https://github.com/kimimgo/awesome-ai-cae

A curated list of 100+ AI-ready tools for Computer-Aided Engineering, ranked by an AI-Readiness Score (agent-callability: MCP, Python API, CLI, pip). CFD, FEA, SPH, DEM, differentiable simulation, neural operators, PINNs, MCP servers.
https://github.com/kimimgo/awesome-ai-cae
List: awesome-ai-cae
ai ai-for-science artificial-intelligence awesome awesome-list cae cfd computational-engineering deep-learning differentiable-simulation fea machine-learning mcp mesh-generation neural-operator physics-informed-neural-networks simulation sph surrogate-model visualization
Last synced: 2 days ago
JSON representation
Host: GitHub
URL: https://github.com/kimimgo/awesome-ai-cae
Owner: kimimgo
License: cc0-1.0
Created: 2026-03-13T14:04:43.000Z (3 months ago)
Default Branch: main
Last Pushed: 2026-06-08T09:34:14.000Z (6 days ago)
Last Synced: 2026-06-08T10:19:39.516Z (6 days ago)
Topics: ai, ai-for-science, artificial-intelligence, awesome, awesome-list, cae, cfd, computational-engineering, deep-learning, differentiable-simulation, fea, machine-learning, mcp, mesh-generation, neural-operator, physics-informed-neural-networks, simulation, sph, surrogate-model, visualization
Language: Python
Size: 1.46 MB
Stars: 33
Watchers: 1
Forks: 7
Open Issues: 3
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: code-of-conduct.md
Awesome Lists containing this project

README

          









[![Awesome](https://awesome.re/badge-flat2.svg)](https://awesome.re)

[![awesome-lint](https://img.shields.io/github/actions/workflow/status/kimimgo/awesome-ai-cae/lint.yml?branch=main&style=flat-square&label=awesome-lint&color=00d4ff)](https://github.com/kimimgo/awesome-ai-cae/actions/workflows/lint.yml)

[![License CC0-1.0](https://img.shields.io/badge/license-CC0--1.0-7c3aed?style=flat-square)](https://creativecommons.org/publicdomain/zero/1.0/)

[![PRs welcome](https://img.shields.io/badge/PRs-welcome-2ea44f?style=flat-square)](CONTRIBUTING.md)

[![Stars](https://img.shields.io/github/stars/kimimgo/awesome-ai-cae?style=flat-square&color=f472b6)](https://github.com/kimimgo/awesome-ai-cae/stargazers)

[![Last commit](https://img.shields.io/github/last-commit/kimimgo/awesome-ai-cae?style=flat-square&color=00d4ff)](https://github.com/kimimgo/awesome-ai-cae/commits/main)

[![Tools](https://img.shields.io/badge/tools-100%2B-00d4ff?style=flat-square)](READINESS.md)

[![AI-Native](https://img.shields.io/badge/🟢_AI--Native-2-2ea44f?style=flat-square)](READINESS.md)

[![Ranking](https://img.shields.io/badge/ranking-weekly-7c3aed?style=flat-square)](.github/workflows/readiness.yml)

### The CAE tools an AI agent can actually call

**Open-source simulation, CAD & meshing tools for agentic / LLM-driven engineering** — driveable headless via **MCP, Python, or CLI** (no GUI-only tools). The **only CAE list with a weekly agent-callability ranking**. Ranked by *callability*, not stars.

**100+ tools** · **3 MCP servers** · **2 AI-Native** · machine-readable [JSON](data/readiness.json) / [CSV](data/readiness.csv) · weekly-regenerated [ranking](READINESS.md)

_{Scope: agent-callable CAE/CAD/CAM **tools**, plus a small set of **adjacent** Datasets & Learning Resources for context.}

[**🚀 Quickstart**](#quickstart--give-your-agent-a-cae-tool) · [**🏆 Index**](#ai-readiness-index) · [**📊 Methodology**](#how-the-score-works)

[한국어](docs/README.ko.md) · [中文](docs/README.zh.md) · [日本語](docs/README.ja.md) · [Deutsch](docs/README.de.md) · [Français](docs/README.fr.md) · [Español](docs/README.es.md) · [Português](docs/README.pt.md)








## Contents

- [Quickstart](#quickstart--give-your-agent-a-cae-tool)

- [AI-Readiness Index](#ai-readiness-index)

- [How the Score Works](#how-the-score-works)

- [Core Engine Readiness](#core-engine-readiness)

- [MCP Servers](#mcp-servers)

- [CFD — Computational Fluid Dynamics](#cfd--computational-fluid-dynamics)

