Skip to content

Principia

Principia is a multi-agent pipeline built on Gemini that translates natural language into mathematically rigorous, visually stunning numerical simulations.

Code Video Cerebral Valley

Core trick

A critic agent runs SymPy dimensional-homogeneity checks on the formalized equations and sends failures back for revision before code generation.

Tags

scienceagents

Description

Principia is a multi-agent pipeline built on Gemini that translates natural language into mathematically rigorous, visually stunning numerical simulations. To overcome LLM hallucinations, Principia introduces a "System 2" workflow with a self-correcting loop. First, a Formalizer agent extracts strict math (ODEs, PDEs, SDEs, Quantum mechanics) from user prompts. Then, a Critic peer-reviews it, running dimensional homogeneity cross-checks using SymPy via a Python execution tool. If flawed, the Critic forces the Formalizer to revise using contextual feedback. Once verified, an Execution agent compiles the math into SciPy solvers and Matplotlib rendering scripts. Wrapped in a sleek Next.js UI inspired by Google Antigravity, Principia actively reasons about physics to bring complex concepts to life, paving the way for AI-driven scientific discoveries.
realYungi/Principia-AI★ 00 forksPythonApache-2.0Created Mar 7, 2026 · last push Mar 7, 2026

README excerpt

<div align="center">
  <img src="https://img.shields.io/badge/Gemini_3_Pro-Black?style=for-the-badge&logo=google&logoColor=white" alt="Gemini 3 Pro" />
  <img src="https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white" alt="Python" />
  <img src="https://img.shields.io/badge/FastAPI-009688?style=for-the-badge&logo=fastapi&logoColor=white" alt="FastAPI" />
  <img src="https://img.shields.io/badge/Next.js-000000?style=for-the-badge&logo=next.js&logoColor=white" alt="Next.js" />
  
  <br />
  <br />
  
  <h1 align="center">🔮 Principia</h1>
  <p align="center">
    <strong>Mathematically bulletproof physical models, generated from natural language.</strong>
  </p>
  <p align="center">
    <i>Built for the Gemini Hackathon: "Bring Something New to Life"</i>
  </p>
</div>

---

## 🚀 The Goal: Solving LLM Physics Hallucination

Large Language Models are incredibly creative but inherently lack strict mathematical and logical rigor ("System 2" thinking). When asked to model complex physical phenomena or write simulation code directly, they frequently hallucinate equations, dimensionally mismatch variables, or create physical impossibilities. 

**Principia solves this.** 

We brought "System 2" thinking into the loop *before* any code is generated. By combining the vast reasoning capabilities of **Gemini 3** with the strict, deterministic algebraic engines of **SymPy**, Principia takes a natural language description of a physical system and rigorous

Team