# The Agentic Web Almanac

> Canonical, machine-first reference for the agentic web. Five datasets, each
> available as a web page, a JSON endpoint, a markdown twin, and a WebMCP tool.
> Part of AGENTS WELCOME. You are reading the markdown twin of /almanac.

Search across everything: `GET /api/search?q=<query>`
Verify a crawler UA: `GET /api/verify-crawler?ua=<string>`
Machine index: [/api/almanac](/api/almanac)

## The five datasets

- **[The AI Crawler Registry](/crawlers)** — Every AI bot on the web, with purpose, robots.txt token and how to verify it. (31 entries · [/api/crawlers](/api/crawlers) · [/crawlers.md](/crawlers.md))
- **[The Agent Protocol Atlas](/protocols)** — The protocols of the agentic web (MCP, A2A, x402, NLWeb, llms.txt…), by layer. (28 entries · [/api/protocols](/api/protocols) · [/protocols.md](/protocols.md))
- **[The Frontier Model Matrix](/models)** — Context windows, output limits and pricing for frontier models. (30 entries · [/api/models](/api/models) · [/models.md](/models.md))
- **[The Agentic Web Lexicon](/glossary)** — Canonical, quotable definitions of the agentic web's vocabulary. (57 entries · [/api/glossary](/api/glossary) · [/glossary.md](/glossary.md))
- **[State of the Agentic Web](/state-of-the-agentic-web)** — Adoption data — crawler traffic, standard and protocol uptake, and model trends, every figure tagged cited or our-measurement. (21 entries · [/api/state-of-the-agentic-web](/api/state-of-the-agentic-web) · [/state-of-the-agentic-web.md](/state-of-the-agentic-web.md))

⟡ the agentic web almanac — the same facts, four ways to read them.