[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-96062":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":15,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":16,"rankGlobal":9,"rankLanguage":9,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":9,"pushedAt":9,"updatedAt":40,"readmeContent":41,"aiSummary":42,"trendingCount":14,"starSnapshotCount":14,"syncStatus":12,"lastSyncTime":43,"discoverSource":44},96062,"Awesome-OKF","Albertchamberlain\u002FAwesome-OKF","Albertchamberlain","OKF (Open Knowledge Format) — curated catalog of tools, plugins, skills, proposals, and docs for agent-friendly knowledge. YAML-driven, agent-searchable, MCP-ready.",null,"Python",102,2,4,0,1,41.53,"MIT License",false,"main",true,[22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"agent-memory","agent-skills","ai-agents","ai-memory","awesome","awesome-list","claude-code","knowledge-base","knowledge-graph","knowledge-management","llm","llm-wiki","markdown","mcp","okf","open-knowledge-format","structured-knowledge","yaml","2026-09-20 04:01:32","\u003Cp align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"assets\u002Flogo-dark.svg\">\n    \u003Cimg alt=\"Awesome OKF\" src=\"assets\u002Flogo.svg\" width=\"128\">\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ch1 align=\"center\">Awesome OKF\u003C\u002Fh1>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>The curated catalog of Open Knowledge Format resources.\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  YAML-driven. Agent-searchable. Community-curated.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAlbertchamberlain\u002FAwesome-OKF\">\u003Cimg alt=\"Awesome\" src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fsindresorhus\u002Fawesome@main\u002Fmedia\u002Fbadge.svg\">\u003C\u002Fa>\n  \u003Ca href=\"LICENSE\">\u003Cimg alt=\"License\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-4c1?logo=open-source-initiative&logoColor=white\">\u003C\u002Fa>\n  \u003Cimg alt=\"Catalog\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcatalog-29%20entries-7c3aed\">\n  \u003Cimg alt=\"OKF Anything\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOKF-Anything-7c3aed\">\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cb>English\u003C\u002Fb> | \u003Ca href=\"README.zh.md\">中文\u003C\u002Fa> | \u003Ca href=\"README.ja.md\">日本語\u003C\u002Fa> | \u003Ca href=\"README.ko.md\">한국어\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cbr>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"#catalog\">\u003Cb>Catalog\u003C\u002Fb>\u003C\u002Fa>  · \n  \u003Ca href=\"#connect-to-your-agent\">\u003Cb>Connect an Agent\u003C\u002Fb>\u003C\u002Fa>  · \n  \u003Ca href=\"#cli\">\u003Cb>CLI\u003C\u002Fb>\u003C\u002Fa>  · \n  \u003Ca href=\"#contributing\">\u003Cb>Contributing\u003C\u002Fb>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cbr>\n\n---\n\n## What is OKF\n\n[Open Knowledge Format (OKF)](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Fblob\u002Fmain\u002Fokf\u002FSPEC.md) is an open specification by Google Cloud — define knowledge as a directory of Markdown files with YAML frontmatter and a small set of conventions. No runtime, no SDK.\n\n## What's Different Here\n\nAwesome OKF keeps the entire OKF ecosystem in **one validated YAML catalog**, then turns it into a browsable list, a searchable CLI, and an MCP meta-server that AI agents can query directly:\n\n\u003Cdiv align=\"center\">\n\n```\n                      catalog.yaml\n                           │\n          ┌────────────────┼────────────────┐\n          ▼                ▼                 ▼\n      README.md         CLI tools        MCP server\n   (human-browsable)  (searchable)   (agent-searchable)\n```\n\n\u003C\u002Fdiv>\n\n> **Edit one record. Regenerate the docs. Re-query from anywhere.