yggy

What makes it different

Most "chat with your data" tools throw a pile of text chunks at a model and hope for the best. yggy does what those tools skip: it turns your cluttered documents and connected systems into a real knowledge graph — with no schema to design and no pipeline to run. Instead of hoping the model guesses right, your knowledge gets structure: entities, facts, and the relationships between them, all kept in sync with the sources they came from.

The way it works is what makes it different. You connect the mess — PDFs, mailboxes, drives, tickets — and yggy builds the graph itself. Every fact keeps its source, so nothing is a black box. Duplicates merge themselves instead of polluting the graph, and you can undo any merge if the automation gets it wrong. The team is blunt about the origin story: they wanted to build knowledge graphs themselves, discovered how much time disappears into data modelling, ontology design and entity matching, and automated the part of graph building that makes people give up.

Then one graph serves everyone: your team in the app, your code through the API, and your agents through MCP. That last piece is the bet — a structured, source-linked graph is exactly what coding agents need to stop hallucinating about your own knowledge. And it is hosted in the EU, with the plain pitch that your knowledge stays yours.

yggy is built by Dominik Müller, Maximilian Pfestorf and Carlos Gienow, and launched on Product Hunt on 21 October 2026. The product is free, and the ask to the community is direct: try to break the graph builder.