The platform
A working atlas.
Four capabilities, mapped to four scales. Click any pin to read the deep dive.
Open a capability
Full-Scale Simulation
From morphology-rich single neurons to whole-brain networks — one runtime spans every scale.
Read full →AI Compatibility
Compose Flax, Optax, and Orbax inside biologically realistic simulations.
Read full →Differentiable Optimization
Backprop through time, surrogate gradients, online learning — built into the language of the model.
Read full →Powered by JAX
JIT-compiled, GPU/TPU accelerated, composable transforms.
Read full →