Guide
The Open Knowledge Format (OKF), explained
The Open Knowledge Format (OKF) is an open specification from Google Cloud, published in June 2026, that represents knowledge as a directory of markdown files with YAML frontmatter. It formalizes the LLM-wiki pattern into a portable, vendor-neutral format that humans can read and AI agents can parse without an SDK. This guide covers what OKF is, how the format works, a worked example, how it compares to llms.txt, and how to add a bundle to your own site.
By WitsCode. Published June 18, 2026. Last updated June 18, 2026.
What is the Open Knowledge Format?
The Open Knowledge Format is an open, human- and agent-friendly format for representing knowledge: the metadata, context, and curated insight that surround data and systems. Google Cloud's Data Cloud team, led by Sam McVeety and Amir Hormati, published OKF v0.1 in June 2026 in the public Knowledge Catalog repository. It formalizes the LLM-wiki pattern that Andrej Karpathy described (a markdown knowledge base an agent reads and maintains like code) into a portable, vendor-neutral standard.
The point is producer and consumer independence. A bundle hand-written by a person can be read by an AI agent. A bundle generated by one tool can be browsed in another. Because it is just markdown, just files, and just YAML frontmatter, anyone who can open a file can read it and anyone who can clone a git repo can ship it. OKF is the file format agents read, not a service you call.
Where OKF fits: the agent-readable web stack
OKF is the top floor of a stack of conventions for making a site legible to machines. Each layer hands an agent a little more.
robots.txt and sitemap.xml
Tells a crawler which URLs exist and may be fetched.
llms.txt
Points an agent at the handful of pages worth reading.
AGENTS.md and CLAUDE.md
Tells a coding agent how to behave inside one repository.
Open Knowledge Format
Hands the agent the knowledge itself, as a portable graph of typed concepts.
A sitemap says which pages exist. llms.txt and AGENTS.md or CLAUDE.md point and instruct. OKF goes one floor higher and hands over the content itself, as a graph an agent can traverse. For the full picture of making a site legible to AI, see our guide to AI search optimization.
Why Google built OKF
In most organizations, the knowledge an AI agent needs lives in fragmented surfaces: metadata catalogs with their own APIs, wikis and shared drives, code comments and docstrings, and the heads of a few senior engineers. When an agent has to answer a question like how weekly active users are computed from the event stream, it reassembles the answer from scattered, mutually incompatible places, every time.
Google's argument is that the fix is not another knowledge service. It is a format: a way to represent knowledge that anyone can produce without an SDK, anyone can consume without an integration, that survives moving between systems, lives in version control next to the code it describes, and is readable by humans and parseable by agents in the same file. That format is OKF.
The OKF format in depth
A bundle is a directory tree of markdown files. This site ships one, and it looks like this.
knowledge/
├── index.md
├── services/
│ ├── index.md
│ ├── web-application-development.md
│ └── ai-search-optimization.md
├── pipelines/
│ ├── index.md
│ └── lead-pipeline.md
└── log.mdEach concept is one .md file. The concept id is its path with the .md removed, so the file's location is its identity. A YAML frontmatter block carries the structured fields, and the body is normal markdown.
---
type: Service
title: AI search optimization
description: Get a brand cited by ChatGPT, Perplexity, and Google AI Overviews.
resource: https://witscode.com/ai-search-optimization
tags: [seo, aeo, ai-search]
timestamp: 2026-06-18T09:00:00Z
---
# What it is
Structuring content and entities so large language models cite you.
# Related
Pairs with [technical SEO](/services/technical-seo.md) for crawlability.The only required field is type, a short non-empty string naming the kind of concept. The recommended fields are title, description, resource, tags, and timestamp, and producers may add any keys they like. Two filenames are reserved: index.md lists a folder's concepts for progressive disclosure, and log.md records dated changes.
# Knowledge bundle
## Services
* [Web application development](/services/web-application-development.md) - custom web apps
* [AI search optimization](/services/ai-search-optimization.md) - get cited by AI
## Pipelines
* [Lead pipeline](/pipelines/lead-pipeline.md) - how website leads reach the CRMInternal links are the important part. A link from one concept to another is a directed edge, so the directory becomes a graph. An agent does not just learn what each concept is, it learns how they sit relative to each other, which is most of what understanding a system actually means.
How agents read an OKF bundle
OKF separates two roles. Enrichment agents write into a bundle, drafting concepts from a database, a codebase, or a catalog and adding citations and schemas. Consumption agents read and traverse it. Because the contract between them is just files, neither has to know anything about the other.
A consumption agent typically starts at the root index.md, reads the entries it needs, and follows links deeper, a pattern Google calls progressive disclosure. This is the same instinct behind a shared markdown library that agents read and update over time, which is where production AI agents and MCP servers are heading: less re-deriving the same facts, more reading a curated source of truth.
How to add OKF to your website and WordPress
You add OKF by publishing a bundle alongside your site. There are three common paths.
Pick the knowledge worth sharing
Schemas, metric definitions, runbooks, join paths, product facts, FAQs. The context an agent keeps re-deriving from scratch.
Write each concept as one markdown file
Add a YAML frontmatter block with a type field at minimum. Put the detail in the body as normal markdown.
Link concepts and add an index.md
Cross-link related concepts so the bundle becomes a graph, and add an index.md so an agent can navigate the hierarchy.
Host the bundle at a stable path
A git repo, a tarball, or a folder served at a URL such as /okf/ on your domain.
Validate it
Run the bundle through a conformance validator so any tool can consume it, pass or fail.
