awesome-okf
开放知识格式(OKF)的中文资料整理,以及几个把飞书、Obsidian、Notion、GitHub 等转成 OKF 的小工具
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/yzfly/awesome-okf with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/yzfly/awesome-okf'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/yzfly--awesome-okf)HTML
<a href="/listings/yzfly--awesome-okf"><img src="/api/listings/yzfly--awesome-okf/badge.svg" alt="findsafeskills safety rating" /></a>Install
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 145 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- ---
- type: Overview
- title: Awesome OKF
- description: 中文世界第一个 OKF 落点:规范翻译、工具链、提案,以及一份活的合规范例。
- tags: [okf, awesome, 中文]
- lang: zh
- generated: { by: human:yzfly, at: 2026-06-14T00:00:00Z }
- author: 云中江树
- ---
- # Awesome OKF
- 中文 | [English](./README.en.md)
- 开放知识格式(OKF)的中文资料和工具。规范翻译、七个 producer 插件、七个 Claude Code skill、三份向上游的扩展提案。
- [OKF](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) 是 Google Cloud 发布的一份开放规范——把知识定义为一个目录的 Markdown 文件,带 YAML frontmatter,加一小套约定。没有运行时,没有 SDK。
- > 📌 **规范已升到 v0.2**:新增出处(`sources`)、信任(`generated`/`verified`)、生命周期(`status`/`stale_after`)与可验算计算(`Attested Computation`)四个家族;两处破坏性变更是 `timestamp` → `generated.at`、正文 `# Citations` → 头信息 `sources`。本仓库(规范译文、校验器、七个插件、全部文档)已完成迁移,详见 [规范中文版 §13](./docs/okf-spec-zh.md#13-与-v01-的差异)。
- ## 快速开始
- ```bash
- # 安装
- pip install myokf-cli
- # 从一个 GitHub 仓库拉取 OKF bundle
- myokf from-github yzfly/awesome-okf -o ./kb
- # 校验
- myokf validate ./kb
- # 打包成单文件网页
- myokf to-web ./kb -o kb.html
- ```
- ## 内容
- **工具(plugins/)**
- | 工具 | 输入 → OKF |
- |---|---|
- | [feishu-to-okf](./plugins/feishu-to-okf/) | 飞书知识空间 / 文档 |
- | [obsidian-to-okf](./plugins/obsidian-to-okf/) | Obsidian vault(wikilink → OKF 链接) |
- | [notion-to-okf](./plugins/notion-to-okf/) | Notion Markdown 导出 |
- | [github-to-okf](./plugins/github-to-okf/) | GitHub 仓库(提取代码符号) |
- | [awesome-to-okf](./plugins/awesome-to-okf/) | GitHub awesome-xx 列表 |
- | [html-to-okf](./plugins/html-to-okf/) | HTML 文件 |
- | [myokf-cli](./plugins/myokf-cli/) | 以上工具的统一 CLI 入口 |
- 全部零第三方依赖,标准库,产物通过符合性校验。
- **Skill(skills/)** —— Claude Code 配套工作流
- | Skill | 用途 |
- |---|---|
- | [okf-creator](./skills/okf-creator/) | 从零创建高质量 OKF 知识库 |
- | [awesome-to-okf](./skills/awesome-to-okf/) | 导入 awesome 列表并富化 |
- | [book-to-okf](./skills/book-to-okf/) | 书 / 长文拆成互链概念库 |
- | [code-to-okf](./skills/code-to-okf/) | 代码库转 OKF |
- | [github-to-okf](./skills/github-to-okf/) | 仓库 → OKF 富化工作流 |
- | [okf-to-book](./skills/okf-to-book/) | OKF 发布为 VitePress 文档站 |
- | [okf-to-web](./skills/okf-to-web/) | OKF 打包成单文件网页(含图谱) |
- **文档(docs/)**
- - [OKF 规范中文版](./docs/okf-spec-zh.md) —— 全文翻译,标注硬要求与留白
- - [发布博客中文版](./docs/blog-zh.md)
- - [Karpathy 的 LLM Wiki](./docs/karpathy-llm-wiki-zh.md) —— OKF 的思想来源
- - [代码 / PDF / 图片支持度调研](./docs/code-support-research-zh.md)
- - [全网资料汇总](./docs/resources-zh.md)
- - [仓库自身怎么做成 OKF bundle 的](./docs/dogfooding-zh.md)
- **三份扩展提案** —— 向后兼容,不动任何 MUST
