# Gerris — robots.txt
# This site is published to be read and cited by search engines and AI
# assistants alike. Crawlers are welcomed, not tolerated: the services
# sold here include making other sites this readable.

User-agent: *
Allow: /

# The documented AI crawlers, welcomed by name. A named group replaces
# the wildcard group for that agent, so each Allow is written out in full.

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

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

# OpenAI — user-triggered fetch
User-agent: ChatGPT-User
Allow: /

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

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

# Anthropic — user-triggered fetch
User-agent: Claude-User
Allow: /

# Perplexity — answer index
User-agent: PerplexityBot
Allow: /

# Perplexity — user-triggered fetch
User-agent: Perplexity-User
Allow: /

# Google — Gemini training token (not a crawler)
User-agent: Google-Extended
Allow: /

# Google — Search and AI surfaces
User-agent: Googlebot
Allow: /

# Microsoft — Bing index, which also feeds Copilot answers
User-agent: Bingbot
Allow: /

# Common Crawl — the open corpus many labs train on
User-agent: CCBot
Allow: /

# Apple — Siri and Spotlight
User-agent: Applebot
Allow: /

# Apple — Apple Intelligence training token
User-agent: Applebot-Extended
Allow: /

# Meta — Meta AI
User-agent: Meta-ExternalAgent
Allow: /

# ByteDance — TikTok and Doubao
User-agent: Bytespider
Allow: /

# Amazon — Alexa and Amazon search
User-agent: Amazonbot
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Yandex
User-agent: YandexBot
Allow: /

# For language models: https://gerris.ai/llms.txt and https://gerris.ai/llms-full.txt

Sitemap: https://gerris.ai/sitemap.xml