# agitate-discourse.org — robots.txt
#
# AI-training crawlers are disallowed site-wide. Users' arguments and opinions
# are not offered up as model-training data; the Data Promise
# (https://agitate-discourse.org/data-promise) cites this file as evidence.
# Ordinary search-engine crawling remains welcome (see the final block).

# --- OpenAI (training) ---
User-agent: GPTBot
Disallow: /

# --- Anthropic (training) ---
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# --- Google generative-AI training (does not affect Google Search) ---
User-agent: Google-Extended
Disallow: /

# --- Common Crawl (primary corpus for many model trainers) ---
User-agent: CCBot
Disallow: /

# --- Meta (training) ---
User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

# --- Apple Intelligence training (does not affect Siri/Spotlight indexing) ---
User-agent: Applebot-Extended
Disallow: /

# --- ByteDance / TikTok ---
User-agent: Bytespider
Disallow: /

# --- Cohere ---
User-agent: cohere-ai
Disallow: /

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

# --- Perplexity ---
User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

# --- Data brokers / scraping corpora resold for training ---
User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

# --- Allen Institute for AI ---
User-agent: AI2Bot
Disallow: /

# --- Everyone else (ordinary search engines etc.): crawl freely ---
User-agent: *
Disallow: