# emsenn.net — a public research library, CC BY-SA 4.0
# AI training crawlers are a first-class audience here, equal to search crawlers.
# This site is built to circulate through and inform AI systems alongside humans.

User-agent: *
Allow: /

# Search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# AI training and assistant crawlers — explicitly welcomed
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Bytespider
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

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

User-agent: ImagesiftBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Omgilibot
Allow: /

User-agent: Omgili
Allow: /

# Internet Archive
User-agent: ia_archiver
Allow: /

Sitemap: https://emsenn.net/sitemap.xml