Change detection from satellite images typically incurs a delay ranging from several hours up to days because of latency in downlinking the acquired images and generating orthorectified image products at the ground stations; this may preclude real- or near real-time applications. To overcome this limitation, we propose shifting the entire change detection workflow onboard satellites. This requires to simultaneously solve challenges in data storage, image registration and change detection with a strict complexity constraint. In this paper, we present a novel and efficient framework for onboard change detection that addresses the aforementioned challenges in an end-to-end fashion with a deep neural network composed of three interlinked submodules: (1) image compression, tailored to minimize onboard data storage resources; (2) lightweight co-registration of non-orthorectified multi-temporal image pairs; and (3) a novel temporally-invariant and computationally efficient change detection model. This is the first approach in the literature combining all these tasks in a single end-to-end framework with the constraints dictated by onboard processing. Experimental results compare each submodule with the current state-of-the-art, and evaluate the performance of the overall integrated system in realistic setting on low-power hardware. Compelling change detection results are obtained in terms of F1 score as a function of compression rate, sustaining a throughput of 0.7 Mpixel/s on a 15W accelerator.