Building the future of European AI infrastructure from the Nordics
NobodyWho is an on-device inference engine that runs LLMs locally on any device. Developers can embed fast, scalable models into mobile and desktop apps with just a few lines of code. Because inference runs entirely on-device, no servers are required and applications scale automatically with user adoption. This significantly reduces both costs and overall footprint.
The result is offline, privacy-preserving and sustainable AI. The library is open source under EUPL 1.2 and is free for both individuals and companies.
We're a small team excited about on-device AI
Our headquarter is in Copenhagen, Denmark. We're always on the lookout to add kind, thoughtful, and exceptionally talented individuals to our team. Drop us a line if you're motivated by the intersection of individual developer experience and global scale at info@nobodywho.ai
Milestones
-
May 2023
Project started as "Nimbus2000", an inference engine for Godot written in the Nim language. Desktop only
-
January 2024
Renamed to "NobodyWho"
-
August 2024
Rewritten in Rust
-
July 2025
Runs on Android
-
October 2025
Runs on iOS
-
November 2025
Inference engine is available for Python
-
December 2025
€2M fundraising to challenge Big Tech's cloud AI
-
February 2026
Inference engine is available for Flutter
-
April 2026
Inference engine is available for React Native
-
May 2026
Inference engine is available for Swift