# Music Existence — https://musicexistence.com
# Source of truth for this file lives in the MusicExistence repo.

# ---------------------------------------------------------------------------
# AI assistants and answer engines: explicitly welcome.
# Named individually so they are not caught by any future default rules, and
# given no crawl delay so they can actually work through ~19,700 posts.
# ---------------------------------------------------------------------------
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: CCBot
Allow: /

# Exa crawls ~2 pages a second across the whole archive; welcome, but paced.
User-agent: ExaSearchBot
Allow: /
Crawl-delay: 2

# ---------------------------------------------------------------------------
# Search engines.
# ---------------------------------------------------------------------------
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
Allow: /

# ---------------------------------------------------------------------------
# Aggressive SEO-metrics crawlers: no traffic value, real server cost.
# ---------------------------------------------------------------------------
User-agent: DotBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# ---------------------------------------------------------------------------
# Everyone else. No blanket Crawl-delay: it was 10 seconds, which meant a full
# crawl of the archive took ~55 hours and throttled AI ingestion badly.
# Varnish and CloudFront absorb the load.
# ---------------------------------------------------------------------------
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://musicexistence.com/wp-sitemap.xml
Sitemap: https://musicexistence.com/news-sitemap.xml
# LLM-readable site map: https://musicexistence.com/llms.txt