AI Crawler Index Status API

openapi: 3.2.0
info:
  title: AI Crawler Index Status API
  version: '2026-09-01'
  summary: Every AI crawler on the web, what it is for, what blocking it costs you, and the IP ranges its operator publishes — as JSON, CSV, robots.txt and regex.
  description: 'A read-only, static, keyless index of 56 web crawlers operated by 30 companies and projects: what each one is for, the exact robots.txt token and user-agent substring, whether the operator says it obeys robots.txt, how to verify it is genuine, and — the part nobody else publishes — what you lose by blocking it.'
  license:
    name: CC0-1.0
    url: https://creativecommons.org/publicdomain/zero/1.0/
  contact:
    url: https://www.pathwren.workers.dev/about.html
servers:
- url: https://www.pathwren.workers.dev
tags:
- name: Status
  description: Freshness of the upstream sources.
paths:
  /status.json:
    get:
      summary: Freshness and health of every upstream IP-range endpoint
      operationId: getStatus
      tags:
      - Status
      responses:
        '200':
          description: Per-source fetch state
          content:
            application/json:
              schema:
                type: object
                properties:
                  sources_ok:
                    type: integer
                  sources_failed:
                    type: integer
                  generated_at:
                    type: string
                    format: date-time
  /feed.json:
    get:
      summary: JSON Feed 1.1 of what changed
      operationId: getFeed
      tags:
      - Status
      responses:
        '200':
          description: JSON Feed
          content:
            application/feed+json: {}