Summary
The Open Knowledge Format (OKF) is a vendor‑neutral, open specification for representing structured knowledge as a portable bundle of markdown files with YAML frontmatter. It formalises the LLM wiki pattern into a standard that both humans and AI agents can read, write, and exchange without proprietary tools. OKF is designed to solve the fragmentation of internal knowledge in organisations — schemas, metrics, runbooks, API deprecations, and other “atoms of knowledge” that are currently scattered across wikis, catalogs, code comments, and engineers’ heads.
Key Points
- OKF bundles are directories of markdown files (
.md), each representing one concept (e.g. a table, metric, playbook, API). - A small set of YAML frontmatter fields (
type,title,description,resource,tags,timestamp) provides structured queryability. - The format lives in version control, is human‑readable, and requires no SDK or special runtime.
- OKF follows three design principles: minimally opinionated, producer/consumer independence, and “format, not platform”.
- Reference implementations include a BigQuery enrichment agent, a static HTML visualiser, and sample bundles for GA4, Stack Overflow, and Bitcoin datasets.
Concepts
- LLM wiki pattern — a practice (popularised by Andrej Karpathy) of using a shared markdown wiki that an AI agent can consult and update, turning knowledge maintenance into a task the LLM handles while humans curate.
- Concept document — a single markdown file in an OKF bundle, with YAML frontmatter and a body that can contain prose, links, code, or diagrams.
- Bundle — the top‑level directory containing concept files, optional
index.md(for hierarchical navigation) andlog.md(for chronological change history). - Producer / consumer independence — OKF cleanly separates knowledge creation from consumption; a hand‑authored bundle works with any agent, and a machine‑generated bundle can be browsed in any viewer.