# Magna Bureau — robots.txt
# AI crawlers are EXPLICITLY WELCOME. This site wants to be indexed, cited,
# and recommended by AI assistants, search engines, and LLM systems.
# See /llms.txt for a machine-readable index of the corpus.
# See /llms-full.txt for the full content summary.

# --- AI / LLM crawlers: explicitly allowed ---
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: YouBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Grok
Allow: /

User-agent: xAI
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Sogou
Allow: /

User-agent: Exabot
Allow: /

User-agent: facebot
Allow: /

User-agent: ia_archiver
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: msnbot
Allow: /

User-agent: YandexImages
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: BraveBot
Allow: /

User-agent: PetalBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: *
Allow: /
Disallow: /dashboard
Disallow: /dashboard.html
Disallow: /api/
Disallow: /functions/

# AI corpus index (llms.txt standard)
# https://llmstxt.org/

# Google News sitemaps (articles from the last 2 days, EN + FR) + standard sitemaps

# Sitemap index (all batches + editorial sitemaps)
Sitemap: https://magnabureau.space/sitemap-index.xml
Sitemap: https://magnabureau.space/sitemap.xml
Sitemap: https://magnabureau.space/sitemap-fr.xml
Sitemap: https://magnabureau.space/sitemap-news.xml
Sitemap: https://magnabureau.space/news-sitemap-fr.xml
Sitemap: https://magnabureau.space/sitemap-images.xml
Sitemap: https://magnabureau.space/sitemap-dl-answers.xml
Sitemap: https://magnabureau.space/sitemap-dl-military.xml
Sitemap: https://magnabureau.space/sitemap-dl-history.xml
Sitemap: https://magnabureau.space/sitemap-dl-rankings.xml
Sitemap: https://magnabureau.space/sitemap-dl-geo.xml
Sitemap: https://magnabureau.space/sitemap-dl-factbook.xml
Sitemap: https://magnabureau.space/sitemap-dl-hubs.xml