We introduce GHP-MOFassemble, a Generative artificial intelligence (AI), High Performance framework to accelerate the rational discovery of metal-organic frameworks (MOFs) with high CO2 capacity and synthesizable linkers. We combine a diffusion model, a class of generative AI, to generate novel linkers that are assembled with one of three pre-selected nodes into MOFs in a primitive cubic (pcu) topology. The CO2 capacities of these AI-generated MOFs are predicted using a modified version of the crystal graph convolutional neural network model. We then use the LAMMPS code to perform molecular dynamics simulations to identify AI-generated MOF structures that converge to stable structures, and maintain their porous properties throughout the simulations. Among 120,000 pcu MOF candidates generated by GHP-MOFassemble, with three distinct metal nodes (Cu paddlewheel, Zn paddlewheel, Zn tetramer), a total of 102 structures completed molecular dynamics simulations at 1bar with predicted CO2 capacity higher than 2mmol/g at 0.1 bar, which corresponds to the top 5% of hMOF in the hypothetical MOF (hMOF) dataset in the MOFX-DB database. Among these candidates, 18 have change in density lower than 1% during molecular dynamics simulations, indicating their stability. The top five GHP-MOFassemble's MOFs have CO2 capacities higher than 96.9% of hMOF structures.