# The Houston — Houston, Texas
# https://www.thehouston.org
# Part of the Nexcom Media Network — https://nexcom.media

User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/internal
Crawl-delay: 1


# Sitemaps
Sitemap: https://www.thehouston.org/sitemap.xml
Sitemap: https://www.thehouston.org/sitemap-news.xml

# AI / LLM discoverability — see /llms.txt for full org graph + URL surface map.
# Every named AI crawler that respects robots.txt + cites sources is a
# brand vector for The Houston. We allow them all explicitly so they don't
# have to guess from the wildcard.

# OpenAI
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: Anthropic-AI
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# Google AI / Gemini
User-agent: Google-Extended
Allow: /

# Apple
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

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

# ByteDance
User-agent: Bytespider
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /
User-agent: cohere-training-data-crawler
Allow: /

# Common Crawl (powers many LLM training sets)
User-agent: CCBot
Allow: /

# Diffbot, Andi, Mistral, DuckAssist, Brave Leo, Kagi, etc.
User-agent: Diffbot
Allow: /
User-agent: AndiBot
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: Bravebot
Allow: /
User-agent: Kagibot
Allow: /

# Traditional search engines — explicit allow keeps Google News + Bing News happy
User-agent: Googlebot
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Slurp
Allow: /
User-agent: facebookexternalhit
Allow: /