# SUNNY M Lab — robots.txt
# Policy: Allow search, AI retrieval, and social preview agents.
# Restrict API paths, bulk SEO scrapers, and training-only crawlers.
# Last updated: 2026-05

# ─── Content Signal ────────────────────────────────────
# Informational signal for AI systems that respect it.
Content-Signal: search=yes,ai-input=yes,ai-train=no

# ─── Default ───────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/

# ─── Search Engines ────────────────────────────────────
User-agent: Googlebot
Allow: /
Disallow: /api/

User-agent: Bingbot
Allow: /
Disallow: /api/

User-agent: Slurp
Allow: /
Disallow: /api/

User-agent: DuckDuckBot
Allow: /
Disallow: /api/

# ─── AI Search + Retrieval Agents ─────────────────────
User-agent: GPTBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: Claude-SearchBot
Allow: /
Disallow: /api/

User-agent: Claude-User
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: YouBot
Allow: /
Disallow: /api/

User-agent: Applebot
Allow: /
Disallow: /api/

User-agent: Amazonbot
Allow: /
Disallow: /api/

# ─── Social Preview Crawlers ──────────────────────────
User-agent: Twitterbot
Allow: /
Disallow: /api/

User-agent: LinkedInBot
Allow: /
Disallow: /api/

User-agent: facebookexternalhit
Allow: /
Disallow: /api/

# ─── Training Crawlers (restricted) ───────────────────
User-agent: CCBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# ─── Aggressive SEO / Bulk Scrapers ───────────────────
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# ─── Sitemap ───────────────────────────────────────────
Sitemap: https://sunnymlab.com/sitemap-index.xml