Google recently introduced the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format. This is a vendor-neutral, agent- and human-friendly standard for representing the metadata, context, and curated knowledge that modern AI systems need.

As published, OKF v0.1 represents knowledge as a directory of markdown files with YAML frontmatter, with a small set of agreed-upon conventions that let wikis written by different producers be consumed by different agents without translation.

That's it. No complex compression scheme, no new runtime, no required SDK. A bundle of OKF documents is:

  • Just markdown — readable in any editor, renderable on GitHub, indexable by any search tool

  • Just files — shippable as a tarball, hostable in any git repo, mountable on any filesystem

  • Just YAML frontmatter — for the small set of structured fields that need to be queryable: type, title, description, resource, tags, and timestamp

How OKF works: The design in one screen

Each concept document has a small block of YAML front matter for structured fields and a markdown body for everything else:

Concepts link to each other with normal markdown links, turning the directory into a graph of relationships that is richer than the parent/child links implied by the file system. Bundles can optionally include index.md files (for progressive disclosure as agents navigate the hierarchy) and log.md files (for chronological history of changes).

The full v0.1 specification (including conformance criteria, cross-linking rules, and the small number of reserved filenames) fits on a single page.

Three principles behind the design

1. Minimally opinionated. OKF requires exactly one thing of every concept: a type field. Everything else (e.g., what types exist, what other fields to include, what sections the body has) is left to the producer. The spec defines the interoperability surface, not the content model.

2. Producer/consumer independence. OKF cleanly separates who writes the knowledge from who consumes it. A bundle hand-authored by a human can be consumed by an AI agent. A bundle generated by a metadata export pipeline can be browsed in a visualizer. A bundle synthesized by one LLM can be queried by another. The format is the contract; the tooling at each end is independently swappable.

3. Format, not platform. OKF is not tied to any specific cloud, database, model provider, or agent framework. It will never require a proprietary account or SDK to read, write, or serve. We're publishing it as an open standard because the value of a knowledge format comes from how many parties speak it, not from who owns it.
Reference - https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing