# Machine-readable index for assistants and tools (not a robots directive; for humans/operators).
# https://sequencetool.com/llms.txt

# ——— STANDARD CRAWLERS ———
User-agent: *
Allow: /
Disallow: /dev/
Disallow: /api/

Sitemap: https://sequencetool.com/sitemap-index.xml

# ——— AI TRAINING CRAWLERS (blocked) ———
# These scrape content for model training — no citation benefit to you.

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

# Blocking Anthropic training crawlers
User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

User-agent: cohere-ai
Disallow: /

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

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Amazonbot
Disallow: /

# ——— AI RETRIEVAL/SEARCH CRAWLERS (allowed) ———
# These fetch pages to answer user questions and cite the source — good for you.
# Explicit Disallow for /dev/ and /api/ as these blocks do not inherit wildcard rules.

User-agent: OAI-SearchBot
Allow: /
Disallow: /dev/
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /dev/
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /dev/
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /dev/
Disallow: /api/