Safeguard runs in sovereign and classified environments on customer-owned GPU, with no internet egress, full audit log export, and the entire model family — through Griffin Zero (671B-MoE) — installed on-prem. Built for regulated public-sector workloads and defence supply chains.
Sovereign is not a marketing tier. It is a deployment topology with measurable properties — and we ship the evidence.
Control plane and inference cluster live on customer-owned hardware. No shared tenant boundary, no shared key material, no shared logs.
Bring-your-own KMS, hardware-rooted signing, and a full audit log export every action emits — in JSON and CycloneDX, signed.
Lino at the edge, Eagle in the cluster, Griffin Lite through Griffin Zero (671B-MoE) all run on-prem with no calls to Safeguard's cloud.
Pick the shape that matches your data-residency and trust boundary. The lineup stays consistent end-to-end.
Multi-tenant inference, fastest onboarding, per-tenant isolation at the prompt and KV cache layer.
Single-tenant inference on isolated VPC hardware. No cross-tenant traffic, deterministic latency, SHA-pinned weight attestation.
Customer-controlled VPC, bring-your-own-key encryption, no cross-tenant traffic. Inference plane sits inside your network perimeter.
No internet egress, on-prem GPU, full audit-log export. Suits regulated, classified, and sovereign workloads.
Pre-mapped control narratives, evidence packages on demand, and exports in the formats your auditor already accepts.
Talk to the team about on-prem GPU sizing, signed offline bundles, and the evidence packages your ATO or sovereign-readiness review needs.