Structured generation
A schema and generated skeleton keep resource layouts, shader bindings, and rendering modes synchronized.
AI + WebGPU for mathematical exploration
Create Math and Physics Simulations with AI and WebGPU
Describe a phenomenon—from orbital mechanics and electromagnetism to fluid dynamics and quantum physics—and turn it into an interactive GPU simulation in your browser.
Try a prompt:
Create a schema for an N-body simulation.
From an idea to a running model
A structured workflow for AI-generated simulations
GPUSims handles WebGPU resources, bindings, pipelines, and rendering so the AI can focus on the mathematical model and shader logic.
-
01 · Describe
State the phenomenon
Explain the system, controls, and visual behavior you want to explore.
-
02 · Generate
Create a safe blueprint
AI writes a declarative schema; GPUSims turns it into a matching WGSL skeleton.
-
03 · Run
Execute in the browser
Paste the implemented shader, compile it, and run the GPU simulation interactively.
-
04 · Explore
Inspect and improve
Use errors, numerical readback, and captured images to refine the model.
Why GPUSims is different
More than one-shot code generation
The application gives AI a controlled architecture and gives users observable evidence for debugging and learning.
Observable debugging
Compilation messages, numerical results, and captured images support an iterative correction loop.
Explanation and learning
After a simulation runs, AI can explain the visible phenomena, mathematics, numerical method, and WGSL implementation.
A visual laboratory in your browser
Build, observe, question, and revise
GPUSims supports interactive graphics and GPU computation across many areas of mathematics and physics. Start from an existing example or create a new model from a natural-language request.
- Explore published simulations before writing any code.
- Adjust parameters and inspect numerical readback values.
- Capture the rendering and ask the AI whether the result is plausible.
Begin with one idea
What physical world would you like to build?
Start with a familiar system, inspect what the AI creates, and use the simulation as a path into deeper mathematics and physics.