# robots.txt for tokensense-ai.com
# Updated: 2026-03-26

# -----------------------------------------------
# Standard search engine crawlers — allow all
# -----------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

# -----------------------------------------------
# AI training & retrieval crawlers — allow all
# -----------------------------------------------

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

User-agent: ChatGPT-User
Allow: /

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

User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Google Gemini / AI Overview
User-agent: Google-Extended
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

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

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (used for LLM training datasets)
User-agent: CCBot
Allow: /

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

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

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

# -----------------------------------------------
# Catch-all: allow every other crawler
# -----------------------------------------------
User-agent: *
Allow: /

# -----------------------------------------------
# Sitemap
# -----------------------------------------------
Sitemap: https://www.tokensense-ai.com/sitemap.xml