- - [i18n](./docs/okf-spec-zh.md#中文生态议题i18n-扩展提案草案) —— `lang` + `canonical`
- - [代码支持](./docs/code-support-research-zh.md) —— 类型词表、符号引用、行号锚点
- - [HTML 一等公民](./docs/html-first-class-proposal-zh.md) —— `.html` 概念,双表示
- ## OKF 热门仓库
- | 仓库 | ★ | 语言 | 形态 |
- |---|---|---|---|
- | [knowledge-catalog](./references/knowledge-catalog-repo.md)(官方) | [](https://github.com/GoogleCloudPlatform/knowledge-catalog/stargazers) | HTML | OKF 规范 + 参考实现 + 示例 bundle 总入口 |
- | [open-knowledge-format](https://github.com/GoogleCloudPlatform/open-knowledge-format) | [](https://github.com/GoogleCloudPlatform/open-knowledge-format/stargazers) | HTML | **官方规范独立仓库**(2026-08 从 knowledge-catalog 拆出):SPEC v0.2 + PoC 生成 agent + 可视化器 + 4 个示例 bundle,规范的最新提交在这里 |
- | [openwiki](./references/openwiki.md)(LangChain) | [](https://github.com/langchain-ai/openwiki/stargazers) | TS | LangChain 官方:为代码库写并维护 agent 文档的 CLI,**产出 OKF v0.2 bundle**(生态 star 最高) |
- | [iwe](./references/iwe.md) | [](https://github.com/iwe-org/iwe/stargazers) | Rust | Markdown 知识图谱:编辑器 LSP + CLI + MCP,`iwe init --okf` 一等支持,模板以 v0.2 分发并在 CI 校验 |
- | [zosmaai/pi-llm-wiki](https://github.com/zosmaai/pi-llm-wiki) | [](https://github.com/zosmaai/pi-llm-wiki/stargazers) | TS | 自维护、兼容 Obsidian 的知识库,原始资料→互链 wiki |
- | [fellowgeek/mcp-memory](https://github.com/fellowgeek/mcp-memory) | [](https://github.com/fellowgeek/mcp-memory/stargazers) | Python | OKF 为底的 MCP server,给 agent 持久长期记忆 + SQL 检索 |
- | [coleam00/cole-medin-knowledge-base](https://github.com/coleam00/cole-medin-knowledge-base) | [](https://github.com/coleam00/cole-medin-knowledge-base/stargazers) | JS | OKF 知识库 + Karpathy 式 LLM wiki 合成产物 |
- | [UmairBaig8/okf-generator](https://github.com/UmairBaig8/okf-generator) | [](https://github.com/UmairBaig8/okf-generator/stargazers) | Python | OKF bundle 生成器:Claude skill + OpenCode 集成 |
- | [jyjeanne/okf-rs](https://github.com/jyjeanne/okf-rs) | [](https://github.com/jyjeanne/okf-rs/stargazers) | Rust | Rust 工具链:生成 / 校验 / serve OKF bundle |
- | [openknowledge-sh/openknowledge](https://github.com/openknowledge-sh/openknowledge) | [](https://github.com/openknowledge-sh/openknowledge/stargazers) | Go | 管理 OKF bundle 的 Go CLI |
- | [saschb2b/okf-studio](https://github.com/saschb2b/okf-studio) | [](https://github.com/saschb2b/okf-studio/stargazers) | TS | OKF bundle 的原生桌面阅读器,指向一个目录即可浏览 |
- | [aws-samples/sample-okf-llm-wiki](https://github.com/aws-samples/sample-okf-llm-wiki) | [](https://github.com/aws-samples/sample-okf-llm-wiki/stargazers) | Python | AWS 官方示例:把数据转成 OKF bundle 并对外提供 |
- | [JuneYaooo/lineage-skill](https://github.com/JuneYaooo/teacher-to-skills) | [](https://github.com/JuneYaooo/teacher-to-skills/stargazers) | Python | 带出处(lineage)蒸馏的 Agent Skill,输出 OKF 包 |
- | [psinetron/echoes-vault-opencode](https://github.com/psinetron/echoes-vault-opencode) | [](https://github.com/psinetron/echoes-vault-opencode/stargazers) | TS | OpenCode 持久记忆插件,底层用 OKF |
