NobodyWho

What are we doing differently? NobodyWho allow you to run LLMs at the front end with no server needed. Watch this short clip of our Co-Founder and CTO Asbjørn Olling explain what makes us different :) #DataSecurity #EdgeAI #LocalLLM #Privacy #OpenSource

NobodyWho now supports Text-to-Speech & Speech-to-Text! 🎉 Give your apps a voice and ears, fully on-device. No internet. No API keys. No usage fees.

The speed and scale at which LLMs are developing gives NobodyWho a much larger play ground - we want to bring local LLMs to any device possible. Hear more from Hans, one of our engineers, on our vision for edge deployment of LLMs 🎉 #EdgeAI #OnDeviceAI #LocalLLM #OpenSource

We are growing the team 🎉 and looking for: 1. A customer success profile (Danish Speaking) 2. A growth marketer Have a look at the job postings and reach out if you want to hear more :) https://lnkd.in/ebwiBpqT https://lnkd.in/e73HjkGd

Keeping your data secure when using AI is fast becoming a business necessity. That is a core business pillar for us here at NobodyWho. Here is our CTO Asbjørn Olling explaining how it all works. Try it in 5 minutes → https://lnkd.in/eYtxaWA2 #GDPR #DataPrivacy #EdgeAI #LocalLLM #OpenSource

Working at scale with AI usually means: access to servers, paying per token, and a growing infrastructure that can scales with every new user. NobodyWho removes that layer entirely. It's an inference engine that runs the newest AI models, small but capable versions, directly on the hardware your users already own: phones, laptops, even smartwatches. No server footprint. No usage fees. No infrastructure to babysit. And because compute lives on the device, your AI scales with your user base does. European and open-source (EUPL 1.2) - watch our video from our CTO Asbjørn Olling to hear more and try it in 5 minutes → https://lnkd.in/efbSpdBv #LocalLLM #EdgeAI #OnDeviceAI #OpenSource #AIInfrastructure

What is open source and why should companies choose it? Most companies start by calling a closed API to run their AI models (e.g. Claude, ChatGPT), sending requests to a third-party server and paying per response. It's like hailing a taxi every time you need to move. Fast to start, but you don't own anything, you can't see under the hood, and if the provider changes pricing or shuts down a model, you're stuck. 🚖 An open source inference engine works differently. Instead of sending requests to someone else's infrastructure, the model runs inside yours (e.g. NobodyWho and Ollama). You own the runtime, you control what happens to your data, and the cost structure is much more in your control. More setup upfront, but you're buying the car, not renting it. 🚗

The EU AI Act is now in force and most organisations infrastructure is not built to comply. The act lays out three obligations: 1️⃣ Human oversight. A qualified person must be able to monitor, interpret, and override the AI system's outputs before they cause harm. 2️⃣ Post-market monitoring. Once deployed, organisations must continuously track how the system performs in real conditions and act on anything that goes wrong. 3️⃣ Data governance. Organisations must know what data trained the model, what data it's processing, and be able to demonstrate both are appropriate and lawful. All three are hard to satisfy when your inference layer runs outside your infrastructure and outside your jurisdiction. That's where NobodyWho sits. EU-sovereign inference that runs on your infrastructure. Visible, inspectable, and in your control. Built for exactly this regulatory environment. #AIAct #EnterpriseAI #DataSovereignty #EUtech

Another shoutout to our Founder & CEO Cecilie Waagner Falkenstrøm who spoke last week at the Connected Women in AI women as one of the 100 Women in AI event 🎉

Our founder & CEO Cecilie Waagner Falkenstrøm was on Go'Morgen Danmark yesterday to talk about #womeninAI with Katrine Bach 🎉 Really cool to see AI and representation are becoming a topics that hit morning TV. Shoutout to Connected Women in AI who are pushing this agenda! Link to full segment in the comments ⬇️