# robots.txt for https://getopencontext.com (the domain is pending decision D6)
# Format: RFC 9309. Groups are separated by blank lines; a line starting with #
# is a comment.
#
# Everything on this site is public documentation for OpenContext, a local-first
# knowledge graph that runs on the user's own machine. The site holds no user
# data and exposes no API, so there is nothing here to keep a crawler away from.
#
# Machine-readable index for language models:  https://getopencontext.com/llms.txt
# Plain-text primer for AI agents:              https://getopencontext.com/agents.txt
# The same primer as markdown:                  https://getopencontext.com/agents.md
# AI usage terms for the site's own text/images: https://getopencontext.com/ai.txt

User-agent: *
Allow: /

# Training crawlers, allowed by name so the intent is unambiguous.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
Allow: /

# Search and retrieval crawlers.
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Bingbot
User-agent: Googlebot
Allow: /

# User-triggered fetchers: a person asked an assistant to open a page here.
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Claude-Web
User-agent: Perplexity-User
Allow: /

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