Objective To evaluate the effect of exogenous melatonin and its analogues on the prevention of delirium in critically ill patients by meta-analysis. Methods Randomized controlled trials of exogenous melatonin and its analogues in the prevention of delirium in critically ill patients were searched by computer from the Cochrane Library, PubMed, Web of Science, Embase, China National Knowledge Infrastructure, Chongqing VIP, Wanfang, and SinoMed databases. The trial group was treated with melatonin or its analogues, while the control group was treated with placebo. The retrieval period was from the establishment of database to January 14th, 2021. Two researchers independently evaluated the literature quality, and meta-analysis was performed using RevMan 5.4 software. Results A total of 11 randomized controlled trials containing 1177 patients were enrolled, including 588 patients in the trial group and 589 patients in the control group. The results showed that exogenous melatonin and its analogues could reduce the occurrence of delirium in critically ill patients [odds ratio (OR)=0.45, 95% confidence interval (CI) (0.22, 0.91), P=0.03] and shorten the time of mechanical ventilation [standard mean difference (SMD)=−0.49, 95%CI (−0.94, −0.03), P=0.04], while might not affect the mortality rate [OR=0.73, 95%CI (0.46, 1.17), P=0.19] or length of intensive care unit stay [SMD=−0.05, 95%CI (−0.26, 0.15), P=0.61]. Conclusions The current evidence shows that exogenous melatonin and its analogues have some effect on reducing the occurrence of delirium and shortening the duration of mechanical ventilation in critically ill patients, and have no significant effect on reducing the mortality or length of intensive care unit stay. The above conclusions need to be confirmed by more high-quality studies.