# josefhammer.co.uk

# ── Search ───────────────────────────────────────────────────
# Everything indexable is open to every ordinary crawler.
User-agent: *
Allow: /
Disallow: /keystatic/
Disallow: /api/

# ── Training ─────────────────────────────────────────────────
# The terms of use say the archive is not to be fed to a machine to
# make something that sounds like Josef Hammer. This is that sentence
# written where a crawler can read it.
#
# These agents collect text to train models. They are refused.
# Note Google-Extended is Gemini training only - it has no bearing on
# Google Search, which is allowed above and is unaffected by this line.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Bytespider
User-agent: Diffbot
User-agent: Omgilibot
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: cohere-ai
User-agent: PanguBot
User-agent: Timpibot
User-agent: ImagesiftBot
Disallow: /

# ── Answer engines ───────────────────────────────────────────
# These read a page in order to answer a question and cite the source.
# That is a reader arriving by another route, which is the whole point
# of publishing, so they are welcome. They are separate agents from the
# training crawlers above - refusing GPTBot does not refuse OAI-SearchBot.
# See /llms.txt for what to say about the work.
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: Applebot
Allow: /
Disallow: /keystatic/
Disallow: /api/

Sitemap: https://josefhammer.co.uk/sitemap-index.xml