Eastern Boundary Upwelling Systems (EBUS) contribute disproportionately to global marine productivity and fisheries, yet their response to climate change remains poorly understood. Given the essential ecosystem services they support, improving projections of future EBUS dynamics is critical. Here we analyze projections of Net Primary Production (NPP) and its driving mechanisms using Earth System Models (ESMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6). Across the four major EBUS, twenty-first century NPP projections exhibit larger model uncertainty than scenario uncertainty, with limited confidence in the direction of future trends under different scenarios. This uncertainty partially results from compensating positive and negative NPP anomalies within individual systems, with consistent multi-model responses only emerging at subsystem scales. Although, consistent with most past studies, changes in upwelling-favorable winds are an important driver of the EBUS NPP response to climate change, they cannot fully explain projected responses. In the equatorward sectors of the Canary and Benguela systems, as well as in the historically most productive area of the California system (regions encapsulating 25 % of total EBUS area) a weakening of alongshore wind stress reduces upwelling intensity, nutrient supply to the euphotic zone and consequently NPP. However, in the remaining 75 % of EBUS extent, additional mechanisms are required to explain projected changes. These include upwelling anomalies induced by geostrophic transport and wind-stress curl, enhanced stratification, and changes in subsurface nutrient reservoirs, highlighting the complex and locally-specific response of EBUS productivity to climate change.