The Format Convergence

2025-11-17 · Source: The Ontologist · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Software Development & Engineering · Depth: Intermediate, medium

Summary

Google Cloud engineers introduced the Open Knowledge Format (OKF) on June 12, 2026, a vendor-neutral, agent- and human-friendly standard for representing metadata and curated knowledge for modern AI systems. OKF is essentially a directory of markdown files with YAML frontmatter, formalizing patterns like Andrej Karpathy's "LLM Wiki." Its design prioritizes minimal opinion, producer/consumer independence, and format over platform. This architecture converges with the W3C DataBook specification, which also uses markdown and YAML. While OKF functions as a simple wiki format, DataBook extends it with formal typing, IRI-based identity, and tooling (CLI v1.4.4) for deploying knowledge to triplestores via the SPARQL Graph Store Protocol, including SHACL validation. The article proposes DataBook as a formal OKF profile.

Key takeaway

For AI Architects evaluating knowledge representation standards, recognize OKF as a foundational, widely adoptable format for AI-driven knowledge bases. Your teams should consider extending OKF with semantic web capabilities, potentially through a DataBook-based profile, to enable formal ontological typing and SPARQL-queryability for robust knowledge graph deployment. Engage with the W3C Holon Community Group to shape this evolution.

Key insights

Open Knowledge Format (OKF) formalizes a markdown-based, human/AI-friendly standard for structured knowledge, enabling interoperability.

Principles

• Minimally opinionated format.
• Producer/consumer independence.
• Format, not platform.

Method

An OKF bundle is a directory where each markdown file represents a concept with YAML frontmatter (required "type" field) and links to other files.

In practice

• Use markdown libraries for AI agents.
• Formalize metadata-as-code repositories.
• Integrate human-authored content with AI.

Topics

• Open Knowledge Format
• DataBook
• Semantic Web
• Knowledge Graphs
• AI Agents
• Markdown

Code references

• w3c-cg/holon

Best for: CTO, VP of Engineering/Data, AI Architect, AI Engineer, Director of AI/ML

Related on AIssential

• The KG-ER Conceptual Schema Language — KG-ER provides a representation-agnostic conceptual schema language for knowledge graphs, enhancing semantic capture.
• W3C Holon Graph Community Group — The W3C Holon Graph Community Group formalizes the "holon" concept using RDF, SHACL, SPARQL, and Prov-O for diverse applications.
• Steal This Deck — Reliable agentic AI requires robust knowledge infrastructure, not just data, to overcome current productivity and hallucination issues.
• The Gap That Runs Both Ways — RDF 1.2 reification enables formal systems to model speech acts, bridging the expressivity gap with natural language by adding precision and provenance.
• Knowledge Graphs, Part II — Knowledge graphs are architectures defined by component configuration, not finite products.
• Formalizing the DATASUS RTS: An Ontological Model for a Resource Description Framework Knowledge Graph — Transforming relational health data into a W3C-compliant knowledge graph improves interoperability and semantic querying.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Ontologist.