OKF tool: build, read and query your own Open Knowledge Format

Google publishes the Open Knowledge Format in its Knowledge Catalog repository as an open, vendor-neutral file format. In the version checked on 15 August 2026, the specification is at 0.2. Technically, it is a directory of Markdown files with YAML frontmatter whose concepts link into a graph.

Examples in Google’s repository integrate services including BigQuery. My tool starts earlier: with users who want to create, inspect and query a file bundle without that infrastructure.

That is exactly where my lab experiment comes in. The tool makes OKF usable without you writing Markdown and YAML by hand. Upload once, then structure, see it as a graph and query it.

Create and structure – Concept Library

You upload a bundle as .zip, .md or .json in the OKF v0.2 format. The parser reads the concepts along with their frontmatter — titles, descriptions, tags and body text. Each concept stays a file, exactly as the spec intends, and you edit it in place.

See and understand – knowledge graph

The concepts link to each other through ordinary Markdown links, which turns your bundle into a graph. A force-directed view shows how topics connect and where the links run. It also shows the gaps — the links you would expect but do not yet have. A click on a node opens the concept behind it.

Ask and answer – RAG chat

You ask in plain language across your entire OKF. The chat is instructed to use only the uploaded bundle and displays the associated source concepts. This makes answers auditable, but does not rule out unsupported model output. As of August 2026, the experiment uses Gemini 2.5 Flash.

Why OKF

Google released OKF as a file format, not as a finished platform. The Markdown and YAML files can live in version control next to code and remain readable without a proprietary editor. My current chat is still provider-specific: it uses Gemini 2.5 Flash.

Anyone already working with llms.txt, Obsidian or AGENTS.md and CLAUDE.md knows the pattern. OKF is one possible common form for those file-based knowledge stores. If you work on context engineering, this is where you build the knowledge base an agent draws its context from.

The spec to read up on: Open Knowledge Format on GitHub.

Who it is for

For developers who want to give their AI agent portable context. For data and research teams moving knowledge from a single catalog into readable files. And for anyone who wants model answers to point back to a visible knowledge base.

Status and limits

OKF itself is at version 0.2; the standard is still evolving. My tool is an experiment and grows with it. The chat currently runs on Gemini 2.5 Flash, so answer quality stands and falls with the model and with the cleanliness of your uploads. I build this for my own use and open it up step by step. Feedback is welcome.

Contact

Want to try the OKF tool or have an idea for it? Write to me.