# https://www.kuzog.com/robots.txt
#
# Everything on this site is public and intended to be read — by people, by
# search engines, and by AI agents. Nothing is disallowed.
#
# For a condensed, machine-readable brief see /llms.txt (and /llms-full.txt for
# the complete content reference). Both are generated from the site's own copy.

User-agent: *
Allow: /

# ---------------------------------------------------------------------------
# AI / LLM crawlers and assistants — explicitly welcome.
# Several of these treat the absence of a named group as a reason to back off,
# so each is listed rather than relying on the wildcard above.
# ---------------------------------------------------------------------------

# OpenAI — training, search index, and on-demand user fetches
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic — Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google — Gemini / AI Overviews grounding
User-agent: Google-Extended
Allow: /

# Common Crawl — the corpus behind many open models
User-agent: CCBot
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ByteDance
User-agent: Bytespider
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon (Alexa / Rufus)
User-agent: Amazonbot
Allow: /

# The www host is the one that serves the site; the apex 301-redirects to it.
# Every canonical, <loc> and JSON-LD @id names www, so this must too — a Sitemap
# line pointing at a redirect makes a crawler take an extra hop to a URL set it
# will then find disagrees with the host it was fetched from.
Sitemap: https://www.kuzog.com/sitemap.xml