- [FEA — Finite Element Analysis](#fea--finite-element-analysis)

- [SPH — Smoothed Particle Hydrodynamics](#sph--smoothed-particle-hydrodynamics)

- [DEM — Discrete Element Method](#dem--discrete-element-method)

- [Visualization & Post-processing](#visualization--post-processing)

- [CAD & Geometry](#cad--geometry)

- [Mesh Generation](#mesh-generation)

- [Differentiable Simulation](#differentiable-simulation)

- [AI/ML for Simulation](#aiml-for-simulation)

- [Surrogate Models & PINNs](#surrogate-models--pinns)

- [Optimization](#optimization)

- [Data Formats & I/O](#data-formats--io)

- [Datasets & Benchmarks](#datasets--benchmarks)

- [Learning Resources](#learning-resources)

- [Star History](#star-history)

## Quickstart — give your agent a CAE tool







> Three tools here ship a [Model Context Protocol](https://modelcontextprotocol.io/) server, so an agent (Claude Desktop, Cursor, Cline…) drives them with zero glue code. Add one to your MCP client config:

```jsonc

{

  "mcpServers": {

    "viznoir": { "command": "uvx", "args": ["viznoir"] }

  }

}

```

MCP serverAsk your agentInstall

viznoir"Render this OpenFOAM case as a cinematic volume animation."uvx viznoir

ParaView-MCP"Open this VTK file, color by pressure, screenshot it."see repo

OpenFOAM-MCP"Set up a pipe-flow case and explain the turbulence model."see repo

_{Exact launch command lives in each server's README. No MCP? Every other tool is Python/CLI-scriptable — your agent calls it the same way you would.}

^{[back to top](#contents)}

## AI-Readiness Index

> The headline metric: tools ranked by **agent-callability** — MCP, Python API, CLI, maintenance — not stars. Auto-updated weekly by [`readiness-score.py`](scripts/readiness-score.py). Full table: [READINESS.md](READINESS.md) · machine-readable: [`data/readiness.json`](data/readiness.json).

#ScoreGradeToolInterfaces⭐

🥇94🟢 AI-Nativellnl/paraview_mcpMCP, Python, pip52

🥈93🟢 AI-Nativekimimgo/viznoirMCP, Python, pip ✅13

🥉65🔵 Agent-Readytaichi-dev/taichiPython, pip ✅28,243

465🔵 Agent-Readygoogle-deepmind/mujocoPython, pip13,795

565🔵 Agent-ReadyNVIDIA/warpPython, pip6,736

665🔵 Agent-Readygoogle-deepmind/graphcastPython, pip6,667

764🔵 Agent-Readymaziarraissi/PINNsPython, pip5,915

864🔵 Agent-ReadyCadQuery/cadqueryPython, pip ✅5,260

964🔵 Agent-Readylibigl/libiglPython, pip5,027

1064🔵 Agent-Readylululxvi/deepxdePython, pip4,222

1164🔵 Agent-Readypyvista/pyvistaPython, pip ✅3,695

1264🔵 Agent-ReadyNeuralOperator/neuraloperatorPython, pip3,680

1364🔵 Agent-Readymikedh/trimeshPython, pip ✅3,582

1464🔵 Agent-Readymeta-pytorch/botorchPython, pip3,545

1564🔵 Agent-ReadyPolymathicAI/the_wellPython, pip3,422

_{🟢 2 AI-Native · 🔵 56 Agent-Ready · 🟡 23 Scriptable · ⚪ 20 Experimental — across 101 ranked tools (updated 2026-06-08). ✅ = install + import execution-verified. Full ranking →}

^{[back to top](#contents)}

## How the Score Works

> The **AI-Readiness Score** (0–100) ranks tools by how directly an autonomous agent can drive them — *callability over popularity*.

SignalPointsWhy it matters to an agent

MCP server35The agent calls it with zero glue code

Python API25Native scripting

CLI / REST15Headless automation

pip-installable+15One-command install (verified on PyPI)

Maintained (<6 mo)15Won't rot mid-project

Adoption (stars)10log-scaled — popularity barely moves the needle

The five base signals (MCP + Python + CLI + Maintained + Adoption) total **100**; **pip is an additive bonus**, and the final score is **capped at 100**. So a tool can reach 100 several ways, but only MCP servers clear the AI-Native bar.

