正在打开每日关注
OKF：用 Markdown 构建可互操作的 Agent 知识库
Google提出以目录化Markdown和YAML元数据统一承载可供人和Agent使用的知识。
来源摘录
This is really big news. Google introduced the Open Knowledge Format (OKF) - a standardized way to store information in a directory of markdown files. Makes it really easy to make a digital brain that agents can use. These files can serve as a living wiki. You can give agents the ability to query them or edit them. They can interlink. Seems to me this could replace Notion or Obsidian. I can think of so many uses for this. Google's blog post: https://t.co/DqSjg4UpvH An easier to understand explanation is the SPEC.md file: https://t.co/A3qSz3Tfas I gave those two links to Antigravity and asked how we could use it for any of the projects we're working on. It came up with so many ideas. I would imagine Claude Fable 5 would whip up some pretty amazing things based on this system. Currently creating an OKF library of our pepper garden. It's going to be a fun weekend.
深度解析
是什么 OKF把“LLM wiki”固化为开放规范：用目录化Markdown表达概念，用YAML frontmatter提供可查询字段，用文件路径确定身份，用普通Markdown链接形成关系图，并可通过index.md、log.md支持渐进披露与变更记录。它解决的不是再建一个知识服务，而是让不同团队、目录和Agent共享可迁移上下文。
核心论点 文章认为组织知识分散在目录、Wiki、共享盘、代码和个人经验中，Agent因此反复拼装上下文；统一格式可以降低集成与翻译成本，并让知识进入版本控制，便于人机共同维护。截图用sales目录及datasets、tables、metrics树直观呈现身份与层级。
仓库对应物 GoogleCloudPlatform/knowledge-catalog是TypeScript的Knowledge Catalog工具、Agent与示例仓库，README称其用于展示数据目录、知识图谱、上下文管理、丰富与检索方案；采用Apache 2.0，并声明不是官方Google产品，不能据此断言它完整实现OKF。
亮点与边界 最值得借鉴的是小而稳定的互操作面：只强制type，其余内容模型交给生产者。v0.1仍需面对权限、敏感信息、陈旧内容、链接治理和质量校验；文件可移植不等于知识可靠，也不会自动解决检索、授权与更新责任。