# robots.txt — Mărturie Athonită
# Single source of truth for crawl policy.
#
# Content preferences (contentsignals.org / IETF Draft).
# We allow AI use for training, search, and retrieval-augmented input —
# our mission is dissemination of monastic teaching with attribution.
Content-Signal: ai-train=yes, search=yes, ai-input=yes

User-agent: *
Disallow: /wp-admin/
Disallow: /api/
Allow: /wp-admin/admin-ajax.php

# ─── OpenAI ────────────────────────────────────────────────
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ─── Anthropic (3-bot framework, Sept 2025) ────────────────
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

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

User-agent: Perplexity-User
Allow: /

# ─── Google (Gemini training opt-in, separate from Googlebot) ──
User-agent: Google-Extended
Allow: /

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

# ─── Common Crawl (feeds many open ecosystems) ─────────────
User-agent: CCBot
Allow: /

# ─── Block: ByteDance crawler (rate-limit / robots.txt abuse history) ──
User-agent: Bytespider
Disallow: /

Sitemap: https://marturieathonita.ro/sitemap.xml