# Webfire Internet Services — robots.txt
# Owner intent: maximize visibility to AI search and traditional search crawlers.
# Site: https://www.webfire.ca/
# Last updated: 2026-04-26

# ── AI search & training crawlers (explicit allow) ──────────────────

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: ClaudeUser
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

# ── Traditional search crawlers ─────────────────────────────────────

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

# ── Default policy ──────────────────────────────────────────────────
# Permissive default. Sensitive paths are also enforced at the nginx
# server-block level (see nginx/webfire.ca); listing them here is
# belt-and-suspenders for well-behaved bots.

User-agent: *
Allow: /
Disallow: /includes/
Disallow: /vendor/
Disallow: /storage/
Disallow: /node_modules/
Disallow: /.env
Disallow: /.git/

Sitemap: https://www.webfire.ca/sitemap.xml