# Author-it robots.txt
# Last updated: May 2026

User-agent: *
Allow: /
Disallow: /search
Disallow: /cdn-cgi/

# Sitemap
Sitemap: https://www.author-it.com/sitemap.xml

# -----------------------------------------------
# Major search engines
# -----------------------------------------------

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 training and LLM crawlers
# -----------------------------------------------

# OpenAI — ChatGPT browsing + training
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Google — Gemini / AI Overviews training
User-agent: Google-Extended
Allow: /

# Anthropic — Claude training
User-agent: ClaudeBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Common Crawl (feeds many open LLMs incl. LLaMA, Mistral)
User-agent: CCBot
Allow: /

# Meta — Llama training
User-agent: FacebookBot
Allow: /

# Apple — Applebot-Extended covers AI/ML training
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Amazon — Alexa + Bedrock
User-agent: Amazonbot
Allow: /

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

# Diffbot (knowledge graph, feeds AI apps)
User-agent: Diffbot
Allow: /

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

# Bytedance / Bytespider (feeds Doubao and TikTok AI)
User-agent: Bytespider
Allow: /

# Timpi (emerging EU-based AI search)
User-agent: Timpibot
Allow: /

Sitemap: https://www.author-it.com/sitemap.xml