Quantitative prediction of electronic properties in correlated materials requires simulations without empirical truncations and parameters. We present a method to achieve this goal through a new ab initio formulation of dynamical mean-field theory (DMFT). Instead of using small impurities defined in a low-energy subspace, which require complicated downfolded interactions which are often approximated, we describe a full cell GW+DMFT approach, where the impurities comprise all atoms in a unit cell or supercell of the crystal. Our formulation results in large impurity problems, which we treat here using an efficient coupled-cluster impurity solver that works on the real-frequency axis, combined with a one-shot G 0 W 0 treatment of long-range interactions. We apply our full cell approach to bulk Si and two antiferromagnetic correlated insulators, NiO and -Fe 2 O 3 , with impurities containing up to 10 atoms and 124 orbitals. We find that spectral properties, magnetic moments, and two-particle spin correlation functions are obtained in good agreement with experiments. In addition, in the metal oxides, the balanced treatment of correlations involving all orbitals in the cell leads to new insights into the orbital character around the insulating gap.