- | [guhcostan/claude-mega-brain](https://github.com/guhcostan/claude-mega-brain) | [](https://github.com/guhcostan/claude-mega-brain/stargazers) | Python | Claude Code 的 OKF 知识上下文注入插件 |
- | [takeshy/obsidian-gemini-helper](https://github.com/takeshy/obsidian-gemini-helper) | [](https://github.com/takeshy/obsidian-gemini-helper/stargazers) | TS | 支持 OKF 知识源的 Obsidian Gemini 助手 |
- | [coleam00/cole-medin-ai-coding](https://github.com/coleam00/cole-medin-ai-coding) | [](https://github.com/coleam00/cole-medin-ai-coding/stargazers) | Python | Cole Medin AI 编程视频的 OKF 知识包 |
- | [okf-gem](./references/okf-gem.md) | [](https://github.com/serradura/okf/stargazers) | Ruby | 创作 skill + CLI/库 + 图谱,覆盖 bundle 全生命周期 |
- | [OWOX Model Canvas](./references/owox-model-canvas.md) | [](https://github.com/OWOX/models/stargazers) | TS | 可视化建模 / 创作端(公司维护) |
- | [0dust/OKFy](https://github.com/0dust/OKFy) | [](https://github.com/0dust/OKFy/stargazers) | TS | 文档 → agent 可读 OKF bundle 转换器 |
- | [okf-knowledge](./references/okf-knowledge.md) | [](https://github.com/sniperunder123/okf-knowledge/stargazers) | Python | Claude Code `/okf` skill |
- | [PoorvaJ-WW/okft](https://github.com/PoorvaJ-WW/okft) | [](https://github.com/PoorvaJ-WW/okft/stargazers) | Python | OKF 规范校验器(okft lint,适合 CI)+ MCP 服务器(okft serve),pip 安装 |
- | [longsizhuo/okf-frontmatter](https://github.com/longsizhuo/okf-frontmatter) | [](https://github.com/longsizhuo/okf-frontmatter/stargazers) | Python | 把仓库文档维护成 OKF 形态的 skill |
- | [hermes-okf](./references/hermes-okf.md) | [](https://github.com/EliaszDev/hermes-okf/stargazers) | Python | 基于 OKF 的 Agent 持久记忆(PyPI) |
- | [pumblus/okf-harness](https://github.com/pumblus/okf-harness) | [](https://github.com/pumblus/okf-harness/stargazers) | TS | 本地优先的 agent 终端 harness |
- | [scaccogatto/okf-skills](https://github.com/scaccogatto/okf-skills) | [](https://github.com/scaccogatto/okf-skills/stargazers) | Python | Claude Code 的 OKF 技能 |
- | [wiki-as-an-mcp](./references/wiki-as-an-mcp.md) | [](https://github.com/taikunudel/wiki-as-an-mcp/stargazers) | Python | 首个通用 Wiki MCP server |
- | [superops-team/okf](./references/superops-okf.md) | [](https://github.com/superops-team/okf/stargazers) | Go | 项目级知识库 |
- | [xSAVIKx/okf-skills](https://github.com/xSAVIKx/okf-skills) | [](https://github.com/xSAVIKx/okf-skills/stargazers) | Go | Go 实现的 OKF agentic skills |
- | [okf-rag](./references/okf-rag.md) | [](https://github.com/killop/okf-rag/stargazers) | Rust | 本地优先 OKF 检索 / RAG |
- | [Sudhakaran88/okf-conformance](https://github.com/Sudhakaran88/okf-conformance) | [](https://github.com/Sudhakaran88/okf-conformance/stargazers) | JS | OKF 一致性校验器 |
- | [joshuaswarren/remnic](https://github.com/joshuaswarren/remnic) | [](https://github.com/joshuaswarren/remnic/stargazers) | TS | 面向「认识用户」的 agent 记忆 / 上下文层:记忆目录即 OKF bundle,自带 `remnic okf lint`,MCP/HTTP 双接口 |
- | [ZeroDot1/LLMWikiNG](https://github.com/ZeroDot1/LLMWikiNG) | [](https://github.com/ZeroDot1/LLMWikiNG/stargazers) | Python | 本地、隐私优先的 Karpathy 式 LLM Wiki 平台(OKF Edition),由 AI 维护与扩写 |
