Private AI on the hardware you already own.
A self-contained AI node: local inference over GGUF models on CPU, Metal or CUDA, an OpenAI-compatible API so existing code works unchanged, and a mesh that pools the machines on your network — with the governance a regulated organisation needs built into the same binary.
Role-based access, directory sign-in, a PII scanner, access-controlled retrieval and a tamper-evident audit ledger — no cluster, no platform team.
Nodes discover each other on a LAN or private overlay and pool capacity, so older hardware contributes instead of being replaced.
An OpenAI-compatible API: client code written for a cloud provider runs against your own machine unchanged.
Each request's route is decided and recorded; with no remote configured everything stays local, however large.
What each tier unlocks, generated from the same catalogue the application gates against — so the feature list here is exactly what the software enforces. Pricing is announced at launch.
| Plan | Price | Includes |
|---|---|---|
| Community | Included |
|
| Professional | At launch |
|
| Team | At launch |
|