{
  "name": "GitHub Machine Beacon",
  "updated": "2026-06-15",
  "keyword_groups": [
    {
      "name": "machine-readable web discovery",
      "intent": "Signals for crawlers and search indexes that prefer structured, canonical resources.",
      "terms": [
        "machine-readable repository",
        "crawler-friendly GitHub project",
        "GitHub Pages metadata",
        "sitemap.xml",
        "robots.txt",
        "structured data",
        "JSON-LD",
        "Open Graph metadata",
        "canonical URL",
        "Atom feed",
        "RSS feed",
        "web crawler observability"
      ]
    },
    {
      "name": "AI and LLM discovery",
      "intent": "Signals for retrieval systems, AI coding tools, and agent browsers.",
      "terms": [
        "llms.txt",
        "LLM crawler",
        "AI agent browser",
        "AI search indexing",
        "retrieval augmented generation",
        "RAG source",
        "agent-readable documentation",
        "machine context file",
        "AI code search",
        "LLM metadata",
        "crawler manifest",
        "semantic README"
      ]
    },
    {
      "name": "GitHub repository discovery",
      "intent": "Signals that help repository search, code search, and topic-based browsing.",
      "terms": [
        "GitHub search optimization",
        "GitHub repository metadata",
        "GitHub topics",
        "README structure",
        "code indexing",
        "open source discoverability",
        "repository traffic experiment",
        "GitHub Insights traffic",
        "GitHub Pages deployment",
        "open research repository",
        "software citation",
        "CITATION.cff"
      ]
    },
    {
      "name": "measurement and ethics",
      "intent": "Signals that the project is an observable, non-deceptive experiment.",
      "terms": [
        "crawler experiment",
        "traffic measurement",
        "ethical SEO",
        "transparent metadata",
        "no fake traffic",
        "no cloaking",
        "privacy-preserving analytics",
        "search experiment",
        "bot traffic research",
        "machine traffic benchmark",
        "crawlability audit",
        "public web observability"
      ]
    }
  ],
  "page_keywords": [
    {
      "title": "Machine-Readable Repository Checklist",
      "url": "https://beacon.ybliterature.com/machine-readable-repository-checklist.html",
      "keywords": [
        "machine-readable repository checklist",
        "GitHub README structure",
        "crawler-friendly documentation",
        "AI agent documentation",
        "repository metadata"
      ]
    },
    {
      "title": "Crawler Surface Map",
      "url": "https://beacon.ybliterature.com/crawler-surface-map.html",
      "keywords": [
        "crawler surface map",
        "crawler entry points",
        "GitHub Pages metadata",
        "repository discovery",
        "web crawler observability"
      ]
    },
    {
      "title": "AI Agent Entrypoints",
      "url": "https://beacon.ybliterature.com/ai-agent-entrypoints.html",
      "keywords": [
        "AI agent entrypoints",
        "LLM crawler",
        "llms.txt",
        "agent-readable documentation",
        "RAG source"
      ]
    },
    {
      "title": "Experiment Protocol",
      "url": "https://beacon.ybliterature.com/experiment-protocol.html",
      "keywords": [
        "repository traffic experiment",
        "GitHub Insights traffic",
        "crawler experiment protocol",
        "public web observability",
        "bot traffic research"
      ]
    },
    {
      "title": "Standards and Sources",
      "url": "https://beacon.ybliterature.com/standards-and-sources.html",
      "keywords": [
        "GitHub topics documentation",
        "GitHub Pages Actions",
        "Schema.org JSON-LD",
        "llms.txt proposal",
        "sitemap robots Atom feed"
      ]
    },
    {
      "title": "Crawlability Audit",
      "url": "https://beacon.ybliterature.com/crawlability-audit.html",
      "keywords": [
        "crawlability audit",
        "machine-readable audit",
        "GitHub Pages audit",
        "metadata validation",
        "crawler readiness"
      ]
    },
    {
      "title": "Results Log",
      "url": "https://beacon.ybliterature.com/results-log.html",
      "keywords": [
        "GitHub traffic log",
        "crawler experiment results",
        "repository views",
        "unique visitors",
        "traffic measurement"
      ]
    }
  ]
}