# llms.txt for https://ish.li
# Last updated: 2025-08-20
# This file defines permissions and restrictions for Large Language Model (LLM) crawlers.

# ========================
# Global Defaults
# ========================
User-agent: *
Allow: /blog/
Allow: /articles/
Allow: /photos/
Disallow: /wp-admin/
Disallow: /private/
Disallow: /drafts/
Disallow: /premium/
Disallow: /cgi-bin/
Contact: ishay.lindenberg@gmail.com
Crawl-delay: 86400  # once per day

# ========================
# OpenAI (GPTBot)
# ========================
User-agent: GPTBot
Allow: /blog/
Allow: /articles/
Allow: /photos/
Disallow: /premium/
Disallow: /private/
Disallow: /drafts/
Policy: no-commercial-use
Attribution: required
Contact: ishay.lindenberg@gmail.com
Crawl-delay: 86400

# ========================
# Anthropic (ClaudeBot)
# ========================
User-agent: ClaudeBot
Allow: /blog/
Allow: /articles/
Allow: /photos/
Disallow: /premium/
Disallow: /private/
Disallow: /drafts/
Policy: no-commercial-use
Attribution: required
Contact: ishay.lindenberg@gmail.com
Crawl-delay: 86400

# ========================
# Google DeepMind
# ========================
User-agent: Google-Extended
Allow: /blog/
Allow: /articles/
Allow: /photos/
Disallow: /premium/
Disallow: /private/
Disallow: /drafts/
Policy: research-only
Attribution: required
Contact: ishay.lindenberg@gmail.com
Crawl-delay: 86400

# ========================
# Perplexity AI
# ========================
User-agent: PerplexityBot
Allow: /blog/
Allow: /articles/
Allow: /photos/
Disallow: /premium/
Disallow: /private/
Disallow: /drafts/
Policy: must-link
Attribution: required
Contact: ishay.lindenberg@gmail.com
Crawl-delay: 86400

# ========================
# CommonSense Notes
# ========================
# - This site allows LLMs to learn from public blog posts & photos,
#   but prohibits training on private, draft, and premium content.
# - Commercial use requires explicit licensing.
# - Attribution (link back to https://ish.li) is required.
# - Please respect the crawl frequency of once per day.