchain can provide trusted collaboration support, traditional energy-intensive architectures are constrained by the energy limitations of embodied intelligent agents, potentially leading to performance bottlenecks. To address this issue, this paper proposes DDSR, a consensus mechanism based on Dynamic Swarm Reputation, to provide trusted service support for embodied intelligence collaboration. DDSR confines the consensus scope within the collaborative swarm and links the agents’ stakes and fault tolerance thresholds to swarm reputation, ensuring trusted collaboration while achieving lightweight consensus. Additionally, DDSR introduces a dynamic fault tolerance strategy based on swarm reputation, allowing the fault tolerance threshold to be adaptively adjusted according to the reputation performance within the swarm, thereby optimizing consensus efficiency and security. Experimental results demonstrate that DDSR enables fair reputation evaluation, ensures the stability and security of the consensus process, and enhances the robustness of swarm collaboration.