INTRODUCTION: There are more people living with dementia in low- and middle-income countries (LMICs) than in high-income countries. Evidence-based interventions to improve the lives of people living with dementia and their carers are needed, but a systematic mapping of methodologically robust studies in LMICs and synthesis of the effectiveness of dementia interventions in these settings is missing. METHODS AND ANALYSIS: A systematic review and meta-analysis will be conducted to answer the question: Which dementia interventions were shown to be effective in LMICs and how do they compare to each other? Electronic database searches (MEDLINE, EMBASE, PsycINFO, CINAHL Plus, Global Health, WHO Global Index Medicus, Virtual Health Library, Cochrane CENTRAL, Social Care Online, BASE, MODEM Toolkit, Cochrane Database of Systematic Reviews) will be complemented by hand searching of reference lists and local knowledge of existing studies from an international network of researchers in dementia from LMICs. Studies will be eligible for inclusion if they were published between 2008 and 2018, conducted in LMICs and evaluated the effectiveness of a dementia intervention using a study design that supports causal inference of the treatment effect. We will include both randomised and non-randomised studies due to an anticipated low number of well-conducted randomised trials in LMICs and potentially greater external validity of non-randomised studies conducted in routine care settings. In addition to narrative synthesis of the interventions, feasibility of pairwise and network meta-analyses will be explored to obtain pooled effects of relative treatment effects. ETHICS AND DISSEMINATION: Secondary analysis of published studies, therefore no ethics approval required. Planned dissemination channels include a peer-reviewed publication as well as a website, DVD and evidence summaries. PROSPERO REGISTRATION NUMBER: CRD42018106206.