# Google Cloud 推出 Open Knowledge Format （OKF）：将散乱文档转为 Markdown 文件供 AI 智能体使用

- 来源：The Decoder：AI News（RSS）
- 作者：Matthias Bastian
- 发布时间：2026-06-14 21:29
- AIHOT 分数：41
- AIHOT 链接：https://aihot.virxact.com/items/cmqdu59tl000pslrdwvefdrug
- 原文链接：https://the-decoder.com/google-clouds-open-knowledge-format-turns-scattered-docs-into-markdown-files-for-ai-agents

## AI 摘要

Google Cloud 发布 Open Knowledge Format (OKF)，一种将分散的组织知识标准化为带 YAML frontmatter 的 Markdown 文件的极简规范。OKF 使知识可移植且可直接供 AI 智能体使用，正式化了 Andrej Karpathy 近期推广的 “LLM Wiki” 模式。

## 正文

Google Cloud's Open Knowledge Format turns scattered docs into Markdown files for AI agents

Google Cloud is introducing the Open Knowledge Format (OKF), a new spec that standardizes knowledge as Markdown files and makes it portable across systems.

It takes the "LLM wiki" pattern recently popularized by Andrej Karpathy and turns it into an interoperable format. OKF v0.1 represents knowledge as a directory of Markdown files with YAML frontmatter. The spec is minimal. One required field ("type"), a handful of optional fields like title, description, resource, tags, and timestamps, plus a Markdown body for everything else.

Concepts link to each other through standard Markdown links, forming a knowledge graph. An OKF bundle is readable in any editor, renders on GitHub, and can be indexed by any search tool.

Fragmented knowledge slows AI agents down

Most organizations know the problem OKF is trying to solve. Knowledge is scattered across metadata catalogs, wikis, code comments, notebook cells, and the heads of individual engineers. When an AI agent needs to write a SQL query for a specific dataset, it has to piece together fragments from all these sources.

According to Google Cloud, every agent developer currently solves this context problem from scratch, and every catalog vendor reinvents the same data models. Obsidian Vaults hooked up to coding agents, AGENTS.md and CLAUDE.md convention files, "metadata as code" repos on data teams. They all follow a similar pattern. But each solution is custom-built and not designed to work with the others, Google says. Knowledge stays locked inside the system that created it. That's the gap OKF aims to close.

Built to be minimal and portable

OKF requires just one field ("type"). Which types exist, what extra fields a document contains, and how the body is structured is up to the producer. Producers and consumers are decoupled. A bundle written by humans can be consumed by an AI agent. A machine-generated bundle can be viewed in a visualizer. OKF works with any cloud provider, database, or agent framework.

Alongside the spec, Google Cloud is shipping several reference implementations. There's an enrichment agent that crawls BigQuery datasets and creates an OKF document for each table, a static HTML visualizer, and three sample bundles for GA4 e-commerce, Stack Overflow, and Bitcoin datasets.

Google Cloud also updated its Knowledge Catalog so it can ingest OKF and serve it to agents. The spec and code are available on GitHub. The Knowledge Catalog integration is documented separately.

AI News Without the Hype – Curated by Humans