# KAON2 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/kaon2
> Markdown URL: https://aitinkerers.org/technologies/kaon2.md
> Technology record last updated: 2026-05-05T00:56:17Z
> Generated: 2026-09-21T06:46:11Z

KAON2 is a high-performance reasoning engine for OWL-DL and DL-safe rules that leverages deductive database techniques for efficient query answering.

Developed at the University of Karlsruhe, KAON2 optimizes OWL-DL reasoning by reducing ontologies to disjunctive datalog programs. This approach shifts the computational burden to a dedicated inference engine capable of handling large-scale ABoxes stored in relational databases. By implementing the SHIQ(D) logic fragment, KAON2 provides a robust framework for SPARQL query processing and rule-based reasoning (specifically DL-safe rules) without the memory overhead common in traditional tableau-based reasoners.

- Official technology site: https://on-top.org/kaon2/
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Agents: Thinking Fast and Slow](https://bengaluru.aitinkerers.org/talks/rsvp_PZxSQjRYFmQ)

For AI agents to operate seamlessly across diverse applications, they must dynamically expand context to retrieve relevant information and converge on the right actions without relying on predefined workflows. This talk explores how we enable agents to adapt to new environments, effectively acting as the UI for AI to navigate and interact with software systems. We'll cover: Context Expansion: Dynamically retrieving and structuring relevant knowledge for better decision-making. Convergence on Demand: Iterative reasoning strategies that refine actions through multi-step execution. Ontology-Guided Reasoning: Leveraging structured knowledge to improve accuracy and decision reliability. Real-World Applications: How these techniques allow agents to orchestrate complex workflows, break API limitations, and drive automation across SaaS tools. By combining structured retrieval with adaptive reasoning, we move beyond static integrations—unlocking AI agents that can truly think in motion and execute with precision.

- Event context: AI Tinkerers - Bengaluru - January Meetup — 2025-01-23 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_PZxSQjRYFmQ

## Related Technologies

- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos
- [APIs](https://aitinkerers.org/technologies/apis) ([Markdown](https://aitinkerers.org/technologies/apis.md)) — 19 public demos
- [FaCT++](https://aitinkerers.org/technologies/fact) ([Markdown](https://aitinkerers.org/technologies/fact.md)) — 1 public demo
- [HermiT](https://aitinkerers.org/technologies/hermit) ([Markdown](https://aitinkerers.org/technologies/hermit.md)) — 1 public demo
- [OWL](https://aitinkerers.org/technologies/owl) ([Markdown](https://aitinkerers.org/technologies/owl.md)) — 1 public demo
- [Pellet](https://aitinkerers.org/technologies/pellet) ([Markdown](https://aitinkerers.org/technologies/pellet.md)) — 1 public demo
- [Protege](https://aitinkerers.org/technologies/protege) ([Markdown](https://aitinkerers.org/technologies/protege.md)) — 1 public demo
- [RDF](https://aitinkerers.org/technologies/rdf) ([Markdown](https://aitinkerers.org/technologies/rdf.md)) — 2 public demos
- [SaaS tools](https://aitinkerers.org/technologies/saas-tools) ([Markdown](https://aitinkerers.org/technologies/saas-tools.md)) — 1 public demo
- [SPARQL](https://aitinkerers.org/technologies/sparql) ([Markdown](https://aitinkerers.org/technologies/sparql.md)) — 2 public demos