# peterdsharpe/AeroSandbox

Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory design, and much more.

Repository: https://github.com/peterdsharpe/AeroSandbox
Canonical: https://ross.abutalabs.com/products/aerosandbox
Homepage: https://peterdsharpe.github.io/AeroSandbox/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: aerodynamics, airplane, cfd, mdo, aircraft-design, aerospace, optimization, vlm, aerodynamic-analysis, xfoil, analysis, 3d-panel, python, aircraft, automatic-differentiation, mdao, aerospace-engineering, simulation
Last push: 2026-07-05T14:54:17+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 35, longevity 100
- inputs: {"age_days": 2667, "days_push": 59, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1315, forks 205 (observed 2026-08-28T04:04:20.702869+00:00)

## What it is
AeroSandbox is a Python library for designing and optimizing aircraft and other engineered systems using automatic differentiation. It provides differentiable physics models for aerodynamics, structures, propulsion, and trajectory analysis, feeding exact gradients to nonlinear optimizers like IPOPT.

## Use cases
- optimize an aircraft's aerodynamics, structures, and propulsion simultaneously
- analyze airfoil performance with differentiable models like NeuralFoil
- run vortex-lattice or lifting-line aerodynamic analysis on a wing
- size a solar-electric aircraft or RC glider from scratch
- solve large multidisciplinary design optimization problems with thousands of variables
- compute stability derivatives for a whole aircraft
- model propeller, electric motor, or turbofan performance in an optimization loop

## When to choose
- you need gradient-based optimization of coupled aerospace physics models
- you want fast, differentiable aerodynamics analysis in pure Python
- you're doing conceptual or preliminary aircraft design and want design closure in seconds
- you prefer NumPy-style syntax without hand-deriving gradients

## When to avoid
- you need high-fidelity RANS CFD or detailed CAD-level structural FEA
- you're not doing optimization and just need a standalone GUI-based analysis tool
- you work outside Python or need certified/validated industrial aerospace tooling

## Facets
- artifact type: library
- maturity: active
- function: simulation, math, machine-learning
- domain: simulation
- platform: python, cross-platform
- tags: aircraft-design, aerodynamics, automatic-differentiation, multidisciplinary-design-optimization, vortex-lattice-method, xfoil, cfd, propulsion, trajectory-optimization, mdao, optimization, aerospace-engineering, algorithms, engineering

## Member repositories
- peterdsharpe/AeroSandbox (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.702869+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:48:42.856676+00:00, confidence not recorded.
  - readme: https://github.com/peterdsharpe/AeroSandbox (fetched 2026-08-28T04:04:20.702869+00:00, sha 3341de6bb2a5)
  - homepage: https://peterdsharpe.github.io/AeroSandbox/ (fetched 2026-08-29T12:07:15.361500+00:00, sha acdc7aa9f45e)
  - registry_pypi: https://pypi.org/pypi/aerosandbox/json (fetched 2026-08-29T12:07:15.370952+00:00, sha a5641936cbfa)
- Data as of 2026-08-30T08:39:29.467469+00:00.