**\n\n---\n\n## 🌐 OKF Anything\n\n**Anything readable → OKF.** Every format above — and any you invent — collapses into one intermediate shape, then bundles into OKF:\n\n```\n        ┌────────── EXTRACT ──────────┐   ┌── NORMALIZE ──┐   ┌──── BUNDLE ────┐\n        │  Markdown · Typora · PDF    │   │  title         │   │  # title       │\n        │  Obsidian · Notion · Feishu │ → │  url           │ → │  description   │\n        │  GitHub · JSON · YAML       │   │  description   │   │  resource      │\n        │  CSV · key-value · OCR      │   │  body \u002F tags   │   │  myokf-ready   │\n        └─────────────────────────────┘   └────────────────┘   └────────────────┘\n```\n\n1. **Extract** — pull readable text out of any source. Platform exports and local engines (pymupdf, PaddleOCR) do the lifting; **nothing runs through our model**.\n2. **Normalize** — every format reduces to `title \u002F url \u002F description` (+ optional `body`, `tags`).\n3. **Bundle** — render the intermediate shape into a myokf-validatable OKF directory.\n\n`--format anything` is the programmatic form: feed it arbitrary text and it walks the parser chain (list → JSON → key-value → URLs → line-per-row) until one sticks:\n\n```bash\npython scripts\u002Fconvert-to-okf.py whatever.txt --format anything -o kb\u002F\n```\n\nThe MCP tool `convert_to_okf` speaks the same idea — an agent hands it arbitrary text, it hands back OKF.\n\n---\n\n## See It in Action\n\n```text\nUser (or Agent):\n  \"Find an OKF plugin for Obsidian vault conversion.\"\n\nAgent calls:\n  search_catalog({\n    \"query\": \"Obsidian\",\n    \"kind\": \"plugin\",\n    \"limit\": 3\n  })\n\nAwesome-OKF responds:\n  ┌──────────────────────────────────────────────────────────────┐\n  │ obsidian-to-okf                                plugin        │\n  │ Convert Obsidian vaults to OKF — wikilinks become OKF links. │\n  │ Platform: python  ·  Tags: obsidian, wikilink, markdown      │\n  └──────────────────────────────────────────────────────────────┘\n```\n\n*The catalog speaks OKF.*\n\n---\n\n## Quick Start\n\n### Connect to Your Agent\n\nAdd Awesome OKF to any MCP client so your agent can discover OKF resources:\n\n```bash\npipx install awesome-okf\n```\n\n```json\n{\n  \"mcpServers\": {\n    \"awesome-okf\": {\n      \"command\": \"awesome-okf-server\"\n    }\n  }\n}\n```\n\n### CLI\n\n```bash\nawesome-okf stats\nawesome-okf list --kind plugin\nawesome-okf search obsidian\nawesome-okf readme\n```\n\n---\n\n## 🛠️ Our Tools\n\n### convert-to-okf 🔄\n\nZero-dependency CLI that converts content from your favorite platforms into OKF knowledge bundles:\n\n| 📥 Input Format | ✨ What It Does |\n|---|---|\n| 📋 Markdown awesome-xx lists | Extracts `- [Title](URL) — Description` items → OKF entries |\n| 📊 JSON arrays | Converts `{title, url, description}` objects → OKF entries |\n| 🔗 URL lists | Plain text URL collections → OKF entries |\n| 🧾 YAML files | Lists\u002Fmappings of `{title, url, description}` — needs pyyaml (optional) |\n| 📑 CSV tables | `title\u002Furl\u002Fdescription` columns; first column wins when there's no title column |\n| 🗂️ Key-value text | Generic `key: value` blocks — frontmatter, properties files, custom formats |\n| 🐙 GitHub repos | Paste a repo URL — metadata + README fetched live → OKF entry |\n| 📓 Obsidian vaults | Local vault directory → one entry per note, wikilinks resolved |\n| 📝 Notion exports | Notion \"Export → Markdown\" directory → one entry per page |\n| 🦩 Feishu docs | Feishu-exported Markdown → one entry per document |\n| 🖋️ Typora notes | Plain `.md` files — point at a file or folder, done |\n| 📕 PDF documents | Text layer extracted via pymupdf (optional dep); scanned pages print an OCR recipe |\n| 🖼️ Scans & images | No bundled OCR — prints a ready-to-run PaddleOCR recipe instead |\n\n```bash\n# Every platform, one command\npython scripts\u002Fconvert-to-okf.py README.md -o kb\u002F -t concept\npython scripts\u002Fconvert-to-okf.py https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog --format github -o kb\u002F\npython scripts\u002Fconvert-to-okf.py my-vault\u002F --format obsidian -o kb\u002F\npython scripts\u002Fconvert-to-okf.py notion-export\u002F --format notion -o kb\u002F\npython scripts\u002Fconvert-to-okf.py feishu-doc.md --format feishu -o kb\u002F\n\n# Structured data\npython scripts\u002Fconvert-to-okf.py data.yaml --format yaml -o kb\u002F   # needs: pip install pyyaml\npython scripts\u002Fconvert-to-okf.py table.csv --format csv -o kb\u002F\npython scripts\u002Fconvert-to-okf.py notes.properties --format kv -o kb\u002F\n\n# Text-layer PDFs\npip install pymupdf\npython scripts\u002Fconvert-to-okf.py paper.pdf --format pdf -o kb\u002F\n\n# Scans \u002F image-only PDFs → OKF: OCR first (your local engine, never our model), then convert\npython scripts\u002Fconvert-to-okf.py scan.png --format image    # prints the OCR recipe\npip install paddleocr paddlepaddle\npaddleocr ppocr -i scans\u002F --type ocr --lang en -o ocr-text\u002F\npython scripts\u002Fconvert-to-okf.py ocr-text\u002F --format notion -o kb\u002F\n\n# Output: kb\u002F with Markdown files, each with YAML frontmatter\n# Ready for: myokf validate kb\u002F\n```\n\n### awesome-okf CLI 🎛️\n\nThe data-driven catalog CLI (same architecture as Awesome-MCP):\n\n| 🔍 Command | 📝 Purpose |\n|---|---|\n| `awesome-okf search obsidian` | Full-text search across all 29 entries |\n| `awesome-okf list --kind plugin` | Filter by category |\n| `awesome-okf readme` | Regenerate this README from catalog.yaml |\n| `awesome-okf-server` | MCP meta-server — let AI agents query the catalog |\n\n---\n\n## 🔥 Popular Repositories\n\n| 🏆 Repository | 📌 What It Offers |\n|---|---|\n| ⭐ [yzfly\u002Fawesome-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf) | 中文世界第一个 OKF 落点 — 7 plugins + 7 skills + 3 proposals |\n| ⭐ [linyiru\u002Fawesome-okf](https:\u002F\u002Fgithub.com\u002Flinyiru\u002Fawesome-okf) | English OKF resource hub — spec, tools, samples, guides |\n| 📚 [GoogleCloudPlatform\u002Fknowledge-catalog](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog) | Official OKF spec, SDK, and proposals by Google |\n| 🧠 [karpathy\u002Fllm-wiki](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fllm-wiki) | The original LLM Wiki that inspired OKF |\n\n---\n\n## Catalog\n\n> **29 curated entries** · 4 tools · 7 plugins · 7 skills · 5 proposals · 6 docs\n> *Deliberately curated — not an exhaustive index.*\n\n\u003C!-- CATALOG:TOOLS:START -->\n\n## 🛠️ Tools & CLI\n\n### Cli\n\n- [myokf-cli](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf) `cli` — Unified CLI for OKF — pull from GitHub, validate, and package to single-file web. — `cli`, `python`, `validation`, `packaging`\n\n### Conversion\n\n- [binder](https:\u002F\u002Fgithub.com\u002Fghchinoy\u002Fbinder) `cli` — Go CLI that converts an existing plain-markdown corpus into a conformant OKF v0.2 bundle, resolving the corpus link web (markdown links and wikilinks) into OKF relationships — with validate, a stdio MCP server, and an agent plugin. — `conversion`, `go`, `markdown`, `wikilink`\n- [convert-to-okf](https:\u002F\u002Fgithub.com\u002FAlbertchamberlain\u002FAwesome-OKF) `cli` — CLI tool to convert Markdown awesome-xx lists, JSON arrays, and URL lists into OKF knowledge bundles — zero dependencies, standard library only. — `conversion`, `cli`, `markdown`, `json`\n\n### Quality\n\n- [OKF Validator (myokf)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf) `cli` — Built-in OKF schema validator — checks YAML frontmatter, link integrity, and spec compliance. — `validation`, `quality`, `schema`\n\n### SDK\n\n- [OKF Python SDK](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Ftree\u002Fmain\u002Ftools\u002Fpython) ✅ `python` — Official Python SDK for reading, validating, and writing OKF bundles — referenced by Google as the reference implementation. — `sdk`, `python`, `official`\n\n\u003C!