# GitHub - strot-ai/Project-STROT: STROT (arXiv:2505.01636): compile-time LLM code synthesis with deterministic, self-routing NLU runtimes

> Compile once with LLM, decide forever with type-safe JSON outputs.
- Title: GitHub - strot-ai/Project-STROT: STROT (arXiv:2505.01636)…
- Summary: Compile once with LLM, decide forever with type-safe JSON outputs. STROT compiles LLM intent into type-safe JSON decisions at compile time, reducing routing…
- Keywords: strot, llm, compile-time, nlu, json, type-safe, arxiv, github, technology, startups, strot-ai, Project-STROT
- Source: GitHub — https://github.com/strot-ai/Project-STROT
- Read time: 1 min
- Topics: strot, llm, compile-time, nlu, json, type-safe, arxiv, github, technology, startups
## STROT Overview
STROT compiles intent once with an LLM to create type-safe JSON decisions for routing records.

> Compile your intent once with an LLM. Then decide on every record forever, classification, scoring, routing, as type-safe json with probabilities and confidence, on your own hardware, at zero marginal cost
## How It Works
STROT uses compile-time schema synthesis to generate a frozen decision model that runs on every record without lldm calls.

> COMPILE (once per intent + schema) intent + sample ─▶ synthesize ─▶ golden gate ─▶ teacher labels ─▶ calibrate
## Key Features
STROT provides type-safe JSON outputs with confidence scores, zero marginal cost, and no structural hallucinations.

> 0% structural hallucination, output is selection + computation over your registry; nothing is generated at runtime
## Performance Metrics
STROT achieves 92.5% routing accuracy versus 74.8% for naive methods, with 86.7% semantic text accuracy.

> Grounded routing accuracy (398 records) 92.5% compiled vs 74.8% naive, the compiler is worth +18pp on the same model
## Installation
Install STROT via pip with options for local or hosted decision models and nlu check points.

> pip install strot-ai # core: pure stdlib
## Why STROT
STROT uses compile-time schema synthesis to eliminate runtime hallucinations and improve decision accuracy.

> Golden-record promotion, artifacts must pass your known answers before they serve
## Key takeaway

STROT compiles LLM intent into type-safe JSON decisions at compile time, reducing routing errors by 18 percentage points compared to naive methods.