On WordPress
The fastest route is a free OKF plugin that turns your published posts and pages into a bundle, serves it at /okf/, and rebuilds it whenever you publish or edit, so it never goes stale. That gets you a valid bundle in minutes. The catch is that an automatic export gives every post the same generic type and no real relationships, which is the opposite of what makes a bundle useful. The value is in typed concepts (a Service, a Metric, a Runbook) linked to each other the way they actually relate, which a plugin cannot decide for you. The same is true whether you run WordPress, headless, or a custom web app.
Done properly
We make your site agent-ready
We map your real entities to typed OKF concepts, link them into a graph, generate the bundle, and validate it so any agent can read it. Then we measure whether AI search actually picks you up. It is the same AI search optimization work, with OKF as one more surface.
OKF vs llms.txt, AGENTS.md, and CLAUDE.md
These conventions solve different problems. llms.txt is a pointer, AGENTS.md and CLAUDE.md are instructions, and OKF is the portable knowledge itself.
| Format | What it is | Scope | Who reads it |
|---|---|---|---|
| OKF | A directory of typed markdown concepts | A whole knowledge base | Any agent or tool, across orgs |
| llms.txt | A single file at a site root | One pointer list | Web crawlers and LLMs |
| AGENTS.md, CLAUDE.md | An instructions file in a repo | One repo or agent | The coding agent in that repo |
Is OKF worth it? An honest take
First, clear up the common myth: OKF is not an SEO ranking signal. Google's search systems do not fetch a bundle from your site and rank you on it. It is an internal knowledge format for agents, not a web publishing signal. A bundle will not move your rankings this week, or next week.
It is also early. Google calls v0.1 a starting point, not a finished standard. The spec is deliberately lenient (broken links and unknown types are tolerated), which buys resilience as a wiki grows but means quality varies a lot between bundles. And an agent-updated knowledge base is a real attack surface: if an agent writes from untrusted input, a bundle becomes a vector for indirect prompt injection, so what you let write into it matters.
The honest case for adopting now is the schema-markup case from a decade ago. It is cheap to ship, it makes your knowledge legible to the agents and answer engines that are starting to field questions about you, and shipping early is how you learn the format before it matters. A small, well-typed, validated bundle beats a large auto-generated one. If you ship anything, ship that.
Validate your OKF bundle
A bundle is only useful if any tool can read it, so check it against the spec before you publish. WitsCode maintains a free, open-source conformance suite and validator that tells you, pass or fail, whether a bundle follows the Open Knowledge Format.
Open Knowledge Format FAQ
What is the Open Knowledge Format?
The Open Knowledge Format (OKF) is an open specification from Google Cloud, published in June 2026, for representing knowledge as a directory of markdown files with YAML frontmatter. It formalizes the LLM-wiki pattern into a portable, vendor-neutral format that humans can read and AI agents can parse without an SDK. Its only required field is type, so any tool that can read files can read an OKF bundle.
Who created OKF and when?
Google Cloud's Data Cloud team created the Open Knowledge Format. Tech leads Sam McVeety and Amir Hormati announced OKF v0.1 in June 2026, and the specification lives in the public Knowledge Catalog repository on GitHub. It is an open, vendor-neutral format, not a hosted Google product.
Does OKF help SEO or improve my Google rankings?
No. OKF is not a ranking signal and Google's search systems do not read a bundle from your site to rank it. It is an internal knowledge format for AI agents, not a web publishing signal. The value is in giving agents and answer engines clean, structured knowledge to read, which is a different goal from ranking blue links.
What does an OKF bundle look like?
A bundle is a directory of .md files. Each concept file opens with a YAML frontmatter block (a required type field, plus optional fields like title, description, resource, tags, and timestamp) followed by a normal markdown body. Reserved files index.md and log.md list contents and record changes. Internal links turn the directory into a graph of related concepts.
How do I add OKF to my website?
Write your key knowledge as markdown concept files with a type in the frontmatter, link them together, add an index.md, and host the bundle at a stable path such as /okf/ or a git repo. Then validate it with a conformance checker. On WordPress you can use a plugin that generates and serves the bundle automatically.
How do I add OKF to WordPress?
There is a free Open Knowledge Format plugin that turns your published posts and pages into a bundle, serves it at /okf/, and rebuilds it whenever you publish or edit. That gets you a valid bundle fast. To make it genuinely useful, give your concepts real types and relationships rather than one generic type per post, which is the part a plugin cannot decide for you.
OKF vs llms.txt: what is the difference?
llms.txt is a single file at your site root that points an agent at the pages worth reading. OKF is a whole directory of cross-linked, typed markdown concepts that hands the agent the knowledge itself. llms.txt is a pointer; OKF is the content. They are complementary, and a site can ship both.
Is OKF worth adopting yet?
OKF v0.1 is an early, experimental spec that Google calls a starting point, not a finished standard. A bundle will not change your traffic this week. The honest case for adopting now is the same as schema markup a decade ago: it is cheap to ship, it makes your knowledge legible to the agents that are starting to answer questions about you, and early movers learn the format before it matters.
How do I validate an OKF bundle?
Run the open-source OKF validator over your bundle: node validator/okf-validate.mjs ./your-bundle. It returns pass or fail, names every rule a file tripped, and exits with a code you can gate CI on. See the OKF conformance suite for the rules and the validator.
Sources: the Open Knowledge Format was announced by Google Cloud's Sam McVeety and Amir Hormati in June 2026. See the Google Cloud OKF announcement and the OKF specification (SPEC.md).