-- CATALOG:TOOLS:END -->\n\n\u003C!-- CATALOG:PLUGINS:START -->\n\n## 🔌 Producer Plugins\n\n### Cli\n\n- [myokf-cli (plugin entry)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fmyokf-cli) `python` — Unified CLI entry point wrapping all seven producer plugins. — `cli`, `aggregator`, `zero-dependency`\n\n### Code\n\n- [github-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fgithub-to-okf) `python` — Extract code symbols from GitHub repositories into OKF. — `github`, `code`, `symbols`, `zero-dependency`\n\n### Document\n\n- [feishu-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Ffeishu-to-okf) `python` — Convert Feishu (Lark) knowledge spaces and documents into OKF. — `feishu`, `lark`, `document`, `zero-dependency`\n- [notion-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fnotion-to-okf) `python` — Convert Notion Markdown exports into OKF. — `notion`, `markdown`, `zero-dependency`\n- [obsidian-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fobsidian-to-okf) `python` — Convert Obsidian vaults to OKF — wikilinks become OKF links. — `obsidian`, `wikilink`, `markdown`, `zero-dependency`\n\n### List\n\n- [awesome-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fawesome-to-okf) `python` — Convert GitHub awesome-xx lists into structured OKF knowledge bases. — `awesome-list`, `conversion`, `zero-dependency`\n\n### Web\n\n- [html-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fhtml-to-okf) `python` — Convert HTML files into OKF. — `html`, `web`, `zero-dependency`\n\n\u003C!-- CATALOG:PLUGINS:END -->\n\n\u003C!-- CATALOG:SKILLS:START -->\n\n## 🤖 Claude Code Skills\n\n### Conversion\n\n- [book-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fbook-to-okf) `claude-code` — Split books and long-form articles into interlinked concept knowledge bases. — `book`, `long-form`, `concepts`\n- [code-to-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fcode-to-okf) `claude-code` — Convert codebases into OKF with Claude Code. — `code`, `repository`, `enrichment`\n\n### Creation\n\n- [okf-creator](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fokf-creator) `claude-code` — Create high-quality OKF knowledge bases from scratch with Claude Code. — `creation`, `knowledge-base`\n\n### Import\n\n- [awesome-to-okf (skill)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fawesome-to-okf) `claude-code` — Import awesome lists and enrich them into OKF with Claude Code. — `awesome-list`, `import`, `enrichment`\n- [github-to-okf (skill)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fgithub-to-okf) `claude-code` — Repository to OKF enrichment workflow with Claude Code. — `github`, `repository`, `enrichment`\n\n### Publishing\n\n- [okf-to-book](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fokf-to-book) `claude-code` — Publish OKF knowledge bases as VitePress documentation sites. — `vitepress`, `publishing`, `docs`\n- [okf-to-web](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fskills\u002Fokf-to-web) `claude-code` — Package OKF into a single-file web page with interactive knowledge graph. — `web`, `single-file`, `knowledge-graph`\n\n\u003C!-- CATALOG:SKILLS:END -->\n\n\u003C!