# robots.txt for https://gyrus.ai
# Last updated: 2026-06
# Policy: allow search and AI crawlers full access for discovery and citation.
# AI-specific guidance for LLMs is provided separately in /llms.txt

# -----------------------------------------------------------------------------
# Default rule — all well-behaved crawlers may access the whole site
# -----------------------------------------------------------------------------
User-agent: *
Allow: /

# -----------------------------------------------------------------------------
# Search engine crawlers (explicitly allowed)
# Bing matters specifically: ChatGPT Search retrieves results via the Bing index.
# -----------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# -----------------------------------------------------------------------------
# AI / LLM crawlers (explicitly allowed so Gyrus AI can be discovered and cited)
# -----------------------------------------------------------------------------

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google generative AI (Gemini / AI Overviews training signal)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (feeds many model training sets)
User-agent: CCBot
Allow: /

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

# Amazon
User-agent: Amazonbot
Allow: /

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

# --- Sitemap ---
Sitemap: https://gyrus.ai/sitemap.xml
Sitemap: https://gyrus.ai/images_sitemap.xml