No Cloud, No API Key: How to Run a Private AI Assistant on Your Own Hardware
Most AI tools send your queries to someone else's server. This one stays on your machine.
Welcome back.
This week we start building. Over the coming issues we will show you how to run your own AI capability, fully open source, fully in-house, with no internet connection and no running costs.
As always, the latest news and and tradecraft tips from across the OSINT industry are also inside.
Missed last week?
New Vacancy: Associate Analyst, North Quay — London
We have launched the first CTF on our new assessment platform. The challenge is not fictional. It reflects the actual work of the role. Complete it, perform well, and you progress through the application. A CV remains a formality.
If you think you can do the work and have the right to work in the UK, go here.
PS: Hiring? Contact us for a free company account and run the same process.
How to Run a Private AI Assistant on Your Own Hardware
This week we show you how to run an AI assistant entirely on your own hardware. No API key. No cloud. No cost per query. The model runs locally, your data stays with you, and the setup takes around 10 minutes.
The full guide, including chat interface setup and model recommendations, is below.
This is the first instalment in a series on building a local AI capability specifically for OSINT work.