**Grades:** ![AI-Native 75+](https://img.shields.io/badge/🟢_AI--Native-75%2B-2ea44f?style=flat-square) ![Agent-Ready 50-74](https://img.shields.io/badge/🔵_Agent--Ready-50--74-00d4ff?style=flat-square) ![Scriptable 30-49](https://img.shields.io/badge/🟡_Scriptable-30--49-f5a623?style=flat-square) ![Experimental under 30](https://img.shields.io/badge/⚪_Experimental-%3C30-9e9e9e?style=flat-square)

Scores regenerate weekly from `README.md` via [`readiness-score.py`](scripts/readiness-score.py) — fully reproducible, no hand-tuning. Open a PR adding a tool and [a bot scores it automatically](.github/workflows/pr-readiness.yml).

### Verified vs declared

Honest about what's checked.

**Verified** (objective, reproducible) — live GitHub stars/activity; PyPI availability; and an **install + import smoke-test** ([`verify_install.py`](scripts/verify_install.py) → [`data/verified.json`](data/verified.json)) that spins up an isolated `uv` venv, runs `pip install` + `import`, and records the result. Tools that pass are marked **✅** in the Index. *Current run: 8/10 flagship tools pass; the 2 misses are recorded honestly — Gmsh needs a system GL lib, DeepXDE needs a chosen backend.*

**Declared** (from the entry's tags) — `MCP` and `CLI/API`. We link the server/CLI; we don't yet replay an end-to-end agent call.

**Roadmap** (deepening the moat) — execution-verified MCP handshakes and headless runs, plus a per-tool *agent-call transcript*, so the score reflects tools an agent has actually driven, not just ones that expose an interface.

^{[back to top](#contents)}

## Core Engine Readiness

> A **hand-curated editorial** deep-dive on 17 foundational solvers — capability columns (Python binding, headless, Docker, AI-native) reflect maintainer judgment, ⭐ is live. This complements the auto-generated [Index](#ai-readiness-index) above, which stays the single source of truth for scores. Only 2 engines have MCP integration today.

EngineDomain⭐Python APIHeadlessDocker🤖 AI-Native

OpenFOAMCFDPyFoam✅✅✅ Foam-Agent, MCP

FEniCSFEA✅ Native✅✅—

GmshMesh—✅ Native✅✅—

VTK / ParaViewViz✅ Native✅✅✅ ParaView-MCP

SU2CFDpySU2✅✅—

MFEMFEAPyMFEM✅✅—

deal.IIFEALimited✅✅—

DualSPHysicsSPHInductiva API✅✅—

TaichiDiff. Sim✅ Native✅✅—

PyFRCFD✅ Native✅✅—

CalculiXFEA—pycalculix✅✅—

ElmerFEAPyElmer✅✅—

OpenCASCADECADpythonOCC✅✅—

MOOSEFEAPython✅✅—

FreeFEMFEAFreeFem++✅✅—

SfePyFEA✅ Native✅✅—

MuJoCoDiff. Sim✅ Native✅✅—

^{[back to top](#contents)}

## MCP Servers

> AI agents call these directly via [Model Context Protocol](https://modelcontextprotocol.io/).

- [kimimgo/viznoir](https://github.com/kimimgo/viznoir) `Python` `MCP` - Cinema-quality science visualization. 22 tools for rendering, slicing, contouring, volume rendering, and animating OpenFOAM/VTK/CGNS data via VTK. Headless EGL/OSMesa.

- [llnl/paraview_mcp](https://github.com/llnl/paraview_mcp) `Python` `MCP` - Natural language control of ParaView via MCP. Multimodal LLM observes viewport for visual feedback (LLNL).

- [webworn/openfoam-mcp-server](https://github.com/webworn/openfoam-mcp-server) `C++` `MCP` - OpenFOAM MCP server with Socratic questioning for CFD education and expert error resolution.

^{[back to top](#contents)}

## CFD — Computational Fluid Dynamics

> Open-source solvers for fluid flow, heat transfer, and multiphysics.

- [OpenFOAM/OpenFOAM-dev](https://github.com/OpenFOAM/OpenFOAM-dev) `C++` - The open source CFD toolbox. Finite volume solvers for incompressible/compressible flow, multiphase, combustion, heat transfer.

- [su2code/SU2](https://github.com/su2code/SU2) `C++` `Python` - Multiphysics simulation and design optimization. Compressible/incompressible flow, structural analysis, adjoint-based design.

- [LLNL/Nek5000](https://github.com/Nek5000/Nek5000) `Fortran` - High-order spectral element CFD solver. DNS/LES of turbulent flows. Scalable to millions of cores.

