Relying on intuitive understanding, data availability, and fixed physical assumptions, traditional constitutive models often fall short in accurately predicting the non-affine behaviors of materials with fibrous microstructures, such as the extracellular space surrounding cells in soft tissues [1]. Instead of using histology-derived strain energy functions, FE2 homogenization computes the macroscopic stress by volume-averaging the mesoscale stress obtained by solving the mechanical equilibrium on discrete microstructures reconstructed from high-resolution images [2]. This approach offers greater fidelity but at a high computational cost [3]. Data-driven modeling is promising, yet standard neural networks (NNs) overlook material theory and require large datasets. Physics-informed and constitutive artificial NNs embed physical laws via the loss function and the architecture, respectively [4, 3]. However, most remain histology-inspired with limited access to microstructural features. HyperCANs advance this direction by devising a methodology to account for microstructural variability within lattice-based metamaterials [5]. In this work, we explore what HyperCANs [5] bring to the table to model the non-affine mechanics of extracellular fiber networks. Using meta-learning, we develop a microstructure-informed constitutive model for biological tissue, trained on the responses of our topology-based representative volume elements [1]. The hypernetwork receives as input the structural descriptors and dynamically generates the parameters of a thermodynamically consistent target network that maps strain to stress. By conditioning the tissue response on the microstructure, the proposed model offers a promising framework for advancing the field of tissue biomechanics and mechanobiology. [1] Cardona S., Peirlinck M., Fereidoonnezhad B., J. Mech. Phys. Solids 205 (2025). [2] Stylianopoulos T., Barocas V.H., Comput. Methods Appl. Mech. Eng. 196:2981–2990 (2007). [3] Linka K., Hillgärtner M., Abdolazizi K.P., Aydin R.C., Itskov M., Cyron C.J., J. Comput. Phys. 429:110010 (2021). [4] Liu M., Liang L., Sun W., Comput. Methods Appl. Mech. Eng. 372:113402 (2020). [5] Zheng L., Kochmann D.M., Kumar S., Extreme Mech. Lett. 72:102243 (2024).