-- CATALOG:PROPOSALS:START -->\n\n## 📝 Proposals & Extensions\n\n### Upstream\n\n- [Attested Computation Proposal](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fproposals\u002Fattested-computation.md) `web` — Propose verifiable computation records for OKF knowledge entries. — `computation`, `verification`, `upstream`\n- [Lifecycle & Staleness Proposal](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fproposals\u002Flifecycle-staleness.md) `web` — Propose `status` and `stale_after` lifecycle fields for OKF v0.2. — `lifecycle`, `staleness`, `upstream`\n- [OKF Discovery Protocol (KEP-1)](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Fblob\u002Fmain\u002Fproposals\u002Fdiscovery.md) ✅ `web` — Proposal for a standard discovery mechanism that lets agents find OKF bundles without hardcoding paths. — `discovery`, `upstream`, `kep`\n- [Sources & Provenance Extension](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fproposals\u002Fsources-provenance.md) `web` — Propose `sources` field and provenance tracking for OKF v0.2. — `sources`, `provenance`, `upstream`\n- [Trust Signals (KEP-2)](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Fblob\u002Fmain\u002Fproposals\u002Ftrust-signals.md) ✅ `web` — Proposal for verification chains and trust tiering so consumers can distinguish machine-confirmed from human-reviewed content. — `trust`, `verification`, `upstream`, `kep`\n\n\u003C!-- CATALOG:PROPOSALS:END -->\n\n\u003C!-- CATALOG:DOCS:START -->\n\n## 📖 Documentation & Specifications\n\n### Example\n\n- [Karpathy's LLM Wiki (OKF)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Fblob\u002Fmain\u002Fdocs\u002Fkarpathy-llm-wiki-zh.md) `web` — Karpathy's LLM knowledge base converted to OKF — a real-world example of OKF in action. — `example`, `llm`, `karpathy`\n- [LLM Wiki (Karpathy)](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fllm-wiki) `web` — The original LLM knowledge base by Andrej Karpathy that inspired OKF — a living wiki of LLM concepts as Markdown files. — `example`, `llm`, `karpathy`, `inspiration`\n- [OKF Market Concept](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Fblob\u002Fmain\u002Fdocs\u002Fokf-market.md) `web` — A conceptual OKF knowledge market — imagine a marketplace where knowledge entries are traded as verifiable assets. — `market`, `concept`, `knowledge-economy`\n- [OKF Super Corpus](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Ftree\u002Fmain\u002Fokf-super-corpus) ✅ `web` — A large-scale example OKF bundle curated by Google Cloud — demonstrates the format at scale across multiple domains. — `example`, `large-scale`, `google`\n\n### Guide\n\n- [OKF Blog Post (Chinese)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Fblob\u002Fmain\u002Fdocs\u002Fblog-zh.md) `web` — Chinese translation of the OKF launch blog post. — `blog`, `translation`, `chinese`\n\n### Spec\n\n- [OKF Specification (Chinese)](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Fblob\u002Fmain\u002Fdocs\u002Fokf-spec-zh.md) `web` — Full Chinese translation of the OKF specification, with mandatory requirements and gaps annotated. — `spec`, `translation`, `chinese`\n- [OKF Specification (English)](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Fblob\u002Fmain\u002Fokf\u002FSPEC.md) ✅ `web` — Official OKF specification by Google Cloud — v0.2 with sources, trust, lifecycle, and attested computation. — `spec`, `english`, `official`\n- [OKF Specification (Official)](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Fblob\u002Fmain\u002Fokf\u002FSPEC.md) ✅ `web` — Google's official OKF v0.2 specification — the canonical reference for the format. — `spec`, `official`, `google`\n\n\u003C!