- [Nek5000/nekRS](https://github.com/Nek5000/nekRS) `C++` `CUDA` - GPU-accelerated spectral element CFD. Successor to Nek5000 with native CUDA/HIP/OpenCL support.

- [precice/precice](https://github.com/precice/precice) `C++` `Python` - Coupling library for multi-physics simulations. Fluid-structure interaction, conjugate heat transfer.

- [PyFR/PyFR](https://github.com/PyFR/PyFR) `Python` - High-order flux reconstruction CFD on mixed unstructured grids. GPU-accelerated (CUDA/OpenCL/HIP).

^{[back to top](#contents)}

## FEA — Finite Element Analysis

> Structural, thermal, and multiphysics FEM solvers.

- [CalculiX](http://www.calculix.de/) `Fortran` `C` - Free 3D structural FEM. Linear/nonlinear static, dynamic, thermal analysis. Abaqus INP compatible.

- [dealii/dealii](https://github.com/dealii/dealii) `C++` - Adaptive finite elements. Supports hp-refinement, multigrid, and parallel distributed computing.

- [ElmerCSC/elmerfem](https://github.com/ElmerCSC/elmerfem) `Fortran` `C++` - Multiphysics FEM solver. Fluid dynamics, structural mechanics, electromagnetics, heat transfer. CSC Finland.

- [FEniCS/dolfinx](https://github.com/FEniCS/dolfinx) `C++` `Python` - Next-generation FEniCS. Automated PDE solving with high-level Python/C++ interface. Parallel, scalable.

- [firedrakeproject/firedrake](https://github.com/firedrakeproject/firedrake) `Python` - Automated FEM with code generation from high-level problem descriptions. UFL domain-specific language.

- [FreeFem/FreeFem-sources](https://github.com/FreeFem/FreeFem-sources) `C++` - Partial differential equation solver using finite element method. High-level scripting language for 2D/3D problems.

- [idaholab/moose](https://github.com/idaholab/moose) `C++` `Python` - Multiphysics Object-Oriented Simulation Environment. Coupled physics FEM framework from Idaho National Lab.

- [KratosMultiphysics/Kratos](https://github.com/KratosMultiphysics/Kratos) `C++` `Python` - Framework for multi-physics FEM. Structural, fluid, thermal, contact, FSI.

- [mfem/mfem](https://github.com/mfem/mfem) `C++` - High-order finite element library. Supports GPU acceleration, AMR, and dozens of physics applications.

- [OpenSees/OpenSees](https://github.com/OpenSees/OpenSees) `C++` - Open system for earthquake engineering simulation. Structural and geotechnical response analysis. Berkeley.

- [sfepy/sfepy](https://github.com/sfepy/sfepy) `Python` - Simple Finite Elements in Python. Solve PDEs by FEM in 1D, 2D, and 3D with plain Python scripting.

^{[back to top](#contents)}

## SPH — Smoothed Particle Hydrodynamics

> Meshless particle methods for free-surface flows and fluid-structure interaction.

- [DualSPHysics/DualSPHysics](https://github.com/DualSPHysics/DualSPHysics) `C++` `CUDA` - GPU-accelerated SPH solver. Free-surface flows, wave generation, fluid-structure interaction, floating bodies.

- [InteractiveComputerGraphics/SPlisHSPlasH](https://github.com/InteractiveComputerGraphics/SPlisHSPlasH) `C++` - Physically-based SPH fluid simulation. DFSPH, IISPH, PBF pressure solvers. Viscosity, surface tension.

- [pypr/pysph](https://github.com/pypr/pysph) `Python` `Cython` - SPH framework in Python. Compressible/incompressible flows, solid mechanics, coupled problems.

^{[back to top](#contents)}

## DEM — Discrete Element Method

> Particle-based simulation of granular materials, powders, and coupled particle-fluid systems.

- [CFDEMproject/LIGGGHTS-PUBLIC](https://github.com/CFDEMproject/LIGGGHTS-PUBLIC) `C++` - Industry-standard open-source DEM for granular materials. LAMMPS-based with heat transfer and CFD coupling.

- [lammps/lammps](https://github.com/lammps/lammps) `C++` `Python` - Large-scale Atomic/Molecular Massively Parallel Simulator. Classical MD and DEM with granular package. Sandia National Labs.

- [MercuryDPM](https://bitbucket.org/mercurydpm/mercurydpm) `C++` - Open-source DEM for granular and particle-laden flows. Coarse-graining, contact models, and the MercuryCG analysis toolkit.

