GitHub Repository

AeroJAX: A differentiable, structure-preserving framework for real-time flow simulation, control, and inverse design. Architected for neural operator integration and latent-space acceleration. Built with JAX.

120 starsPython

Interactive fluid simulation in Jax using Brinkman penalization

Name: Interactive fluid simulation in Jax using Brinkman penalization
Availability: InStock
Author: arriemeijer

by arriemeijer·May 13, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerWizardrySolve My ProblemNiche Gem

Draw obstacles with your mouse and get gradient-based inverse design without adjoint solvers.

Strengths

•Brinkman penalization enables immersed boundaries without mesh regeneration mid-simulation.
•End-to-end JAX differentiability enables inverse design without separate adjoint solver.
•Swappable pressure solvers (FFT, Multigrid, Neural Operator) at runtime without restart.

Weaknesses

•Niche audience limits broader appeal—CFD researchers only, not general developers.
•No mention of 3D simulation support, appears limited to 2D domains.