-- CATALOG:DOCS:END -->\n\n---\n\n## Data Model\n\n```yaml\n- id: obsidian-to-okf\n  name: obsidian-to-okf\n  kind: plugin\n  category: document\n  url: https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf\u002Ftree\u002Fmain\u002Fplugins\u002Fobsidian-to-okf\n  description: Convert Obsidian vaults to OKF — wikilinks become OKF links.\n  platform: [python]\n  official: false\n  tags: [obsidian, wikilink, markdown]\n```\n\n---\n\n## Contributing\n\nAdd or edit entries in [`data\u002Fcatalog.yaml`](data\u002Fcatalog.yaml), then:\n\n```bash\nawesome-okf validate\nawesome-okf readme\npytest\n```\n\nSee [`CONTRIBUTING.md`](CONTRIBUTING.md) for the entry schema.\n\n---\n\n## 🤖 For AI Agents\n\nIf you are an AI agent (Claude Code, Codex, Cursor) working on this repo, here's what you need to know:\n\n### Project structure\n\n```\ndata\u002Fcatalog.yaml          # SINGLE SOURCE OF TRUTH — all entries live here\nREADME.template.md         # English template (hand-written narrative)\nREADME.template.zh.md      # Chinese template\nREADME.template.ja.md      # Japanese template\nREADME.template.ko.md      # Korean template\nsrc\u002Fawesome_okf\u002F           # CLI + MCP meta-server (Python)\nscripts\u002Fconvert-to-okf.py  # Format converter tool\n```\n\n### Rules (non-negotiable)\n\n1. **Never edit README\\*.md directly** — they are generated. Edit `data\u002Fcatalog.yaml`, then regenerate.\n2. **Never edit the CATALOG blocks** in templates — the `\u003C!-- CATALOG:*:START\u002FEND -->` markers are auto-generated.\n3. **Adding an entry** = append a YAML block to `data\u002Fcatalog.yaml` + regenerate + run tests. Schema:\n   ```yaml\n   - id: kebab-case-id          # unique, never reused\n     name: Human Readable Name\n     kind: tool|plugin|skill|proposal|doc\n     category: free-form-group\n     url: https:\u002F\u002F...\n     description: One sentence, no marketing fluff.\n     platform: [cli|python|web|claude-code]\n     official: false            # true ONLY for Google\u002Fvendor official\n     tags: [3-5 short tags]\n   ```\n4. **Validate before commit**: `awesome-okf validate && pytest`\n5. **Never create duplicate ids** — edit the existing entry in place.\n6. **Multi-language**: if you touch a template, mirror the change in all four templates.\n\n### Useful commands\n\n```bash\nawesome-okf stats                    # entry counts by kind\nawesome-okf list --kind plugin       # filter by kind\nawesome-okf search \u003Cquery>           # full-text search\nawesome-okf validate                 # schema + duplicate-id check\nawesome-okf readme                   # regenerate all READMEs\nawesome-okf-server                   # MCP meta-server (stdio)\n```\n\n### MCP meta-server\n\nThe catalog is exposed to agents via `awesome-okf-server` with four tools:\n`search_catalog`, `list_catalog`, `get_catalog_entry`, `catalog_stats`, `convert_to_okf`.\nConnect it to your MCP client to query OKF resources programmatically.\n\n---\n\n\n## Related Lists\n\n- [yzfly\u002Fawesome-okf](https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-okf) — the original Chinese OKF resource hub\n- [OKF Specification](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog\u002Fblob\u002Fmain\u002Fokf\u002FSPEC.md) — official Google Cloud spec\n\n---\n\n\u003Cbr>\n\n\u003Cp align=\"center\">\n  \u003Csub>MIT — see \u003Ca href=\"LICENSE\">LICENSE\u003C\u002Fa>. Catalog descriptions link to upstream projects under their respective licenses.\u003C\u002Fsub>\n\u003C\u002Fp>","Awesome OKF 是一个面向 AI 代理的知识管理资源目录，基于 Google 提出的 Open Knowledge Format（OKF）规范构建。它以 YAML 文件统一维护工具、插件、技能、提案和文档等结构化知识条目，支持人类可读的 Markdown 文档生成、命令行全文检索，以及通过 MCP（Model Context Protocol）协议供 AI 代理直接查询。项目强调零运行时依赖、YAML 驱动、社区协同维护与多源内容标准化（如 Obsidian、Notion、PDF 等均可归一为 OKF）。适用于需要轻量级、可嵌入、代理友好的结构化知识基底的 AI 应用开发、智能体记忆扩展与跨平台知识同步场景。","2026-09-09 02:30:08","CREATED_QUERY"]