Ontologize your business.
We build the platform and do the work: migrate your data, model it, and connect it to one system you own.
Data becomes a model. The model runs the business. The business generates more data.
One place where all your objects, relationships and logic live.
Everything has a type.
Objects and relationships are typed and editable at runtime — no migrations.
Nothing is ever deleted.
Full history is automatic. Query any moment in the past exactly as it stood.
AI proposes, you decide.
Agents surface proposals. Nothing commits without your approval.
It's yours to run.
Self-hosted, no subscription, no lock-in.
Every conversation with an LLM starts from zero. Your ontology never does.
Inside the platform.
Connect any source — REST APIs, CSVs, ERP exports, databases — as a starting point into the same pipeline. Click to zoom.
Define SQL transforms and materialize clean, typed entities from raw source data into the ontology. Click to zoom · arrows to browse.
Every object type is defined at runtime — properties, relationships and interfaces — no schema migrations. Actions attach directly to the type. Click to zoom · arrows to browse.
Browse and filter every entity in the ontology. Click through to the full detail view — all properties, linked entities and the complete edit history. Click to zoom · arrows to browse.
A force-directed investigation canvas. Expand any entity to see its neighbours, filter by link type, save named layouts and share deep links with your team. Click to zoom.
Workspace functions run server-side TypeScript with full ontology access. Wrap one in an Action to make it callable — trigger it manually, from a workflow, or from the AI assistant. Click to zoom · arrows to browse.
Visual workflow builder with triggers, LLM steps, checkpoints and actions. Human-in-the-loop gates pause execution until a reviewer approves — nothing commits without sign-off. Click to zoom · arrows to browse.
The built-in AI assistant has full access to the ontology. Ask it to research a customer on the web, then watch it write the findings back — new properties, new entities, new links — all tracked in the change log. Click to zoom · arrows to browse.
Generate a fully typed TypeScript client from your ontology in one command. Build internal tools, dashboards, or integrations on top — typed objectSet(), runAction() and traversal out of the box. Click to zoom · arrows to browse.
From raw data to running agents.
We migrate and structure your data, then build on top of it.
Most companies have data that isn't usable in modern AI tools and workflows. We take on a small number of projects at a time to fix that: structuring what you have, migrating it to the ontology, and building whatever you need on top.
Map the model
Understand how the business works: the key objects, how they relate, where the data lives today.
Migrate the data
Pull data out of scattered systems and land it cleanly, and usably, in the ontology.
Build on it
Implement the actions, workflows and agents that make the data useful day to day.
In active development.
The core platform is built and working locally. We're preparing to take on the first paying implementation projects in the second half of 2026.
Have a data problem worth solving?
Based in Sweden. Available remotely.