# Ancestra — Citizenship by Descent Platform
# Your roots. Your rights.
# Last updated: 2026-07-04

# ─── Default policy: full crawl access ─────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /private/
Allow: /api/og

# ─── AI / LLM crawlers — explicitly invited for GEO (Generative Engine Optimization) ───
# OpenAI family
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-Search
Allow: /

# Anthropic family
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /

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

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

# Meta AI
User-agent: FacebookBot
Allow: /
User-agent: Meta-ExternalAgent
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /

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

# Amazon
User-agent: Amazonbot
Allow: /

# ByteDance / TikTok
User-agent: Bytespider
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

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

# Diffbot
User-agent: Diffbot
Allow: /

# OMGILI / Webz
User-agent: omgili
Allow: /
User-agent: omgilibot
Allow: /

# Velen.io
User-agent: velenpublicwebcrawler
Allow: /

# Andi
User-agent: AndrBot
Allow: /

# Vercel
User-agent: Vercelbot
Allow: /

# Search engine bots (ensure full access)
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Slurp
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Baiduspider
Allow: /
User-agent: YandexBot
Allow: /
User-agent: Sogou
Allow: /

# ─── Crawl-delay: respectful but generous ──────────────────────────────────
Crawl-delay: 1

# ─── Sitemaps ──────────────────────────────────────────────────────────────
Sitemap: https://ancestra.legal/sitemap.xml
Sitemap: https://ancestra.legal/sitemap-images.xml

# ─── LLM content guide ────────────────────────────────────────────────────
# See https://ancestra.legal/llms.txt for AI/LLM content guide
# See https://ancestra.legal/llms-full.txt for comprehensive URL listing