# robots.txt — MiRV ELEMENTS
# https://mirvelements.com
#
# Policy: all substantive content on this site is public marketing copy and is
# intentionally open to search engines AND to AI / LLM crawlers. Generative
# engines are a primary discovery channel for this business, so every known AI
# agent is named and permitted explicitly rather than left to default handling.

# ---------------------------------------------------------------------------
# Default — everything is crawlable
# ---------------------------------------------------------------------------
User-agent: *
Allow: /

# ---------------------------------------------------------------------------
# Traditional search engines
# ---------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# ---------------------------------------------------------------------------
# OpenAI
# GPTBot        — trains / indexes for ChatGPT
# ChatGPT-User  — live fetch when a user asks ChatGPT to browse
# OAI-SearchBot — indexes for ChatGPT Search
# ---------------------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# ---------------------------------------------------------------------------
# Anthropic (Claude)
# ---------------------------------------------------------------------------
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

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

User-agent: Perplexity-User
Allow: /

# ---------------------------------------------------------------------------
# Google AI surfaces (Gemini, AI Overviews, Vertex grounding)
# Google-Extended is an opt-OUT token: an empty Disallow is how permission is
# expressed. There is no stronger "allow" signal available for it.
# ---------------------------------------------------------------------------
User-agent: Google-Extended
Allow: /
Disallow:

# ---------------------------------------------------------------------------
# Apple Intelligence — same opt-out token semantics as Google-Extended
# ---------------------------------------------------------------------------
User-agent: Applebot-Extended
Allow: /
Disallow:

# ---------------------------------------------------------------------------
# Common Crawl — the corpus behind a large share of open LLM training sets
# ---------------------------------------------------------------------------
User-agent: CCBot
Allow: /

# ---------------------------------------------------------------------------
# Amazon
# ---------------------------------------------------------------------------
User-agent: Amazonbot
Allow: /

# ---------------------------------------------------------------------------
# Meta AI
# ---------------------------------------------------------------------------
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# ---------------------------------------------------------------------------
# Others
# ---------------------------------------------------------------------------
User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

# ---------------------------------------------------------------------------
Sitemap: https://mirvelements.com/sitemap.xml