# The Common Crawl dataset. Original source for GPT and others.
User-agent: CCBot
Disallow: /

# The example for img2dataset, although the default is *None*
User-agent: img2dataset
Disallow: /

# GPTBot is OpenAI's web crawler
User-agent: GPTBot
Disallow: /

# ChatGPT-User takes direct actions on behalf of ChatGPT users
User-agent: ChatGPT-User
Disallow: /

# Google's Bard and Vertex AI generative APIs
User-agent: Google-Extended
Disallow: /

# Speculative blocks for Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# webz.io - they sell data for training LLMs.
User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

# Meta's bot that crawls public web pages to improve language models
User-agent: FacebookBot
Disallow: /

# ByteDance's bot used to gather data for their LLMs, including Doubao.
User-agent: Bytespider
Disallow: /

# Brandwatch - "AI to discover new trends"
User-agent: magpie-crawler
Disallow: /

Sitemap: https://www.mattedwards.org/sitemap.xml