Run models on your own hardware.
Nobodywho
The Nobodywho inference engine runs AI on devices and on your own servers. Our Assurance Layer helps keep it fast, accurate and up to date, with support from setup through daily operation.
Choose on-device or on-premises AI. The Assurance Layer supports either deployment.
Text, vision, speech and search, built on llama.cpp and ONNX.
Check arguments against each function's schema.
Pick a model and hardware configuration for each device.
Rust, Kotlin, Swift, Python, Dart, TypeScript and GDScript.
Benchmark models and serving setups for your workload.
Integrate Slack, email, CRM and internal systems.
Set permissions, approvals and audit trails.
Connect existing systems through vLLM.
Measure quality and performance against real data.
Select, tune, fine-tune and retrain models as needs change.
Route work between devices, servers and the cloud when needed.
Bespoke tools, 24/7 support and training for your team.
Sovereign AI
Distributed compute
Open Source
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. Your deployment can keep running without our service.
Nobodywho is 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.
Free
We get the Nobodywho tech stack up and running on your servers or edge devices.
from 500EUR / month
On request
Lease GPU servers from us and run on-premises AI without buying hardware. Price depends on the type of GPUs.
Request a quoteNobodywho 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
Questions we get asked most often.
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.
Yes. The core engine is open source under the EUPL 1.2 licence and available on GitHub.
No. The EU AI Act does not legally mandate on-premises deployment. Nobodywho recommends it for control and simplicity, not as a compliance requirement.
Nobodywho is based in Copenhagen, Denmark, and operates within the EU.
On-device AI runs in your application on individual devices. On-premises AI runs on shared servers controlled by your organisation.
The self-hosted SDK is free. Assurance Layer plans start at the rates in our pricing section; leased hardware is quoted for your deployment.
Onboarding, support, model selection and optimisation, and bespoke tooling for on-device or on-premises deployments.
Yes. The open-source SDK is free to run yourself, on-device or on-premises, with no enterprise engagement required. Start with the docs.