- [SudoDEM/SudoDEM](https://github.com/SudoDEM/SudoDEM) `C++` `Python` - DEM for non-spherical particles. Polyhedra, super-ellipsoids, and cylinders for realistic granular simulations.

- [Yade](https://gitlab.com/yade-dev/trunk) `C++` `Python` - Extensible open-source DEM framework. Python scripting, deformable particles, coupled DEM-FEM and DEM-fluid problems.

^{[back to top](#contents)}

## Visualization & Post-processing

> Rendering, plotting, and interactive exploration of simulation results.

- [kimimgo/viznoir](https://github.com/kimimgo/viznoir) `Python` `MCP` - Cinema-quality science visualization MCP server. 22 tools, EGL/OSMesa headless, cinematic lighting, physics animations.

- [Kitware/VTK](https://github.com/Kitware/VTK) `C++` `Python` - The Visualization Toolkit. 3D computer graphics, image processing, scientific visualization. Industry standard.

- [nmwsharp/polyscope](https://github.com/nmwsharp/polyscope) `C++` `Python` - Lightweight 3D viewer for meshes, point clouds, and scalar fields. One-line visualization for geometry processing.

- [pyvista/pyvista](https://github.com/pyvista/pyvista) `Python` - Pythonic VTK. Streamlined 3D plotting, mesh analysis, and interactive visualization.

- [Kitware/ParaView](https://github.com/Kitware/ParaView) `C++` `Python` - Multi-platform data analysis and visualization. VTK-based GUI + Python scripting + client-server architecture.

- [napari/napari](https://github.com/napari/napari) `Python` - Fast n-dimensional image viewer. Plugin ecosystem for biomedical and scientific imaging.

- [marcomusy/vedo](https://github.com/marcomusy/vedo) `Python` - Scientific analysis and visualization of 3D objects and point clouds. VTK-based with simple API.

- [plotly/plotly.py](https://github.com/plotly/plotly.py) `Python` - Interactive, publication-quality graphs. 3D scatter, surface, mesh, volume. Web-based rendering.

^{[back to top](#contents)}

## CAD & Geometry

> Parametric modeling, geometry processing, and CAD data exchange.

- [CadQuery/cadquery](https://github.com/CadQuery/cadquery) `Python` - Parametric 3D CAD scripting. Build models with Python, export STEP/STL/IGES. OpenCASCADE kernel.

- [CadQuery/OCP](https://github.com/CadQuery/OCP) `C++` `Python` - Python wrapper for OpenCASCADE via pybind11. Low-level foundation for CadQuery and build123d.

- [FreeCAD/FreeCAD](https://github.com/FreeCAD/FreeCAD) `C++` `Python` - Open-source parametric 3D CAD modeler. Part design, FEM workbench, BIM, path (CAM).

- [gumyr/build123d](https://github.com/gumyr/build123d) `Python` - Modern Python CAD with algebraic geometry API. Successor to CadQuery with cleaner builder pattern.

- [mikedh/trimesh](https://github.com/mikedh/trimesh) `Python` - Load and manipulate triangular meshes. Boolean operations, ray tracing, convex hulls, format conversion.

- [nschloe/pygmsh](https://github.com/nschloe/pygmsh) `Python` - Python interface for Gmsh. Scripted geometry + mesh generation with parametric control.

- [Open-Cascade-SAS/OCCT](https://github.com/Open-Cascade-SAS/OCCT) `C++` - Open CASCADE Technology. Kernel for 3D surface and solid modeling, CAD data exchange (STEP/IGES).

- [SolidCode/SolidPython](https://github.com/SolidCode/SolidPython) `Python` - Python frontend for OpenSCAD. Generate 3D models programmatically with CSG operations.

^{[back to top](#contents)}

## Mesh Generation

> Structured, unstructured, and AI-driven mesh generation for simulation preprocessing.

- [buaacyw/MeshAnything](https://github.com/buaacyw/MeshAnything) `Python` - Artist-quality mesh generation with autoregressive transformers. Any 3D input to mesh (ICLR 2025 spotlight).

- [CGAL/cgal](https://github.com/CGAL/cgal) `C++` - Computational Geometry Algorithms Library. Mesh generation, triangulation, Boolean operations, convex hulls.

- [Gmsh](https://gitlab.onelab.info/gmsh/gmsh) `C++` `Python` - Full-featured 3D finite element mesh generator. CAD engine, structured/unstructured meshing, built-in post-processing.

- [libigl/libigl](https://github.com/libigl/libigl) `C++` `Python` - Header-only geometry processing library. Mesh parameterization, deformation, Boolean ops. Eurographics award winner.

