# robots.txt for factstore.io
#
# FactStore is an open-source project. Its documentation is meant to be read,
# indexed, quoted and learned from — by people, by search engines and by AI
# systems alike. Everything here is public and permissively licensed, so the
# default answer is yes.

User-agent: *
Allow: /

# ---------------------------------------------------------------------------
# Search engine crawlers
# ---------------------------------------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# ---------------------------------------------------------------------------
# AI training and retrieval crawlers
#
# Listed explicitly rather than left to the wildcard above. Several of these
# agents look for a rule naming them specifically, and an explicit Allow is a
# clearer statement of intent than silence — which some operators treat
# conservatively.
# ---------------------------------------------------------------------------

# OpenAI — model training
User-agent: GPTBot
Allow: /

# OpenAI — ChatGPT browsing on a user's behalf
User-agent: ChatGPT-User
Allow: /

# OpenAI — search index
User-agent: OAI-SearchBot
Allow: /

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

# Anthropic — Claude browsing on a user's behalf
User-agent: Claude-User
Allow: /

# Anthropic — search index
User-agent: Claude-SearchBot
Allow: /

# Anthropic — legacy agent name
User-agent: anthropic-ai
Allow: /

# Google — Gemini and Vertex AI grounding
User-agent: Google-Extended
Allow: /

# Google — AI agents acting for a user
User-agent: Google-CloudVertexBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

User-agent: FacebookBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Mistral AI
User-agent: MistralAI-User
Allow: /

# Common Crawl — a major input to most open training corpora
User-agent: CCBot
Allow: /

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

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

User-agent: cohere-training-data-crawler
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# Timpi
User-agent: Timpibot
Allow: /

# ---------------------------------------------------------------------------
# Machine-readable pointers
# ---------------------------------------------------------------------------

Sitemap: https://factstore.io/sitemap.xml