When we show Kaldryn Platform, the question is rarely tokens per second. It is where the model runs, and who can see the data.

Kaldryn Platform is on-premise software. It gives a company chat over its own documents, a curated catalog of open models and an OpenAI-compatible API, on infrastructure the organisation controls. Local inference does not require a cloud token.

The problem with “just use the cloud”

For a lot of teams, cloud AI is genuinely fine. But every conversation we had with hospitals, law firms, banks and public agencies across the Nordics followed the same arc: people were getting real value out of consumer AI tools, leadership wanted that capability properly, and every path to it ran through somebody else's infrastructure, under somebody else's terms.

  • The pricing scales with headcount. Per-seat AI subscriptions are a tax on growing.
  • The data leaves. However good the contract is, a prompt typed into a cloud assistant physically departs your premises.
  • The dependency compounds. Models get deprecated, terms get revised, prices change, and your workflows are built on all of it.

For regulated organisations, the second point alone often ends the discussion. Our answer is not “trust us instead”. It's: don't send the data anywhere at all.

What we held the platform to

Three constraints shaped the software:

  1. It runs on infrastructure you control. The organisation chooses the servers. The model, the documents and the console stay there.
  2. A small IT team has to run it. Models, access and evidence sit in one console. There is no separate platform organisation required to start.
  3. Local inference does not depend on a cloud API. Air-gap capable deployment is part of the platform. Network isolation still depends on how you configure it.

The test we kept coming back to: if the deployment cannot reach a cloud model, what still works? For Kaldryn Platform, local inference does. That's the difference between owning your AI and renting it.

What a 30-person firm actually needs

An assistant that knows its documents, a private API for the tools it builds, and governance a lawyer can sign off. That is not a hyperscale problem, and it is not a separate piece of hardware we ship. It is Kaldryn Platform on infrastructure the organisation controls.

The same software is what a small firm deploys and what a larger estate grows into. Sovereignty shouldn't be an enterprise luxury.

What's next

We're publishing more of the thinking behind the platform here on the blog, the engineering trade-offs, what runs well on infrastructure you control in 2026, and what we're hearing from the regulated side of the market. For the deeper technical material, the research hub has the reference architecture and compliance white papers. To see the software: Kaldryn Platform.