AI & Data on Azure Local
Run the AI OS on Azure Local — Azure-consistent infrastructure operating inside your own datacentre, so your data, models, and prompts never leave your perimeter while you keep cloud-grade operations and confidential computing. We can also run Microsoft Foundry Local's on-device inference on your Azure Local hardware, in connected or fully disconnected mode.
In Your Perimeter
Azure-consistent infrastructure runs in your own datacentre or edge site — data never leaves your control.
Confidential On-Prem
Confidential VMs and GPUs on AMD SEV-SNP and Intel TDX keep data and models encrypted in use, on your own hardware.
Foundry Local
Microsoft Foundry Local's on-device inference runs on your Azure Local hardware — in connected or fully disconnected mode.
AI & data on Azure Local means running AI and analytics workloads on Microsoft's Azure Local (formerly Azure Stack HCI) — Azure-consistent infrastructure deployed in your own datacentre or edge location — so data and models stay physically within your perimeter and under your control, with confidential computing and remote attestation available on your own hardware. The AI OS can also serve models through Microsoft Foundry Local's on-device inference running on your Azure Local hardware, in connected or fully disconnected mode.
Hyperscale cloud is not always an option: data residency rules, sovereignty mandates, latency, or disconnected sites can require AI to run where the data lives. Azure Local brings Azure-consistent infrastructure into your own datacentre. Running the AI OS on Azure Local gives you the operational model of the cloud while data, models, and prompts stay physically inside your perimeter.
AI & Data on Azure Local in the Scrydon platform
One integrated, sovereign architecture. Here is where AI & Data on Azure Local sits — highlighted against the full stack it works with.
The AI OS for Humans & AI Agents to enable your processes
df.plot.bar()
Link your processes, knowledge & data to ontologies.
Unified storage, structured compute, and secure multi-modal data processing.
Autonomous operatives with specialised skills executing tasks across systems.
Sovereign pipelines, federated APIs, and seamless connector meshes.
Secure domain federation, trusted data sharing, and cross-boundary intelligence.
AI & Data on Azure Local in depth
The AI OS only works if it can be trusted. Every layer of the platform rests on a zero-trust infrastructure and identity foundation that operates consistently from fully air-gapped on-premises deployments through to hyperscale cloud environments. Sovereignty is not a feature added on top — it is the condition under which everything else operates.
- Zero-trust architecture: Continuous verification for every request, every user, and every workload — no implicit trust, even inside the perimeter.
- Federated identity: Seamless integration with your existing IdP (SAML, OAuth 2.0, OIDC) for unified, policy-enforced access control.
- Air-gapped deployment: Run the complete platform with no external network dependencies — ideal for defence, critical national infrastructure, and classified workloads.
- Confidential computing: Hardware-level encryption of data in use via AMD SEV-SNP and Intel SGX, protecting workloads even from infrastructure administrators.
Deployment Options: From Air-gapped to Cloud
Deploy the Scrydon platform where it makes sense for you — from air-gapped environments to public cloud — with sovereignty, compliance, and auditability built in.
No data leaves your jurisdiction. No black-box AI. No compromises on control.
This is sovereignty by design.
Azure-consistent AI inside your own perimeter
The AI OS deploys onto Azure Local so the entire AI workload — data, model weights, and prompts — is processed on infrastructure that physically lives in your datacentre or edge location. You keep Azure-consistent operations and tooling without sending sensitive data to a public region.
Azure-consistent stack — Run Azure-aligned infrastructure and services on your own hardware, in your own datacentre or at the edge.
Confidential compute on-prem — Hardware-isolated confidential VMs and GPUs on AMD SEV-SNP and Intel TDX keep memory encrypted during execution.
Remote attestation — Verify the TEE before secrets, keys, or models are provisioned — the same zero-trust gate used in the cloud.
Sovereign key management — You hold the keys and the hardware; Microsoft and administrators cannot read data in use.
Cloud-grade operations without the data leaving your walls
Regulated and sovereignty-conscious organisations often want the operational model of Azure but cannot place sensitive data in a public region. Azure Local resolves the tension: you get Azure-consistent infrastructure, tooling, and confidential computing while data and models stay physically inside your perimeter — the same zero-trust posture the AI OS applies everywhere, from air-gapped on-premises through to hyperscale cloud.
Microsoft Foundry Local on your Azure Local hardware — connected or fully disconnected
The AI OS can serve models through Microsoft Foundry Local running on your Azure Local hardware, inside your perimeter. Foundry Local brings on-device model inference to your datacentre and edge sites, and the AI OS orchestrates it the same way it orchestrates any other model — so you can run it connected to Azure for management and updates, or fully disconnected with no outbound network at all.
On-device inference — Microsoft Foundry Local serves models locally on your Azure Local hardware — no inference call leaves your perimeter.
Connected mode — Operate connected to Azure for centralised management, model updates, and Azure-consistent tooling.
Fully disconnected mode — Run Foundry Local with no outbound network at all — suitable for air-gapped and sovereignty-constrained sites.
Orchestrated by the AI OS — Foundry Local models are governed and orchestrated by the AI OS alongside your data, agents, and ontology.
Microsoft Fabric, Databricks, and Foundry do not run in your datacentre on confidential compute. Our solution does.
The mainstream Azure analytics and AI platforms — Microsoft Fabric, Databricks, and Azure AI Foundry — are cloud SaaS that process your data in public regions on standard, non-confidential compute, exposing it in memory to the cloud operator while in use. The AI OS runs the same class of analytics and AI workloads on Azure Local inside your own datacentre, on confidential VMs and GPUs, so your data, models, and prompts stay within your perimeter and encrypted in use.
Fabric, Databricks, Foundry — Cloud SaaS on standard compute — your data leaves your perimeter and is decrypted in memory in a public region while being processed.
The AI OS on Azure Local — Runs in your own datacentre on confidential VMs and GPUs — data and models stay in your perimeter and encrypted in use, protected from the cloud operator by hardware isolation.
Frequently asked questions
How can I run AI and data on Azure Local?+
What is Azure Local?+
Can you run Microsoft Foundry Local on Azure Local?+
Do Microsoft Fabric, Databricks, and Azure AI Foundry run in my datacentre on confidential compute?+
Can AI workloads use confidential compute on Azure Local?+
Is data protected from Microsoft and administrators on Azure Local?+
How is Azure Local different from running in a public Azure region?+
Does the AI OS run the same way on Azure Local as in the cloud?+
Explore the platform
Email us
Prefer to write? Email hello [at] scrydon.com and we will get back to you.
Partners
Building the future of Data & AI together with leading innovators. Learn more .
