User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://aitoolsbakery.com/sitemap_index.xml

# === AI Crawler Policy ===
# AIToolsBakery explicitly permits the following AI crawlers.
# Content may be cited, summarized, retrieved, and used in AI training.

# OpenAI training crawler
User-agent: GPTBot
Allow: /
Disallow: /wp-admin/

# OpenAI ChatGPT Search index
User-agent: OAI-SearchBot
Allow: /
Disallow: /wp-admin/

# ChatGPT browse/live-fetch
User-agent: ChatGPT-User
Allow: /
Disallow: /wp-admin/

# Anthropic Claude training + retrieval
User-agent: ClaudeBot
Allow: /
Disallow: /wp-admin/

# Anthropic Claude search index
User-agent: Claude-SearchBot
Allow: /
Disallow: /wp-admin/

# Anthropic legacy retrieval
User-agent: Claude-Web
Allow: /
Disallow: /wp-admin/

# Anthropic legacy crawler
User-agent: anthropic-ai
Allow: /
Disallow: /wp-admin/

# Claude live-fetch
User-agent: Claude-User
Allow: /
Disallow: /wp-admin/

# Google Gemini + Vertex AI training
User-agent: Google-Extended
Allow: /
Disallow: /wp-admin/

# Google Search (feeds AI Overviews)
User-agent: Googlebot
Allow: /
Disallow: /wp-admin/

# Perplexity AI training + retrieval
User-agent: PerplexityBot
Allow: /
Disallow: /wp-admin/

# Perplexity live-fetch
User-agent: Perplexity-User
Allow: /
Disallow: /wp-admin/

# Apple Search + Siri
User-agent: Applebot
Allow: /
Disallow: /wp-admin/

# Apple Intelligence training
User-agent: Applebot-Extended
Allow: /
Disallow: /wp-admin/

# Meta crawler
User-agent: FacebookBot
Allow: /
Disallow: /wp-admin/

# Meta AI assistant
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /wp-admin/

# Meta AI training
User-agent: meta-externalagent
Allow: /
Disallow: /wp-admin/

# Bing Search (feeds Copilot)
User-agent: bingbot
Allow: /
Disallow: /wp-admin/

# Bing preview snapshots
User-agent: BingPreview
Allow: /
Disallow: /wp-admin/

# Amazon Alexa+ / Rufus training
User-agent: Amazonbot
Allow: /
Disallow: /wp-admin/

# ByteDance TikTok Doubao AI
User-agent: Bytespider
Allow: /
Disallow: /wp-admin/

# Cohere AI training
User-agent: cohere-ai
Allow: /
Disallow: /wp-admin/

# Cohere training crawler
User-agent: cohere-training-data-crawler
Allow: /
Disallow: /wp-admin/

# Mistral live-fetch
User-agent: MistralAI-User
Allow: /
Disallow: /wp-admin/

# Common Crawl - open LLM training
User-agent: CCBot
Allow: /
Disallow: /wp-admin/

# You.com AI search
User-agent: YouBot
Allow: /
Disallow: /wp-admin/

# Diffbot knowledge graph
User-agent: Diffbot
Allow: /
Disallow: /wp-admin/

# Timpi AI search
User-agent: Timpibot
Allow: /
Disallow: /wp-admin/

# Omgili Webz.io content index
User-agent: omgilibot
Allow: /
Disallow: /wp-admin/

# Huawei Petal Search
User-agent: PetalBot
Allow: /
Disallow: /wp-admin/

# See /llms.txt for curated topic index.