The future of intelligence is distributed.

We're building it.

AI that runs in one place stops in one place.

When AI runs in a single data center, cluster or cloud, and that place goes down or is cut off, everyone who depends on it loses it at once.

Vertexia spreads AI across many machines and sites. If one machine, one site or a whole cluster is lost, the rest keep working.

Dune

Distributed LLM inference for critical AI infrastructure that has to stay available.
Mycelium In development

Mycelium is peer-to-peer AI inference between individuals. It is in development.

Dune pools machines an organization already owns into one cluster that serves language models through an OpenAI-compatible API.

It spreads the work across ordinary machines, with CPUs or GPUs, and keeps running when some of them are lost.

Any machine can take any request and pass it to a copy of the model that is running.
No machine is in charge. The machines find each other on their own, and if one of them or a whole site is lost, the rest keep serving without anyone stepping in.
A request sent to a lost or slow copy is tried again on another, so people get an answer, not an error.
A new model version reaches one copy first, and Dune goes back to the previous version on its own if the new one does worse.
Optional federated learning: each site can improve a model with its own data, and that data never leaves the site.

Critical AI infrastructure has to be robust, resilient and always available, even when part of it fails. Dune is built for that.

Whether you're interested in exploring a partnership or interested in a one-to-one, we'd love to hear from you.

Vertexia's founder is a federated learning researcher in the SPriNT-Ai lab at MBZUAI, and the company builds distributed AI inference with Dune.

Whether you're interested in joining our team or exploring a partnership, or you have a question, we would love to hear from you.