#       *******                        **       **
#      **/////**                      /**      /**
#     **     //** **   ** ******      /**   *  /**  ******   **    **  *****
#    /**      /**/**  /**//**//*      /**  *** /** //////** /**   /** **///**
#    /**      /**/**  /** /** /       /** **/**/**  ******* //** /** /*******
#    //**     ** /**  /** /**         /**** //**** **////**  //****  /**////
#     //*******  //******/***         /**/   ///**//********  //**   //******
#      ///////    ////// ///          //       //  ////////    //     //////
#
#
#    We thought you'd never make it!
#    We hope you feel right at home in this file...unless you're a disallowed subfolder.
#    And since you're here, read up on our culture and team: https://www.ourwave.org/who-we-are
#    There's even a bring your robot to work day.

User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Bytespider
User-agent: Diffbot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: ICC-Crawler
User-agent: ISSCyberRiskCrawler
User-agent: ImagesiftBot
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: PetalBot
User-agent: Scrapy
User-agent: Sidetrade indexer bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
User-agent: cohere-ai
User-agent: iaskspider/2.0
User-agent: img2dataset
User-agent: omgili
User-agent: omgilibot
Disallow: /

# AI training crawlers (including Amazonbot, which also trains) stay out of survivor-written content. AI search crawlers are not listed
# here, so they follow the * rules and can still cite these pages with a link back.
# Crawlers obey only their most specific group, so the * disallows are repeated below.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
Disallow: /story/
Disallow: /*/story/
Disallow: /shared-activity/
Disallow: /*/shared-activity/
Disallow: /message/
Disallow: /*/message/
Disallow: /gallery
Disallow: /*/gallery
Disallow: /api/
Disallow: /cgi-bin/
Disallow: /logout
Disallow: /_external/link

User-agent: *
Allow: /llms.txt
Allow: /llms-collection-activities.md
Allow: /llms-collection-questions.md
Allow: /llms-collection-question-topics.md
Allow: /llms-collection-resources.md
Disallow: /cgi-bin/
Disallow: /logout
Disallow: /_external/link

Sitemap: https://www.wespeak.ie/sitemap.xml

# Large Language Models (LLMs) and other AI models can find structured info here: https://www.wespeak.ie/llms.txt