# cweird.com — Chris Weir (c.weird), Oakland, CA
# Search engines and AI assistants: indexing, quoting, summarizing and linking are welcome.
# Training, fine-tuning or dataset use of anything here (images, video, text) is NOT permitted
# without a written license. Full policy: https://cweird.com/ai-policy
# Machine-readable: the Content-Signal line below (contentsignals.org), the tdm-reservation
# header on every response, /.well-known/tdmrep.json, X-Robots-Tag noai/noimageai on images,
# the IPTC Data Mining field inside each image file, and (Microsoft has no robots.txt training
# token) <meta name="bingbot" content="nocache"> on every page.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
# Client documents and the API — not for indexing
Disallow: /quote/
Disallow: /api/

# ---- Training crawlers: no ----
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: CCBot
User-agent: Bytespider
User-agent: MistralAI-Training
User-agent: cohere-ai
User-agent: Diffbot
User-agent: img2dataset
User-agent: omgili
User-agent: omgilibot
Disallow: /

# ---- Search, answer and user-requested fetches: yes ----
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: meta-externalfetcher
User-agent: meta-webindexer
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: MistralAI-Index
User-agent: MistralAI-User
Allow: /
Disallow: /quote/
Disallow: /api/

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

# LLM context file — see https://llmstxt.org
LLMsTxt: https://cweird.com/llms.txt