The Climate Modeling Alliance (CliMA) are developing the first Earth system model that automatically learns from diverse data sources. The CliMA model will exploit advances in machine learning and data assimilation to learn from observations and from data generated on demand in targeted high-resolution simulations, for example, of clouds or ocean turbulence. This will allow us to reduce and quantify uncertainties in climate predictions.For processing data and for simulating the Earth system, it will exploit state-of-the-art algorithms to run on the world’s fastest supercomputers and on the cloud. It will be scalable to ever finer resolution globally, and its targeted high-resolution simulations will provide detailed local climate information where needed.The CliMA consortium is committed to transparency and open science principles. The modeling platform is open source, and results are available to the public. This will provide interfaces to the CliMA modeling platform so that it can become the anchor of an ecosystem of front-end apps. These apps may provide detailed models, for example, of flood risks, risks of extreme heat, crop yields, and other climate impacts.