Nengo is highly extensible and flexible: You can define your own neuron types, learning rules, optimization methods, reusable subnetworks, and much more. You can also get input directly from hardware, build and run deep neural networks, drive robots, and even implement your model on a completely different neural simulator or neuromorphic hardware.

Nengo is a powerful development environment at every scale: Among other things, Nengo is used to implement networks for deep learning, vision, motor control, visual attention, serial recall, action selection, working memory, attractor dynamics, inductive reasoning, path integration, and planning with problem solving. Nengo has libraries specifically designed to help with cognitive modelling, deep learning, adaptive control, and accurate dynamics, to name a few.