Part of Content Studio
OKF Generator
Knowledge files about your brand, ready for AI to cite
What are LLMs and why do they matter for your business?
LLM stands for Large Language Model. These are the artificial intelligence systems behind tools like ChatGPT, Google Gemini, Claude, and Perplexity. They work by processing enormous amounts of text to learn human language patterns, which enables them to answer questions, generate content, and hold natural conversations.
When a user asks ChatGPT "what's the best project management tool?" or asks Perplexity "which laptop should I buy for graphic design?", the LLM analyzes everything it learned from the web and selects the sources it considers most trustworthy to build its response. If your brand, product, or website doesn't have the right signals, the model simply won't include you in that answer, and your competition will take that spot.
Google AI Overviews is Google's version of this technology: instead of showing just a list of links, it now generates a direct AI-powered answer at the top of search results. This means the first result many users see is no longer a link to your site, but an AI-generated response that may or may not mention you.
In short: LLMs are the new intermediaries between your business and your potential customers. More and more people use these tools to research, compare, and decide what to buy. AuraMetrics helps you ensure that when AI answers questions about your industry, your brand is part of the answer.
What it does
OKF Generator creates a complete OKF v0.1 knowledge bundle for your site. Given a domain, it crawls the site, classifies each page by concept type, and builds a set of markdown files with YAML frontmatter that AI agents consume directly, packaged as a ZIP ready to deploy. It uses no templates and no AI model calls: classification is deterministic and grounded in the pages that actually exist on your site. The bundle follows the structure of the OKF specification and of AuraMetrics' own bundle at /okf/.
Why it matters
OKF bundles give AI agents canonical, structured access to your organizational knowledge, without scraping or guessing. Instead of inferring your information from HTML, agents read clean, verifiable files. AuraMetrics detects OKF bundle presence as a bonus signal in Content Readiness and recommends it when missing, so publishing one improves how AI engines discover and cite you.
How it works
You enter your site URL and the module crawls up to 50 pages using your sitemap.xml and robots.txt, with SSRF protection on every request. It classifies each page into an OKF type (Product, Concept, Article, Documentation, API, Playbook), generates one markdown file per page with frontmatter (type, title, description, resource, tags, timestamp), a details section, and a citable statement, and builds index.md and log.md. Everything is packaged as a ZIP you drop into your project's /public/okf/ folder.
Metrics you get
Recommended use cases
Frequently asked questions
What is OKF?
The Open Knowledge Format (OKF) is an open specification published by Google Cloud in June 2026 for representing organizational knowledge as a directory of markdown files with YAML frontmatter, designed to be consumed by AI agents.
Where do I put the generated bundle?
Place the /okf/ folder in your project's /public/ directory and serve it at yourdomain.com/okf/. Then reference it in your llms.txt.
Does OKF affect my GEO Score?
Not directly yet. AuraMetrics detects OKF bundle presence as a bonus signal in Content Readiness and includes it as a recommendation when not found.