IP = 176.58.123.62
robots.txt# I know this can just be _totally_ ignored by crawlers
# But let's hope they behave well :)
# Code: https://github.com/ellie/notes
# Source: https://darkvisitors.com/
# OpenAI, ChatGPT
# https://platform.openai.com/docs/gptbot
User-agent: GPTBot
Disallow: /
# Google AI (Bard, etc)
# https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers
User-agent: Google-Extended
Disallow: /
# Block common crawl
# I have mixed feelings on this one, but many models are trained on this data
# It is also used to bootstrap new search indices though
# https://commoncrawl.org/ccbot
User-agent: CCBot
Disallow: /
# Facebook
# https://developers.facebook.com/docs/sharing/bot/
User-agent: FacebookBot
Disallow: /
# Cohere.ai
# https://darkvisitors.com/agents/cohere-ai
User-agent: cohere-ai
Disallow: /
# Perplexity
# https://docs.perplexity.ai/docs/perplexitybot
User-agent: PerplexityBot
Disallow: /
# Anthropic
# https://darkvisitors.com/agents/anthropic-ai
User-agent: anthropic-ai
Disallow: /
# ...also anthropic
# https://darkvisitors.com/agents/claudebot
User-agent: ClaudeBot
Disallow: /
Look up this url in the url tool
https://linuxmemory.org/.well-known/acme-challenge: 404 text/html
https://linuxmemory.org/.well-known/csvm: 404 text/html
https://linuxmemory.org/.well-known/nostr.json: 404 text/html
https://linuxmemory.org/.well-known/security.txt: 404 text/html
https://linuxmemory.org/.well-known/traffic-advice: 404 text/html