User-agent: *
Allow: /
Content-signal: search=yes, ai-input=yes, ai-train=no
Allow: /git/elements/
Disallow: /api/
Disallow: /ping
Disallow: /get-data
Disallow: /404
Disallow: /503
Disallow: /git
Allow: /git/
Disallow: /git/*/*/
Disallow: /git/api/
Disallow: /git/empz/foundation

# retrieval bots, and search engines - welcome to read and cite empz.co.uk, with attribution
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: FirecrawlAgent
User-agent: TavilyBot
User-agent: ExaBot
User-agent: Crawl4AI
User-agent: Cloudflare-AutoRAG
User-agent: ChatGPT Agent
User-agent: Operator
User-agent: Google-Agent
User-agent: GoogleAgent-Mariner
User-agent: NovaAct
User-agent: Manus-User
User-agent: TwinAgent
User-agent: NotebookLM
User-agent: Devin
User-agent: Cursor
User-agent: Claude-Code
User-agent: Code
User-agent: opencode
User-agent: Trae
User-agent: Google-Gemini-CLI
User-agent: PetalBot
User-agent: Sogou web spider
User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: YandexBot
User-agent: Baiduspider
User-agent: Yeti
Allow: /
Content-signal: search=yes, ai-input=yes, ai-train=no
Allow: /git/elements/
Disallow: /api/
Disallow: /ping
Disallow: /get-data
Disallow: /404
Disallow: /503
Disallow: /git
Allow: /git/
Disallow: /git/*/*/
Disallow: /git/api/
Disallow: /git/empz/foundation

# AI-training and model-building crawlers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: TikTokSpider
User-agent: Amazonbot
User-agent: bedrockbot
User-agent: amazon-kendra
User-agent: amazon-QBusiness
User-agent: AmazonBuyForMe
User-agent: CloudVertexBot
User-agent: Google-CloudVertexBot
User-agent: Google-Firebase
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: cohere-training-data-crawler
User-agent: DeepSeekBot
User-agent: ChatGLM-Spider
User-agent: PanguBot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: AI2Bot-DeepResearchEval
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: imageSpider
User-agent: img2dataset
User-agent: LAIONDownloader
User-agent: laion-huggingface-processor
User-agent: Timpibot
User-agent: Webzio-Extended
User-agent: webzio-extended
User-agent: omgili
User-agent: omgilibot
User-agent: Diffbot
User-agent: FriendlyCrawler
User-agent: Kangaroo Bot
User-agent: magpie-crawler
User-agent: peer39_crawler
User-agent: Factset_spyderbot
User-agent: ISSCyberRiskCrawler
User-agent: SBIntuitionsBot
User-agent: Cotoyogi
User-agent: Poseidon Research Crawler
User-agent: VelenPublicWebCrawler
User-agent: Sidetrade indexer bot
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: Brightbot
User-agent: Brightbot 1.0
User-agent: aiHitBot
User-agent: Awario
User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: Datenbank Crawler
User-agent: netEstate Imprint Crawler
User-agent: MyCentralAIScraperBot
User-agent: NagetBot
User-agent: newsai
User-agent: LCC
User-agent: WARDBot
User-agent: Thinkbot
User-agent: YaK
User-agent: QuillBot
User-agent: quillbot.com
User-agent: Panscient
User-agent: panscient.com
User-agent: TerraCotta
User-agent: Terra Cotta
User-agent: HenkBot
User-agent: KunatoCrawler
User-agent: Reflectionbot
User-agent: CragCrawler
User-agent: Crawlspace
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Spider
User-agent: Lightpanda
User-agent: Mozilla-Tabstack
User-agent: Linguee Bot
User-agent: atlassian-bot
Disallow: /

# unclear-purpose and marketing agents
User-agent: Shap-User
User-agent: ShapBot
User-agent: QueritBot
User-agent: BuddyBot
User-agent: Anomura
User-agent: KlaviyoAIBot
User-agent: QualifiedBot
User-agent: wpbot
User-agent: UseAI
User-agent: WRTNBot
User-agent: AgentTimes
Disallow: /

# generic scrapers
User-agent: Scrapy
User-agent: DataForSeoBot
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: SEOkicks
User-agent: spbot
User-agent: SerpstatBot
User-agent: ZoominfoBot
User-agent: Barkrowler
User-agent: MegaIndex
Disallow: /

Sitemap: https://empz.co.uk/sitemap.xml
Sitemap: https://empz.co.uk/git/sitemap.xml

# Guide for agents - https://empz.co.uk/llms.txt
# Please read our robotic activity notice - https://empz.co.uk/legal

# We love robots! :)