{
  "almanac": "The Agentic Web Almanac",
  "description": "Canonical, machine-first reference about the agentic web. Five datasets, each queryable as JSON, served as markdown, and exposed as WebMCP tools.",
  "datasets": {
    "crawlers": {
      "title": "The AI Crawler Registry",
      "description": "Canonical reference of the AI crawlers and agent user-agents on the web (June 2026). 'purpose' is what the operator says the bot does. 'verify' is how to confirm a request claiming this UA is genuine — user-agent strings are trivially spoofed, so verification is by published IP ranges or reverse DNS. No IP addresses are listed here; we link to each operator's authoritative range file instead. This enriched edition backfills the 18 existing records to the full 25-attribute EAV depth defined in research/briefs/crawlers.md, plus S-P-O relationship triples. Every sourced value carries its primary 'source' URL and 'last_verified'; any value not confirmable from a primary source is recorded as a structured placeholder ({value:null, verify_status:'verify-against-primary-at-build', source_hint:<url>}) rather than fabricated. Bot-type enum = the cited 6-type set {training, search-index, user-action-fetcher, opt-out-token, agentic-browser, undocumented} + the Agents Welcome 'data-provider' extension (flagged as such).",
      "count": 31,
      "updated": "2026-06-15",
      "endpoints": {
        "list": "/api/crawlers",
        "item": "/api/crawlers/{id}",
        "page": "/crawlers"
      }
    },
    "protocols": {
      "title": "The Agent Protocol Atlas",
      "description": "The protocols of the agentic web (June 2026), grouped by the layer they operate at: how agents reach tools, talk to each other, prove who they are, transact, and consume content. This enriched edition adds full EAV depth per record — canonical spec source, governance, spec version + date, transport, core mechanism, discovery endpoint, adoption metric (sourced), relationship edges, and a per-record use/when-to-use/when-not-to-use decision triple plus a code example.",
      "count": 28,
      "updated": "2026-06-15",
      "endpoints": {
        "list": "/api/protocols",
        "item": "/api/protocols/{id}",
        "page": "/protocols"
      }
    },
    "models": {
      "title": "The Frontier Model Matrix",
      "description": "Context windows, output limits and pricing for the frontier LLMs an agent-builder reaches for (June 2026), enriched to full EAV depth per research/briefs/models.md. Claude rows are exact, verified against the Anthropic model catalog and AWS Bedrock model cards. Non-Anthropic rows list capability where it is publicly stable and defer pricing/context to the provider, because third-party prices move and we will not print a number we cannot vouch for. Every sourced value carries its primary source URL + last_verified; any value not confirmed against a primary source is a structured placeholder { value:null, verify_status:'verify-against-primary-at-build', source_hint:<primary URL> } rather than a guess.",
      "count": 30,
      "updated": "2026-06-15",
      "endpoints": {
        "list": "/api/models",
        "item": "/api/models/{id}",
        "page": "/models"
      }
    },
    "glossary": {
      "title": "The Agentic Web Lexicon",
      "description": "Canonical, concise definitions of the terms that make up the agentic web (June 2026). Written to be quoted: each term has a one-line short_def for citation and a longer long_def for context. This enriched edition adds full EAV depth per term — etymology/origin, related terms, nearest-neighbour contrast, a dated example, an authoritative source, status, why-it-matters, sameAs links, the Almanac bridge entity, last_verified date and a markdown-twin path.",
      "count": 57,
      "updated": "2026-06-15",
      "endpoints": {
        "list": "/api/glossary",
        "item": "/api/glossary/{id}",
        "page": "/glossary"
      }
    },
    "state-of-the-agentic-web": {
      "title": "State of the Agentic Web",
      "description": "Adoption data for the agentic web (2026): AI-crawler traffic shares, standard adoption, protocol maturity and model trends. Each figure is tagged cited (primary source) or our-measurement (with method); unconfirmed third-party figures are flagged for build-time verification, never asserted as fact.",
      "count": 21,
      "updated": "2026-06-15",
      "endpoints": {
        "list": "/api/state-of-the-agentic-web",
        "item": "/api/state-of-the-agentic-web/{id}",
        "page": "/state-of-the-agentic-web"
      }
    }
  },
  "search": "/api/search?q=<query> — one query across all five datasets",
  "verify_crawler": "/api/verify-crawler?ua=<user-agent string>"
}