# robots.txt — https://www.ogeninfo.com
# Every search engine and answer engine is welcome to crawl the whole public site.
# Only dataset scrapers and website-copier tools are asked to stay out (they are also blocked in .htaccess).

User-agent: *
Allow: /
Disallow: /site-admin/
Disallow: /projects/
Disallow: /ajax/
Disallow: /PHPMailer/
Disallow: /projects/2026/
Disallow: /includei/
Disallow: /bck/
Disallow: /*_preview
Disallow: /*?*session_val=

# Dataset scrapers and site copiers
User-agent: Bytespider
User-agent: Diffbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Omgili
User-agent: Timpibot
User-agent: PanguBot
User-agent: Kangaroo Bot
User-agent: img2dataset
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: FriendlyCrawler
User-agent: ICC-Crawler
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: Brightbot
User-agent: HTTrack
User-agent: WebCopier
User-agent: WebZIP
User-agent: Offline Explorer
User-agent: Teleport
User-agent: TeleportPro
User-agent: SiteSnagger
User-agent: WebStripper
User-agent: WebReaper
User-agent: SiteSucker
User-agent: Wget
Disallow: /

Sitemap: https://www.ogeninfo.com/sitemap.xml
Sitemap: https://www.ogeninfo.com/blog/sitemap.xml