- [MmgTools/mmg](https://github.com/MmgTools/mmg) `C` - Anisotropic mesh adaptation for 2D/3D surface and volume remeshing. Metric-based automatic refinement.

- [NGSolve/netgen](https://github.com/NGSolve/netgen) `C++` `Python` - Automatic 3D tetrahedral mesh generator. CAD (OCC) integration, mesh optimization, parallel meshing.

- [nmwsharp/geometry-central](https://github.com/nmwsharp/geometry-central) `C++` - Applied geometry algorithms for surfaces and volumes. Geodesics, vector fields, intrinsic triangulations.

- [OpenMeshLab/MeshXL](https://github.com/OpenMeshLab/MeshXL) `Python` - Foundation model for 3D mesh generation. Pre-trained on Objaverse, text-to-mesh capable (NeurIPS 2024).

- [PyMesh/PyMesh](https://github.com/PyMesh/PyMesh) `Python` `C++` - Geometry processing library. Boolean, convex hull, remeshing, self-intersection repair.

- [pyvista/tetgen](https://github.com/pyvista/tetgen) `C++` `Python` - Python interface to TetGen tetrahedral mesh generator. Constrained Delaunay tetrahedralization with quality control.

- [wildmeshing/fTetWild](https://github.com/wildmeshing/fTetWild) `C++` - Fast and robust tetrahedral meshing. Handles self-intersections and degenerate input. Ten times faster than TetWild.

^{[back to top](#contents)}

## Differentiable Simulation

> GPU-native frameworks for gradient-based optimization through physics.

- [Autodesk/XLB](https://github.com/Autodesk/XLB) `Python` `JAX` - Differentiable Lattice Boltzmann for physics-ML. Scales to billions of cells on multi-GPU.

- [google/brax](https://github.com/google/brax) `Python` `JAX` - Massively parallel rigidbody physics on accelerator hardware. Millions of steps/second on TPU.

- [jax-md/jax-md](https://github.com/jax-md/jax-md) `Python` `JAX` - Differentiable, hardware-accelerated molecular dynamics. Runs on CPU/GPU/TPU via XLA.

- [gbionics/jaxsim](https://github.com/gbionics/jaxsim) `Python` `JAX` - Differentiable multibody dynamics engine. Hardware-accelerated robot learning and control via JAX.

- [google-deepmind/mujoco](https://github.com/google-deepmind/mujoco) `C++` `Python` - Multi-joint dynamics with contact. General-purpose physics engine for robotics, biomechanics, and control.

- [NVIDIA/warp](https://github.com/NVIDIA/warp) `Python` `CUDA` - Differentiable simulation and spatial computing. Reverse-mode AD, PyTorch/JAX interop.

- [taichi-dev/taichi](https://github.com/taichi-dev/taichi) `Python` `CUDA` - Productive GPU programming with automatic differentiation. DiffTaichi for differentiable physics.

- [tumaer/JAXFLUIDS](https://github.com/tumaer/JAXFLUIDS) `Python` `JAX` - Fully-differentiable CFD solver for 3D compressible single-phase and two-phase flows.

^{[back to top](#contents)}

## AI/ML for Simulation

> Neural operators, LLM agents, and foundation models for computational engineering.

- [csml-rpi/Foam-Agent](https://github.com/csml-rpi/Foam-Agent) `Python` `API` - AI agent for automated CFD workflows. LLM-driven OpenFOAM simulation setup and execution.

- [deepmodeling/deepmd-kit](https://github.com/deepmodeling/deepmd-kit) `Python` `C++` - Deep learning for molecular dynamics. Neural network potentials for large-scale atomistic simulations.

- [dynamicslab/pykoopman](https://github.com/dynamicslab/pykoopman) `Python` - Data-driven Koopman operator approximation. Dynamical system analysis and prediction from time series.

- [dynamicslab/pysindy](https://github.com/dynamicslab/pysindy) `Python` - Sparse Identification of Nonlinear Dynamics. Data-driven discovery of governing equations from measurements.

- [google-deepmind/graphcast](https://github.com/google-deepmind/graphcast) `Python` - Graph neural network for medium-range weather forecasting. Ten-day forecasts in under a minute (Nature 2023).

- [google/jax-cfd](https://github.com/google/jax-cfd) `Python` - JAX-based CFD. Differentiable Navier-Stokes solvers. GPU-accelerated, auto-differentiable.

- [Koopman-Laboratory/KoopmanLab](https://github.com/Koopman-Laboratory/KoopmanLab) `Python` - Koopman Neural Operator for mesh-free nonlinear PDE solving. Multi-scale decomposition.

