Natural language semiconductor geometry generator powered by LLMs
LLM-to-GDSII pipeline, but semiconductor CAD is niche and validation unclear.

Waitlist-only landing page with zero product to evaluate.
Non-English speakers using AI tools
LLM-to-GDSII pipeline, but semiconductor CAD is niche and validation unclear.
Static scanner catches prompt injections in code before runtime, unlike runtime guards.
This repo turns agent loops into tiny, explicit instructions (LF, LI, APP, INF, INT, BGT, OUT) so you can compose reasoning as discrete micro-prompts instead of one huge monolith. The example VIBE_CONTROLLER shows concrete ops for cognition, safety checks and branching — a neat way to formalize ReAct-style loops. It’s a clever, researchy DSL with a Rust interpreter, but it’s early-stage and sits in a crowded space of agent frameworks (needs runtime benchmarks, integrations and real-world demos to move beyond an interesting experiment).
Treats model calls as first-class runtime constructs using $..$ blocks with declared-type enforcement, which makes it unusually ergonomic to intermix deterministic code and LLM-powered operations. The Polars-backed dataframe injection that emits structured JSON summaries instead of raw table dumps is a clever, practical touch for token efficiency; neat sandbox for language designers, but explicitly a hobby/toy project rather than something to deploy.
10x token efficiency + pixel-perfect determinism fixes LLM PDF generation without the HTML chaos.
Non-deterministic compilation via LLM — every natural language programming attempt has failed for decades.