- | [jkroepke/okf-crossplane-v2](https://github.com/jkroepke/okf-crossplane-v2) | [](https://github.com/jkroepke/okf-crossplane-v2/stargazers) | Python | Crossplane v2 的 LLM-wiki,带 CI 校验的真实领域 OKF bundle 样例 |
- | [stjbrown/agent-knowledge](https://github.com/stjbrown/agent-knowledge) | [](https://github.com/stjbrown/agent-knowledge/stargazers) | JS | 可移植 Agent Skills,用纯 Markdown 构建并维护 OKF 项目 wiki |
- | [kiso](https://github.com/oak-invest/kiso) | [](https://github.com/oak-invest/kiso/stargazers) | Java | OKF 发布引擎:bundle → 面向人与 agent 的静态站,附 MCP server |
- | [kushal-omnius/open-knowledge-compiler](https://github.com/kushal-omnius/open-knowledge-compiler) | [](https://github.com/kushal-omnius/open-knowledge-compiler/stargazers) | Python | 把 Git / PR / 测试历史确定性编译成带出处的可查询知识库(v0.2) |
- | [Connorrmcd6/surface](https://github.com/Connorrmcd6/surface) | [](https://github.com/Connorrmcd6/surface/stargazers) | Rust | 「常鲜」文档:hub 是合规 OKF 概念,补上 OKF 留白的新鲜度检查,过期即构建失败 |
- | [okfcli/okf](https://github.com/okfcli/okf) | [](https://github.com/okfcli/okf/stargazers) | Go | 厂商中立 Go CLI:创建 / 校验 / lint / 索引 / 搜索 / 图谱,为被 agent 驱动而设计 |
- | [DavidROliverBA/aix-format](https://github.com/DavidROliverBA/ai-xf-format) | [](https://github.com/DavidROliverBA/ai-xf-format/stargazers) | Python | AIX:OKF v0.2 的严格超集——稳定标识、类型化关系、媒体身份、联邦 |
- | [W4G1/okf](https://github.com/W4G1/okf) | [](https://github.com/W4G1/okf/stargazers) | Rust | 纯 Rust 零依赖实现与 CLI 工具链 |
- | [CogniSwitch/KL4A](https://github.com/CogniSwitch/KL4A) | [](https://github.com/CogniSwitch/KL4A/stargazers) | Rust | 把 SOP、政策、法规文档(PDF / DOCX / 纯文本)转为 OKF 风格 bundle(文档披露了与 v0.2 元数据的差异);每条知识都带原文精确跨度,人工审核通过前不标记 verified |
- | [JidoSeal](https://github.com/Jidoseal/jidoseal-mcp) | [](https://github.com/Jidoseal/jidoseal-mcp/stargazers) | Python | 免费的本地 OKF 检查器(MCP)。可选付费证书。MCP 服务是 Apache-2.0;扫描引擎不是开源。与 OKF 规范或 Google 无隶属。 |
- | [ahmedibrahim085/okf-knowledge-gate](https://github.com/ahmedibrahim085/okf-knowledge-gate) | [](https://github.com/ahmedibrahim085/okf-knowledge-gate/stargazers) | Bash、Python | OKF bundle 的检查关卡:规范合规、自定规则、过期检测、`human:` 人工验证元数据的一致性与可疑标记(不能证明验证者身份)、笔记引用的 commit 是否存在。一个退出码可用于 CI(GitHub Action)、pre-commit 和 Claude Code |
- | [okf-memory/okf-agent-memory](https://github.com/okf-memory/okf-agent-memory) | [](https://github.com/okf-memory/okf-agent-memory/stargazers) | Go | 基于 OKF v0.2 的 Git 原生 Agent 项目记忆:双记忆架构,内存 BM25 检索,内置 MCP server |
- | [frypan05/philosopher-OKF](https://github.com/frypan05/philosopher-OKF) | [](https://github.com/frypan05/philosopher-OKF/stargazers) | Skill | 把任意主题讲成一页论文风格 HTML 学习页的 Agent Skill,知识以 OKF v0.2 bundle 存放 |
- ## 这个仓库本身
- 是一个符合 OKF v0.2 的 bundle。每个 `.md` 带 frontmatter 和非空 `type`,根目录有 `index.md` 和 `log.md`:
- ```bash
- python skills/okf-creator/scripts/validate_okf.py .
- ```
- ## 贡献
- PR 欢迎。标准:跟 OKF 相关,能跑或能读。写 producer 前看 [CONTRIBUTING](./CONTRIBUTING.md)。
- ## 许可
- 云中江树 维护,微信公众号:云中江树。[MIT](./LICENSE)。
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.