- [lululxvi/deepxde](https://github.com/lululxvi/deepxde) `Python` - Deep learning library for PDEs. PINNs, DeepONet. Backends: TensorFlow, PyTorch, JAX, PaddlePaddle.

- [microsoft/aurora](https://github.com/microsoft/aurora) `Python` - Foundation model for Earth system prediction. Atmosphere, ocean, air quality. Pre-trained on ERA5 and CMIP6.

- [microsoft/ClimaX](https://github.com/microsoft/ClimaX) `Python` - Foundation model for weather and climate. Pre-trained on CMIP6, fine-tunable for downstream tasks.

- [NeuralOperator/neuraloperator](https://github.com/NeuralOperator/neuraloperator) `Python` - Neural operators in PyTorch. FNO, SFNO, UNO for learning PDE solution operators.

- [NVIDIA/physicsnemo](https://github.com/NVIDIA/physicsnemo) `Python` `CUDA` - Physics-ML framework (formerly Modulus). PINNs, neural operators, GNNs, diffusion models. Apache 2.0.

- [Terry-cyx/MetaOpenFOAM](https://github.com/Terry-cyx/MetaOpenFOAM) `Python` `API` - LLM-based multi-agent framework for CFD. Automated simulation pipeline from natural language.

- [tum-pbs/PhiFlow](https://github.com/tum-pbs/PhiFlow) `Python` - Differentiable PDE simulations. Fluid dynamics with TF/PyTorch/JAX. ML-physics hybrid workflows.

^{[back to top](#contents)}

## Surrogate Models & PINNs

> Physics-informed neural networks and data-driven reduced-order models for fast PDE solving.

- [lululxvi/deepxde](https://github.com/lululxvi/deepxde) `Python` - Physics-informed neural networks for PDEs. Multi-backend (TF, PyTorch, JAX). Inverse problems, fractional PDEs.

- [mathLab/PINA](https://github.com/mathLab/PINA) `Python` - Physics-Informed Neural networks for Advanced modeling. PyTorch Lightning-based with multi-device training.

- [mathLab/PyDMD](https://github.com/mathLab/PyDMD) `Python` - Dynamic Mode Decomposition. Data-driven reduced-order modeling for fluid dynamics and beyond.

- [NeuroDiffGym/neurodiffeq](https://github.com/NeuroDiffGym/neurodiffeq) `Python` - Neural network solver for ODEs and PDEs. Flexible architecture with native boundary condition handling.

- [NVIDIA/physicsnemo-sym](https://github.com/NVIDIA/physicsnemo-sym) `Python` - Symbolic AI for physics. Physics-informed neural networks with symbolic equation definition.

- [rezaakb/pinns-torch](https://github.com/rezaakb/pinns-torch) `Python` `PyTorch` - Production-ready PINNs in PyTorch. Multi-physics support, inverse problems, uncertainty quantification.

- [sciann/sciann](https://github.com/sciann/sciann) `Python` - Neural networks for scientific computing. Keras-based PINNs with custom loss and constraints.

- [thuml/Neural-Solver-Library](https://github.com/thuml/Neural-Solver-Library) `Python` - Library for advanced neural PDE solvers. Benchmarking Transolver, FNO, and variants on diverse PDE families.

^{[back to top](#contents)}

## Optimization

> Bayesian, topology, and multidisciplinary design optimization.

- [meta-pytorch/botorch](https://github.com/meta-pytorch/botorch) `Python` `PyTorch` - Bayesian optimization in PyTorch. Sequential decision making, multi-objective optimization, batch acquisition.

- [OpenMDAO/OpenMDAO](https://github.com/OpenMDAO/OpenMDAO) `Python` - Multidisciplinary design optimization. NASA-developed. Gradient-based + surrogate-assisted optimization.

- [anyoptimization/pymoo](https://github.com/anyoptimization/pymoo) `Python` - Multi-objective optimization. NSGA-II/III, reference directions, constraint handling, parallelization.

- [dl4to/dl4to](https://github.com/dl4to/dl4to) `Python` `PyTorch` - Deep learning for 3D topology optimization. Autograd + adjoint method for efficient neural optimization.

- [williamhunter/topy](https://github.com/williamhunter/topy) `Python` - Topology optimization with Python. Minimum compliance, heat conduction, mechanism design.

- [mdolab/OpenAeroStruct](https://github.com/mdolab/OpenAeroStruct) `Python` - Aerostructural optimization. VLM aerodynamics + beam FEM structures + ply-level composites.

