AI & Data On-Premises
Your datacentre, first-class. The complete platform on hardware you own — cloud-grade operations, confidential computing, and not a byte beyond your walls.
In Your Perimeter
Run the complete platform on hardware you own and operate — data never leaves your datacentre or edge site.
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.
Cloud to Air-Gapped
The same AI OS runs from Azure-consistent on-prem infrastructure through to fully disconnected, air-gapped networks.
On-premises has a reputation for being the punishment option — last year's software, missing features, everything harder than in the cloud. That penalty is a choice vendors make, not a law of nature. This page describes an on-premises deployment that is the same product, current, and operable by a normal team.
Read this if you're required to keep data physically on your own premises, and unwilling to accept a cut-down product for it.
On-premises AI & data means running the entire platform — models, agents, ontology, and analytics — on infrastructure you own and operate, inside your own datacentre or edge location. Data and models stay physically within your perimeter and under your control, with confidential computing and zero-trust enforcement available on your own hardware.
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. The AI OS runs entirely on-premises — the same agents, ontology, and insights you would run in the cloud — keeping data, models, and prompts physically inside your perimeter. From Azure-consistent infrastructure with Azure Local through to fully disconnected, air-gapped networks, you choose how much of the cloud operating model to bring in-house without giving up control.
On-Premises in the Scrydon platform
One integrated, sovereign architecture. Here is where On-Premises sits — highlighted against the full stack it works with.
The AI OS for Humans & AI Agents
Ontology & Semantic Layer, one connected model for your data, knowledge & processes
Combining the best of data lakes, data warehouses and search
AI agents, workflows & automations that execute across your systems
Integrate across A2A, MCP, legacy systems and data sources
Secure domain federation, trusted data sharing, and cross-boundary intelligence
Sovereign Foundations
On-Premises 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.
The full platform, on hardware you control
On-premises deployment runs every layer of the platform inside your own environment. Data and models stay resident in your datacentre or edge location, while you keep a cloud-grade operating model and the same zero-trust and confidential-computing controls used everywhere else.
Data resident in your perimeter — Data, models, and prompts stay physically inside your datacentre or edge site — important for sovereignty and data-residency rules.
Confidential computing on-prem — Hardware-isolated confidential VMs and GPUs on AMD SEV-SNP and Intel TDX keep memory encrypted during execution.
Zero-trust and identity — The same federated identity and zero-trust access model applies on-premises as in the cloud.
Same capabilities everywhere — The same AI OS, ontology, agents, and insights as a cloud deployment — sovereignty never depends on where you run.
Where you can run the platform on-premises
The AI OS runs across on-premises targets, from Azure-consistent infrastructure in your datacentre to fully disconnected networks — so you can match the operating model to your sovereignty and connectivity requirements.
Azure Local — Run the AI OS on Azure Local (formerly Azure Stack HCI) — Azure-consistent infrastructure in your own datacentre, with Trusted-launch VM hardening, and Foundry Local on Azure Local for in-cluster inference.
Air-Gapped — Run the complete platform on fully disconnected networks, with no internet and no external dependencies — sovereignty in its strictest form.
Frequently asked questions
What does running the platform on-premises mean?+
Can I use confidential computing on-premises?+
What is Azure Local and how does it fit?+
How is on-premises different from air-gapped?+
Do on-premises deployments lose any capabilities?+
Explore the platform
Prefer to write? Email hello [at] scrydon.com and we will get back to you.
Partners
