Service · Systems & Applications
Personal AI Assistants
Secure personal AI assistants, on your own device or in controlled cloud, reachable on the go.
Secure personal assistants, reachable wherever you are. OpenClaw, Hermes Agent, and the new generation of autonomous assistants take on long-running tasks for you. We install, tune, and operate them on your own device or a controlled cloud instance, configured for exactly the balance of freedom and security you want.
The situation
Personal assistants are the fastest way to make AI useful day to day, and the fastest way to hand confidential data to someone else. The interesting question is not whether to use them, but where they run, what they can reach, and how much they may do without asking.
How we work
Where it runs and at what security level
First the decision that determines everything else: your own device, a controlled cloud instance, or both. We establish with you which data may leave that boundary and which may not.
Deliverable
Operating concept with data boundaries and access model
Installation and integration
Setting up the assistant, connecting the tools you already work with, and making it reachable through a messenger of your choice.
Deliverable
Working assistant, reachable from your phone
Autonomy level and guardrails
We tune how much the assistant handles on its own and where it checks back. From pure support to long-running tasks that continue without you.
Deliverable
Tuned autonomy with check-back and abort points
Tuning and operation
Refinement around how you actually work, cost control, and a way to apply changes without the configuration falling apart.
Deliverable
Tuned setup with update and cost control
What you get
- An assistant on your device or in controlled cloud, not on someone else's infrastructure
- Reachable on the go via Telegram, WhatsApp, or Signal
- A deliberately set autonomy level between suggestion and independent execution
- Clear data boundaries and access rights
- A documented setup you can develop further yourself
Engagement
- Duration
- Short. Setup and tuning in a contained effort, then optional ongoing operation.
- Getting started
- A conversation about tasks, data, and the security level you need.
- Who is involved
-
You, for how you work and the autonomy level you want
IT, as soon as company data or systems are connected
- Format
-
Set up together on the device or on your cloud instance
A short introduction rather than a thick manual
On site in Switzerland or remote
Frequently asked
Do the assistants work without the cloud?
Yes. On your own device, or with locally hosted models where confidentiality requires it. Mixed operation works too: sensitive work local, the rest in a controlled cloud.
What about company data and permissions?
As soon as company systems are connected, IT is involved. The assistant works with your existing permissions and sees nothing you are not already entitled to see.
Who owns the code, models, and results in the end?
You do. Code, configuration, and documentation transfer to you in full, in your repositories and your environment. We build so your team can carry on without us.
Where do our data and models run?
In your environment. Your own cloud, your own data centre, or on-premises, in a Swiss or European region on request. Data leaves your environment only for the providers you explicitly approve.
Do you work remotely or on-site?
Both. We are based in Zürich and work on-site across Switzerland; the day-to-day of the engagement works remotely.
Can we start with a small, bounded step?
Yes, and that is the norm. The first slice is deliberately small so something usable exists early and the decision about the next step rests on experience rather than on a plan.