Applied AI · Self-hosted

AI that joins
the team.

KNURZ builds AI products for real work: agent teams that take a task to a reviewed pull request, a meeting participant that remembers what was actually said, and speech that runs on your own terms. One platform — and every piece works on its own.

Self-hosted firstYour models, your keysOIDC identity everywhereGitOps deliveryEvidence on every step

One connected loop

From a sentence in a meeting to a merged pull request.

  1. 01

    Talk

    meeting

    Decisions and commitments are captured as they are spoken — with the original quote attached, across the whole meeting series.

  2. 02

    Frame

    you

    An open point becomes a work item: title, acceptance criteria, repository. A person decides what is worth building.

  3. 03

    Ship

    agentd

    The lead plans and delegates; specialists write the code, run the project’s own tests and open the pull request.

  4. 04

    Merge

    you

    Review and merge stay with people. The pull request is the gate — not a formality.

No lock-in between the pieces: run meeting without agentd, agentd without meeting, and speech under anything that talks the OpenAI audio API.

The platform underneath

Built like infrastructure, not like a demo.

A control plane, not config files

Agents and teams are created and changed in the cockpit. One versioned desired state drives Docker locally and Kubernetes in production — the same contract on both, one agent per container.

Identity is automatic

Every agent gets its own OIDC client, created and removed with the agent. On Kubernetes there are no durable agent secrets at all — short-lived, rotating service-account tokens do the proving.

Delivered by GitOps

Push, tests, image, deployment — on our own Git and Argo CD. What the cockpit shows is what is actually running, down to the version number.

Honest by measurement

Cost per run, evals in the repository, limits written down. When a setup loses to a simpler one, the numbers say so — and the simpler one stays.

See it for yourself.

The platform runs in production on our own cluster — the same way it would run on yours. Start with the piece that fits your problem.