# Incubateer, marketing site
# Welcome, crawlers. Index us. Quote us.

User-agent: *
Allow: /
Disallow: /private/

# AI crawlers, explicitly allowed. The wildcard above already permits them;
# these are named because several only read their own block, and because the
# intent is worth stating: we want to be quoted, with attribution, by every
# answer engine. Two kinds of agent matter and they are not the same bot.
# Training crawlers (GPTBot, ClaudeBot, Google-Extended, CCBot) decide whether
# a model ever learns the site exists. Search and fetch agents (OAI-SearchBot,
# Claude-SearchBot, PerplexityBot, ChatGPT-User) decide whether it can be cited
# in an answer today. Blocking the second kind is the common own goal.

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google, Apple, Meta, Amazon
User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Amazonbot
Allow: /

# Open corpora and the rest
User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

Sitemap: https://incubateer.com/sitemap.xml

# AI-friendly metadata
# See: https://incubateer.com/llms.txt