# kolaboro.com robots.txt
# Search engines and AI answer engines are welcome to crawl, index and cite the public pages and the open data (CC BY 4.0).
# One group for everyone, so the same rules apply to every crawler named here and to all others.
# Reviewed 14 Nov 2026 (n29t): public pages, /data/, /api/open/, /llms.txt and the sitemaps are open; only private, POST-only and Cloudflare paths are closed.
User-agent: *
User-agent: Googlebot
User-agent: Google-Extended
User-agent: Bingbot
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: CCBot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: DuckAssistBot
User-agent: YandexBot
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: MistralAI-User
User-agent: Google-CloudVertexBot
User-agent: Baiduspider
User-agent: SeznamBot
User-agent: PetalBot
Allow: /
Disallow: /admin
Disallow: /backup-admin/
Disallow: /portal
Disallow: /confirm-email/
Disallow: /reset/
Disallow: /shared/
Disallow: /agents/me
Disallow: /login
Disallow: /thanks
Disallow: /watchlist/
Disallow: /saved/
Disallow: /old/
# endpoints that only answer POST from our own pages, and Cloudflare's own paths (n25e: they showed as 404 in Search Console)
Disallow: /api/kb/analyze
Disallow: /api/kb/progress
Disallow: /api/kb/ask
Disallow: /api/kb/document
Disallow: /api/kb/plan
Disallow: /api/kb/report-draft
Disallow: /api/kb/csp
Disallow: /api/x/b/
Disallow: /cdn-cgi/

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