^{[back to top](#contents)}

## Data Formats & I/O

> Libraries for reading, writing, and converting simulation data across mesh and field formats.

- [nschloe/meshio](https://github.com/nschloe/meshio) `Python` - I/O for mesh formats. Abaqus, CGNS, Gmsh, VTK, XDMF, Exodus, and 30+ more.

- [h5py/h5py](https://github.com/h5py/h5py) `Python` - Pythonic interface to HDF5. Read/write large numerical datasets efficiently.

- [Unidata/netcdf4-python](https://github.com/Unidata/netcdf4-python) `Python` - Python/NumPy interface to NetCDF. Climate, ocean, atmospheric simulation data.

- [CGNS/CGNS](https://github.com/CGNS/CGNS) `C` `Fortran` - CFD General Notation System. Standard for CFD data storage and exchange. HDF5-based.

- [pyvista/pyvista](https://github.com/pyvista/pyvista) `Python` - Read/write VTK formats (VTI, VTP, VTU, VTS, VTR), STL, OBJ, PLY, glTF, and more.

^{[back to top](#contents)}

## Datasets & Benchmarks

> Standardized datasets and benchmarks for training and evaluating scientific ML models.

- [divelab/AIRS](https://github.com/divelab/AIRS) `Python` - AI for science benchmarks. Molecular, protein, climate, physics datasets.

- [Extrality/AirfRANS](https://github.com/Extrality/AirfRANS) `Python` - RANS simulation dataset for airfoils. 1000 simulations with Reynolds-averaged fields (NeurIPS 2022).

- [Mohamedelrefaie/DrivAerNet](https://github.com/Mohamedelrefaie/DrivAerNet) `Python` - Large-scale automotive CFD dataset. 4000+ car designs with drag coefficients and surface fields.

- [i207M/PINNacle](https://github.com/i207M/PINNacle) `Python` - Comprehensive PINN benchmark with 20 PDE problems across difficulty levels (NeurIPS 2024).

- [NASA TMR](https://turbmodels.larc.nasa.gov/) - Turbulence Modeling Resource. Validation cases for CFD turbulence models with experimental data.

- [pdebench/PDEBench](https://github.com/pdebench/PDEBench) `Python` - Benchmarks for scientific ML. Standardized PDE datasets with baseline models.

- [PolymathicAI/the_well](https://github.com/PolymathicAI/the_well) `Python` - Large-scale collection of diverse physics simulations for ML. Fifteen-plus PDE systems (NeurIPS 2024).

^{[back to top](#contents)}

## Learning Resources

> Tutorials, courses, and curated reference lists for computational engineering and AI for science.

- [barbagroup/CFDPython](https://github.com/barbagroup/CFDPython) `Python` - Classic "12 Steps to Navier-Stokes" tutorial. Learn CFD fundamentals with Python step by step.

- [ikespand/awesome-machine-learning-fluid-mechanics](https://github.com/ikespand/awesome-machine-learning-fluid-mechanics) - Curated list of ML applications in fluid mechanics. Papers, code, and tutorials.

- [jxx123/simglucose](https://github.com/jxx123/simglucose) `Python` - Type 1 diabetes simulator. Example of AI-in-the-loop biomedical simulation.

- [maziarraissi/PINNs](https://github.com/maziarraissi/PINNs) `Python` - The foundational PINN reference implementation. Data-driven PDE solutions and discovery (JCP 2019).

- [thunil/Physics-Based-Deep-Learning](https://github.com/thunil/Physics-Based-Deep-Learning) - Comprehensive collection of physics-based deep learning resources. Papers, code links, and tutorials from TUM.

- [WillDreamer/Awesome-AI4CFD](https://github.com/WillDreamer/Awesome-AI4CFD) - Survey of ML for CFD covering data-driven surrogates, PINNs, and ML-assisted numerical solvers.

^{[back to top](#contents)}

## Star History





  

    

    

  





^{[back to top](#contents)}



## Contributing

Contributions welcome! Read the [contributing guidelines](CONTRIBUTING.md) first — adding a tool triggers an [automatic AI-Readiness score](.github/workflows/pr-readiness.yml) on your PR.

[![CC0](https://licensebuttons.net/p/zero/1.0/88x31.png)](https://creativecommons.org/publicdomain/zero/1.0/)

To the extent possible under law, [kimimgo](https://github.com/kimimgo) has waived all copyright and related or neighboring rights to this work.
ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/kimimgo/awesome-ai-cae

Awesome Lists containing this project

README
