# ═══════════════════════════════════════════════════════
# IAASSE ResearchOS — robots.txt
# https://researchos.iaasse.org/robots.txt
# ═══════════════════════════════════════════════════════

# Allow all well-behaved crawlers
User-agent: *
Allow: /
Allow: /sitemap.xml
Allow: /robots.txt

# Block admin and API paths
Disallow: /admin/
Disallow: /api/
Disallow: /private/
Disallow: /tmp/
Disallow: /?debug=
Disallow: /?preview=

# ── MAJOR SEARCH ENGINES ────────────────────────────────

User-agent: Googlebot
Allow: /
Crawl-delay: 2

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 3

User-agent: Slurp
Allow: /
Crawl-delay: 5

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 3

User-agent: Baiduspider
Allow: /
Crawl-delay: 5

User-agent: YandexBot
Allow: /
Crawl-delay: 5

# ── AI TRAINING CRAWLERS — blocked ──────────────────────
# Opt-out of AI training data collection

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

# ── BAD BOTS — blocked ──────────────────────────────────

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# ═══════════════════════════════════════════════════════
# Sitemaps
Sitemap: https://researchos.iaasse.org/sitemap.xml

# Host
Host: researchos.iaasse.org