Aura-State: Formally Verified LLM State Machine Compiler

[rohanmunshi08]

I noticed a pattern: every LLM framework today lets the AI manage state and do math. Then we wonder why pipelines hallucinate numbers and break at 3 AM.

I took a different approach and built Aura-State, an open-source Python framework that compiles LLM workflows into formally verified state machines.

Instead of hoping the AI figures it out, I brought in real algorithms from hardware verification and statistical learning:

CTL Model Checking: the same technique used to verify flight control systems, now applied to LLM workflow graphs. Proves safety properties before execution.

Z3 Theorem Prover: every LLM extraction gets formally proven against business constraints. If the total ≠ price × quantity, Z3 catches it with a counterexample.

Conformal Prediction: distribution-free 95% confidence intervals on every extracted field. Not just "the LLM said $450k" but "95% CI: [$448k, $452k]."

MCTS Routing: Monte Carlo Tree Search (the algorithm behind AlphaGo) scores ambiguous state transitions mathematically.

Sandboxed Math: English math rules compile to Python AST. Zero hallucination calculations.

I ran a live benchmark against 10 real-estate sales transcripts using GPT-4o-mini: → 100% budget extraction accuracy ($0 mean error) → 20/20 Z3 proof obligations passed → 3/3 temporal safety properties proven → 65 automated tests passing

The gap between "it usually works" and "it provably works" is smaller than people think.

Would love feedback from anyone building production LLM systems; what would you want formally verified?

https://github.com/munshi007/Aura-State

[ozozozd]

This is interesting and I would appreciate if you could elaborate with a few examples, and perhaps mention what inspired this, and/or what’s similar and/or analogous to your method.

[aristofun]

Couple of simplified examples for us, mere mortals, not mathematicians would be nice.