Google Cloud Introduces the Open Knowledge Format (OKF)

ArticleSam McVeety, Amir HormatiAnnouncement

Google Cloud has announced the Open Knowledge Format (OKF) v0.1, an open and vendor-neutral specification that standardises the LLM-wiki pattern into a portable format. OKF represents enterprise metadata, context, and curated knowledge as a directory of Markdown files with YAML frontmatter, readable by both humans and AI agents without proprietary SDKs.

Key points

  1. OKF v0.1 relies entirely on Markdown file directories with YAML frontmatter, requiring no specialised runtime or custom SDK.
  2. The specification is minimally opinionated, enforcing only a single mandatory frontmatter field: 'type'.
  3. Concepts (such as tables, metrics, runbooks, or APIs) are linked using standard Markdown links; optional index.md and log.md files handle navigation hierarchies and change logs.
  4. Google released reference implementations, including a BigQuery enrichment agent, a standalone static HTML visualizer, and three sample bundles.
  5. Google Cloud's Knowledge Catalog has been updated to ingest OKF bundles and serve them to agents.

Why it matters

Agentic AI workflows often fail due to fragmented internal knowledge scattered across disparate catalogs, shared drives, and codebases. OKF provides a lightweight, version-controlled standard that lives alongside code in Git, preventing context silos and reducing the need to reinvent integration layers for every new agent.

Analysis

By building directly on established patterns like Andrej Karpathy's LLM-wiki concept and files like CLAUDE.md or AGENTS.md, Google attempts to turn fragmented conventions into an interoperable specification. The success of OKF will rely on adoption by third-party catalog vendors and open-source agent frameworks beyond Google Cloud's own tooling.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:GoogleCloudPlatform/knowledge-catalog

    Google Cloud Knowledge Catalog: Tools and Samples for Semantic AI Agents

    The GoogleCloudPlatform/knowledge-catalog repository gathers tools, agents, and sample code for Google Cloud's Knowledge Catalog (formerly Dataplex). The platform functions as an AI-powered data catalog and metadata management system, organising structured and unstructured data into a dynamic knowledge graph to deliver business context to AI agents.

    9.1kstarsTypeScript

    AI & LLMs· Tool

  • Link:Anthropic

    Agent Skills: An Open Standard for Modular AI Agent Capabilities

    Agent Skills is an open format designed to equip AI agents with specialised domain knowledge and repeatable workflows. Centred around a directory containing a SKILL.md file, it relies on progressive disclosure to keep context overhead minimal.

    AI & LLMs· Resource

  • Repository:AgriciDaniel/claude-obsidian

    claude-obsidian: Local-First AI Knowledge Management for Obsidian and Claude Code

    claude-obsidian is an MIT-licensed open-source project that connects Claude Code with Obsidian into a self-organizing knowledge graph. Implementing Karpathy's LLM Wiki pattern, it maintains a structured vault made entirely of local plain Markdown files.

    14.6kstarsPython

    AI & LLMs· Tool

  • Article:Agrici Daniel

    claude-obsidian: Self-Organising Knowledge Base with Claude Code

    Agrici Daniel introduces claude-obsidian, a free open-source plugin for Claude Code. It implements Andrej Karpathy's LLM Wiki pattern to automatically compile and link Obsidian vaults from raw documents without requiring a vector database.

    AI & LLMs· Tool

  • Link:agentwikis.com

    Agent Wikis: Maintained Knowledge Bases for Humans and AI Agents

    Agent Wikis transforms fast-moving information sources such as repositories, changelogs, transcripts, and community Q&A into structured Markdown knowledge bases. Designed for both humans and AI agents, the content is accessible via an llms.txt entry point.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.