# https://seekvectors.com - see /llms.txt for what this site contains.
# Our content, files and data may not be copied or used to train or feed
# AI systems. Terms: https://seekvectors.com/terms-of-use
User-agent: *
# Account and session pages - nothing to index.
Disallow: /login
Disallow: /register
Disallow: /logout
Disallow: /password/
Disallow: /profile
Disallow: /downloads
Disallow: /security
Disallow: /home
Disallow: /admin
# Search is effectively infinite - crawling it burns budget for no gain.
Disallow: /search
# File endpoints return attachments, not pages.
Disallow: /files/download/
Disallow: /full/pack/download/
Disallow: /download/limit/exceed
Disallow: /api/
Disallow: /mail/
# A tool opened with a logo preloaded (?logo=) is the same noindexed tool
# page once per logo - tens of thousands of URLs, and ~40% of Bingbot's crawl.
Disallow: /tools/*?*logo=
# Strip tracking parameters so they do not create duplicate URLs.
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
# The catalogue itself is open.
Allow: /post/
Allow: /categories/
Allow: /brands/
Allow: /tags/
Allow: /colors/
Allow: /tools/
Allow: /blog/
Allow: /storage/

# ---------------------------------------------------------------
# Answer engines. These cite sources and send readers back, so they
# get exactly the access Googlebot gets.
# ---------------------------------------------------------------

#   OAI-SearchBot       ChatGPT search index
#   ChatGPT-User        a ChatGPT user following a link
#   Claude-User         a Claude user following a link
#   Claude-SearchBot    Claude search index
#   PerplexityBot       Perplexity index
#   Perplexity-User     a Perplexity user following a link
#   DuckAssistBot       DuckDuckGo AI answers
#   Applebot            Siri and Spotlight
#   Amazonbot           Alexa
#   MistralAI-User      Le Chat
#   YouBot              You.com
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: Applebot
User-agent: Amazonbot
User-agent: MistralAI-User
User-agent: YouBot
# Account and session pages - nothing to index.
Disallow: /login
Disallow: /register
Disallow: /logout
Disallow: /password/
Disallow: /profile
Disallow: /downloads
Disallow: /security
Disallow: /home
Disallow: /admin
# Search is effectively infinite - crawling it burns budget for no gain.
Disallow: /search
# File endpoints return attachments, not pages.
Disallow: /files/download/
Disallow: /full/pack/download/
Disallow: /download/limit/exceed
Disallow: /api/
Disallow: /mail/
# A tool opened with a logo preloaded (?logo=) is the same noindexed tool
# page once per logo - tens of thousands of URLs, and ~40% of Bingbot's crawl.
Disallow: /tools/*?*logo=
# Strip tracking parameters so they do not create duplicate URLs.
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
# The catalogue itself is open.
Allow: /post/
Allow: /categories/
Allow: /brands/
Allow: /tags/
Allow: /colors/
Allow: /tools/
Allow: /blog/
Allow: /storage/

# ---------------------------------------------------------------
# AI training and dataset crawlers. The Terms of Use forbid using
# this site to train or feed AI systems: https://seekvectors.com/terms-of-use
# ---------------------------------------------------------------

#   GPTBot                        OpenAI model training
#   ClaudeBot                     Anthropic model training
#   anthropic-ai                  Anthropic (older token)
#   Claude-Web                    Anthropic (older token)
#   Google-Extended               Gemini training and grounding; not Search
#   Applebot-Extended             Apple Intelligence training; not Siri or Spotlight
#   CCBot                         Common Crawl, a source for many training sets
#   meta-externalagent            Meta AI training
#   FacebookBot                   Meta language-model training
#   cohere-ai                     Cohere
#   cohere-training-data-crawler  Cohere training data
#   Bytespider                    ByteDance
#   Diffbot                       Diffbot knowledge graph
#   ImagesiftBot                  image dataset collection
#   Timpibot                      Timpi
#   omgili                        Webz.io data feeds
#   omgilibot                     Webz.io data feeds
#   Webzio-Extended               Webz.io AI data
#   AI2Bot                        Allen Institute for AI
#   Ai2Bot-Dolma                  Allen Institute for AI datasets
#   PanguBot                      Huawei AI training
#   Kangaroo Bot                  AI data collection
#   img2dataset                   image dataset tool
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Bytespider
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: omgili
User-agent: omgilibot
User-agent: Webzio-Extended
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: PanguBot
User-agent: Kangaroo Bot
User-agent: img2dataset
Disallow: /

Sitemap: https://seekvectors.com/sitemap.xml