Geodesia is a European AI research lab. G-1, our first product, is live — a non-invasive trust layer that wraps any open-source LLM with frontier-grade safety, hallucination control, and a compliance platform that auto-generates auditable documents for the EU AI Act, California SB 942, and 11 other AI frameworks. Runs on your own infrastructure. Zero data egress.
We work on three frontiers: the safety of open-source LLMs, mechanistic explainability of model behaviour, and geometric deep learning. Every output is a peer-reviewed paper, a patent, and a production capability. G-1 is live today. Our next product, GLAD-Manifold, is a physical, geometric reinvention of the Transformer — and the foundation of the AI and reasoning models that come after it.
G-1 wraps your model via vLLM and lifts it to the safety bar of frontier closed models — without changing a single weight. Constitutional Intelligence aligned to European values. A compliance platform that auto-generates auditable documents for the EU AI Act, California SB 942, and 11 other AI frameworks.
Geodesia G-1 mounted on Gemma 4 E2B — a model two orders of magnitude smaller than the closed frontier — matches and beats most frontier models on truthfulness and safety. Tested on HaluEval for hallucination resistance and on our adversarial-safety test set (validation in progress).
The trust layer in detail: architecture, Constitutional Intelligence, the compliance platform, benchmarks, and how it deploys inside your perimeter.
Three research pillars, peer-reviewed work (MuPAX, EVIDENCE, NSP), and what comes after G-1: GLAD-Manifold, our physical, geometric world model.
The full technical whitepaper for compliance officers, Chief Risk Officers, and AI leadership. Architecture, compliance, three enterprise use cases.
