When someone asks ChatGPT "what's the best project management tool?" does your product show up in the answer? A new open-source tool called XanLens tries to answer that question systematically across seven AI engines at once.
GEO (Generative Engine Optimization) is the emerging practice of making your brand visible in AI-generated answers, the same way SEO targets Google search results. XanLens automates the audit process: give it your website URL, and it scrapes your site to identify your brand, industry, competitors, and keywords. Then it generates 30+ prompts across three categories - industry queries (65%), competitor comparisons (30%), and brand awareness checks (5%) - and fires them at ChatGPT (GPT-4o), Claude, Gemini, Grok, DeepSeek, Llama, and Qwen simultaneously.
An LLM judge then verifies the responses are actually about your brand (catching name collisions) and rates accuracy and citation quality. The output is a 0-100 visibility score plus specific content recommendations for improving your AI presence.
The tool is built with Next.js 15 and TypeScript, uses Turso/LibSQL for storage, and is MIT-licensed for self-hosting. There's also a hosted version at xanlens.com with pay-per-audit pricing if you don't want to run it yourself.
For marketers and small business owners, the value proposition is clear: AI assistants are increasingly where people start their research instead of Google, and most businesses have zero visibility into how they're represented in those answers. Running an audit like this is the GEO equivalent of checking your Google search ranking for the first time.
The limitation is obvious too. AI model responses aren't deterministic - ask the same question twice and you might get different brand mentions. XanLens addresses this with volume (30+ prompts) but a single audit is still a snapshot, not a trend line. Still, for a free tool, it's a practical starting point for anyone wondering whether their brand exists in the AI recommendation layer.