Digital agriculture (DA) broadly is the use of data-driven techniques toward the sustainable intensification of farm yields and efficiency, which can have major financial, environmental, and societal impacts. We present a cloud-native edge computing framework that allows agricultural decision-makers to make sustainable crop management choices in DA. This framework is powered by the KubeStellar open-source project that focuses on addressing configuration management challenges in multi-cluster environments, including edge. The proposed framework is designed with agricultural users in mind and allows researchers to rapidly deploy/manage computational AI models for plant disease detection using NASA imagery without retaining confidential stakeholder information. This system will empower agricultural stakeholders to make well-informed data-driving decisions by granting them access to accurate data on the farm and the latest advances in SI-ML disease detection in a cloud-native environment.