Google announced the Open Knowledge Format (OKF), a new open specification for organizing and exchanging the knowledge that AI systems need in order to perform useful work.
The announcement explains the reason for developing this new specification:
“As foundation models continue to improve, the lack of relevant context often limits what they can do, especially as they are used to build agentic systems. While these models can help you write code, summarize documents, or analyze a dataset, they still need the right information to produce accurate and actionable results. “
AI Agents Need Context
AI systems often need knowledge that exists outside the model, including how data is structured, how systems work, how metrics are defined, and how internal processes operate.
That knowledge is usually scattered across catalogs, wikis, documentation, repositories, shared drives, and other internal systems, forcing AI agents to assemble context before they can complete a task.
Google says OKF is meant to solve that problem by turning scattered knowledge sources into a common format that can move between humans, AI agents, tools, and organizations.
What Open Knowledge Format Is
OKF is a format for representing organizational knowledge in a way that can be shared between different AI agents, tools, and organizations.
The format organizes concepts such as datasets, metrics, APIs, tables, and runbooks into documents that can be read by both humans and AI systems.
Google designed OKF to be simple and independent of any specific platform, allowing the same knowledge to be shared between different AI agents, tools, and organizations.
The announcement explains:
“To make the format concrete, we’re publishing reference implementations at both the producer and consumer ends:
- An enrichment agent that walks a BigQuery dataset, drafts an OKF concept document for every table and view, then runs a second LLM pass that crawls authoritative documentation and enriches each concept with citations, schemas, and join paths.
- A static HTML visualizer that turns any OKF bundle into an interactive graph view in a single self-contained file; no backend, no install on the viewing side, no data leaves the page.
- Three ready-to-browse sample bundles: GA4 e-commerce, Stack Overflow, and Bitcoin public datasets, produced by the reference agent and committed to the repo as living examples of conformant OKF.
These are proofs of concept, deliberately. The agent demonstrates one way to produce OKF; nothing about the format requires a specific agent framework or LLM. The visualizer demonstrates one way to consume it; nothing about the format requires HTML or a graph view. We expect (and want!) the ecosystem of producers and consumers to grow far beyond what we’ve shipped.”
Who OKF Is For
OKF is designed around a producer-and-consumer model. Some users create, edit, and maintain the knowledge. Others consume it through AI agents, LLMs, software systems, or internal tools.
AI Agents and LLMs
AI agents and LLMs are the primary consumers of OKF. They use the format to access the structured context and curated knowledge needed to perform tasks and produce accurate results.
Useful For AI Agents And LLMs
- Coding agents
- Data analysis agents
- Research agents
- Internal enterprise assistants
- Agentic workflows
Humans And OKF
OKF uses markdown files and YAML frontmatter, making the format readable and editable by people using standard tools.
People Who May Find OKF Useful
- AI developers
- Software engineers
- Data engineers
- Analytics teams
- Technical writers
- Business teams
Organizations And OKF
Organizations can use OKF to package and share institutional knowledge that would otherwise remain scattered across documentation systems, metadata catalogs, repositories, and internal tools.
Organizations That May Find OKF Useful
- Organizations building AI agents
- Data teams
- Engineering teams
- Knowledge management teams
Availability
Google is proposing a common format for representing organizational knowledge rather than a new platform for managing it. The OKF specification, reference implementations, and sample bundles are available on GitHub. The announcement makes a point of saying that it is a starting point:
“OKF v0.1 is a starting point, not a finished standard. The format will evolve as more producers and consumers emerge and as we collectively learn what knowledge representations agents actually need in practice.
We’re publishing in the open from day one because that’s the only way a knowledge format earns its name, whether you’re building a knowledge catalog, an enrichment pipeline, a wiki tailored to AI agents, or anything in the AI knowledge domain.”
An explainer tweet by Tech With Mak shared why this solves a problem:
“The most underrated idea in agent tooling this year might be a gist Andrej Karpathy wrote about “LLM Wikis” – markdown libraries that agents read, update, and maintain on their own.
What followed was predictable. Teams everywhere started building their own version – AGENTS[.]md, CLAUDE[.]md, Obsidian vaults wired into coding agents, folders of index[.]md and log[.]md files agents consult before doing anything.
…Google just tried to close that gap with the Open Knowledge Format – a spec that says => here’s the one field every concept needs (type), here’s a small set of optional fields if you want them queryable, and otherwise, write however you want.
It’s not a new tool or platform. It’s an agreement on shape, which is exactly what Karpathy’s pattern needed to stop being a hundred incompatible reinventions of the same idea.”
Read the original announcement here:
Introducing the Open Knowledge Format
Featured Image by Shutterstock/Poetra.RH
Generative AI,News#Google #Cloud #Announces #Open #Knowledge #Format #sejournal #martinibuster1781529750
