I
On-premise
Your hardware, your building
For especially sensitive data: gateway, apps and local models on your own hardware on site. We help choose and size it, and we run the system.
- Data stays in-house
- Local models
Nº 03 Managed Operations
In the EU cloud.Or at your site.
We deploy and run gateway, apps and local AI models: in ISO 27001 certified data centres in the EU or on-premise in your data centre, including hardware advice, updates and monitoring.
The lighthouse · Series 03
01 On-premise
Your infrastructure. Our operations.
When data must not leave the building, AI comes to you: we install gateway, apps and models in your data centre and keep running them there.
- Runs entirely in your data centre
- Local AI models on your own hardware
- Same endpoint as in the cloud
- Combinable with models from the EU cloud
Your apps & agents
Open WebUI · n8n · …
Your gateway
/v1
On-premise
Local models in-house
EU cloud
Models out of the box
Sensitive cases local, everything else optionally in the EU cloud
02 Local AI models
Local models, deployed and maintained.
From the right GPU hardware to the next model update: we bring open-weight models into your building and keep them running.
- 01
Plan & size
We choose models and hardware to fit your use cases, user numbers and budget.
- 02
Install
Kubernetes, gateway, models and apps: we set everything up in your data centre and connect it to your systems.
- 03
Run & update
Monitoring, updates and new models as soon as they are better or more efficient. Without you having to evaluate them yourselves.
For example models from
Mistral AI
Swiss AI
Qwen (Alibaba)
Meta
Google DeepMind
OpenAI
DeepSeek
03 Deployment options
Operated where your data belongs.
Same platform, same endpoint, same operations. You only decide where it runs, and you can switch later.
II
Your cloud
In your environment, operated by us
Gateway and applications run in your cloud account or data centre. You keep contracts and network rules, we keep things running.
- Your contracts
- Your network rules
III
apertus.ai Cloud
EU, ISO 27001 certified
Your dedicated gateway runs in our European cloud, exclusively in ISO 27001 certified data centres. The fastest start.
- Fastest start
- Dedicated
04 Included in operations
Everything that really takes work after go-live.
Monitoring & alerting
We watch availability, latency and errors and react before your users notice.
Updates & patches
Platform, components and dependencies stay current, including security updates.
New models
We test new models and enable them. You benefit without evaluating them yourselves.
Backups & recovery
Configuration and application data are backed up and can be restored.
Security & access
Hardening, access control and logging to a clear, documented standard.
Support from the team
You talk directly to the people who build and run the system, in German or English.
05 On-premise
Models and your databases: securely connected, inside your network.
When apertus.ai runs on your premises, the MCP gateway connects local models directly to your internal databases, ERP, DMS and file shares. Every access goes through permissions and the audit log, and no request ever leaves your network.
- Models, gateway and data in the same network: nothing leaves
- Permissions per data source, tool and team
- Every access traceable in the audit log
Your network
Employees, apps & agents
Your data sources
- SQL databases
- ERP & CRM
- DMS & file shares
- Wikis & tickets
apertus.ai gateway
AI & MCP, on-premise
Local modelson AI Box, AI Powerhouse or your hardware
Contact 20 minutes, an honest assessment
Roll out AI without giving up control.
Book a short call. We look at your situation and tell you honestly whether and how apertus.ai can help.
What happens in the call
- 1You briefly describe where you use AI today.
- 2Using your case, we show what a dedicated gateway, apps and operations look like.
- 3You get an estimate of effort and cost.
- 4Then you decide, not us.