Getting started
Free
We get the Nobodywho tech stack up and running on your servers or edge devices.
- Set-up on your infrastructure, free
- Onboarding, free
Nobodywho
Managed local AI for enterprise
The Nobodywho inference engine runs AI directly on device and servers. Our Assurance Layer helps keep it fast, accurate and up to date, with set up and support with daily operations.
Sovereign AI
Distributed compute
You can read every line of the engine that runs your models. Your team can inspect the code before deploying it.
The engine is yours to run, fork and extend, with no per-token costs. Your deployment keeps running without our service, and without an internet connection.
Nobodywho is built and maintained in Copenhagen and released under the EUPL 1.2, the European Union's own open-source licence, written for European law and compatible with the licences you already use.
Development happens on GitHub, in public. Issues, roadmap and releases are visible to everyone who depends on them.
Product · Deployment model
Two deployment models to match client set ups
| On-device | On-premises | |
|---|---|---|
| Best for | AI inside apps, games, products and machines | Organisation-wide AI shared across teams |
| Runs on | Phones, laptops and embedded hardware | Owned or leased GPU servers |
| Models | Compact open models matched to each device | Larger open models for heavier tasks |
| Scaling | Each new device is a download, with no extra cost per device | One server serves many teams, and costs follow hardware, not usage |
| Connectivity | Works fully offline | Runs inside the organisation's network |
Not sure which fits? Run both: Nobodywho orchestrates work across devices and servers, and the Assurance Layer covers both. Talk to the team
Product · The Assurance Layer
Local AI that keeps performing, without an in-house AI team
The Assurance Layer is how organisations run local AI. Nobodywho handles set-up, model choice, governance and daily operations, on devices, servers or both.
Set up right from day one
Nobodywho installs and configures the engine on the organisation's devices or servers, and onboards the teams who will use it.
Support when issues arise
When something goes wrong, the Nobodywho team picks it up and resolves it, so problems don't land on internal IT.
The right model for each job
Each use case gets a model selected and tuned for it, balancing accuracy, speed and the hardware available.
Always on the best model
Open models improve fast. When a better one is released, Nobodywho assesses it and updates the deployment, so performance improves without a new project.
Governance built in
Restrictions on which models can be used keep every deployment within the organisation's policies and risk appetite.
Tooling built for the organisation
Bespoke tools shaped around existing workflows and systems, so local AI fits how teams already work.
Pricing
Assurance Layer
from 500EUR / month
- Small500 EUR / month
- Medium1,000 EUR / month
- Large2,000 EUR / month
- EnterpriseContact us
Leased hardware
On request
Lease GPU servers from us and run on-premises AI without buying hardware. Price depends on the type of GPUs.
Request a quoteThe numbers that matter when the model runs locally
- Data leaving your infrastructure0bytesWith local deployment, prompts and outputs stay on your hardware.
- Cost per token€0No per-token API fee. You still pay for hardware and any managed service you choose.
- Open models10,000+Deployable on your hardware without vendor lock-in. Any GGUF from Hugging Face.
- Language SDKs7Rust, Kotlin, Swift, Python, Dart, TypeScript, GDScript. Same features in each.
Contact
Nobodywho is a Copenhagen-based company building open-source local AI. Our inference engine runs models on devices and on organisations' own servers, keeping data inside the infrastructure they control.
For teams that need help deploying and operating Nobodywho, we offer onboarding, model selection, monitoring and support for on-device and on-premises deployments.
LocationCopenhagen, Denmark
FAQ
Questions we get asked most often.
What is Nobodywho?
Nobodywho is an open-source inference engine for running large language models on-device or on-premises, built by a Copenhagen-based team for companies that want AI without sending data outside their own infrastructure.
Is Nobodywho open source?
Yes. The core engine is open source under the EUPL 1.2 licence and available on GitHub.
Does the EU AI Act require on-premises deployment?
No. The EU AI Act does not legally mandate on-premises deployment. Nobodywho recommends it for control and simplicity, not as a compliance requirement.
Where is Nobodywho based?
Nobodywho is based in Copenhagen, Denmark, and operates within the EU.
What's the difference between on-device and on-premises AI?
On-device AI runs in your application on individual devices. On-premises AI runs on shared servers controlled by your organisation.
How is Nobodywho's enterprise solution priced?
The self-hosted SDK is free. Assurance Layer plans start at the rates in our pricing section; leased hardware is quoted for your deployment.
What does the Assurance Layer include?
Onboarding, support, model selection and optimisation, and bespoke tooling for on-device or on-premises deployments.
Can I try Nobodywho without talking to sales?
Yes. The open-source SDK is free to run yourself, on-device or on-premises, with no enterprise engagement required. Start with the docs.