Google Cloud Introduces the Open Knowledge Format (OKF)
— by Vivax
Google Cloud has introduced the Open Knowledge Format (OKF) — an open, vendor-neutral specification that turns the emerging 'LLM-wiki' pattern into a…
On June 13, 2026, Google Cloud's data analytics team — Sam McVeety and Amir Hormati — introduced the Open Knowledge Format (OKF), an open specification that formalizes the emerging 'LLM-wiki' pattern into a portable, interoperable format. As foundation models keep improving, the limiting factor is increasingly not the model but the context it can draw on. OKF is a vendor-neutral, agent- and human-friendly standard for representing the metadata, context, and curated knowledge that modern AI systems — especially agentic ones — need to produce accurate, actionable results.
The most striking thing about OKF is how little it invents. As published, OKF v0.1 represents knowledge as a directory of Markdown files with YAML frontmatter, plus a small set of agreed-upon conventions that let wikis written by different producers be consumed by different agents without translation. 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), and just YAML frontmatter for the small set of structured fields that need to be queryable — type, title, description, resource, tags, and timestamp.
If you have used Obsidian, Notion, Hugo, or any of the LLM-wiki patterns that have emerged over the past year, the shape will feel familiar. What OKF adds is the small set of conventions needed to make those patterns interoperable — so curated knowledge can be produced once and consumed by many different agents and tools. The full specification is published openly on GitHub, making it easy for any organization to adopt the format, contribute to it, or build tooling around it.
For Vivax, this matters because grounded clinical AI is only as good as the knowledge it can access. A portable, open standard for sharing curated medical context — guidelines, protocols, and structured domain knowledge — fits naturally with how we think about grounding our clinical world models and agents. An open knowledge format that travels cleanly between systems is a step toward the interoperable, trustworthy data sharing that healthcare AI ultimately depends on.