Format library

8 formats on every plan. 16 on Growth.

See all 16 AI-readable formats: what each one is, who reads it, and what it looks like on disk.

Try it on your site →How it works

Format library

The full set

llms.txtpage.mdschema.jsonindex.yamlfeed.xmlmanifest.jsonhumans.txtog.jsondataset.dcatpage.n3feed.jsonpage.tomlpage.ttlschema.cueactivity.jsoncontent.steno

Geordy emits the right format per page, automatically - eight core on every plan, eight enterprise on Growth.

The library

txt

LLMs.txtllms.txt

Core

The site map for language models.

A plain-text directive at your domain root that tells AI engines what your site is about, which pages matter, and where to look first. The signal-to-noise ratio they wish your homepage had.

llms.txt

# Geordy
> https://geordy.ai

## Purpose
Optimize websites for AI-powered search engines.

## Paths
/features: Platform features
/pricing: Pricing plans
/formats: All 16 formats

Read byChatGPT (GPTBot)Claude (Claude-Web)Perplexity (PerplexityBot)Google GeminiBing AI

Read full details

md

Markdownpage.md

Core

Your page, in the format LLMs were trained on.

Clean Markdown stripped of nav, ads, scripts, and CSS. Headings preserved, link targets normalized, content placed in a single retrieval-tight document. The format AI reads first when given a choice.

page.md

# Geordy

## What is GEO?

GEO is the practice of optimizing content for AI-powered search engines.

## Key Features

- **Multi-format generation**: 16 AI-optimized formats
- **AI bot tracking**: Monitor GPTBot, Claude-Web, PerplexityBot

Read byGPTBotClaude-WebPerplexityBotGeneral LLM systems

Read full details

json

Schema JSON (JSON-LD)schema.json

Core

Structured data, the way Google and AI engines prefer it.

JSON-LD using schema.org vocabulary, page-typed automatically. Geordy detects whether a page is an Article, Product, FAQPage, or Organization and emits the right shape - including required fields most sites silently miss.

schema.json

{
  "@context": "https://schema.org",
  "@type": "SoftwareApplication",
  "name": "Geordy",
  "applicationCategory": "BusinessApplication",
  "description": "AI optimization platform for generative search engines"
}

Read byGoogle SearchBingVoice assistantsAI citation systemsKnowledge graph systems

Read full details

yaml

YAMLindex.yaml

Core

Page metadata, indentation-clean.

Configuration-style metadata: title, summary, canonical, taxonomy, last-updated. Easy for tooling to ingest, easier still for retrieval pipelines to filter.

index.yaml

# AI Optimization Configuration
site:
  name: "Geordy AI Platform"
  domain: "geordy.ai"
  category: "GEO / LLMO"

ai_targeting:
  primary_systems:
    - ChatGPT
    - Claude
    - Perplexity

Read byChatGPTClaudePerplexityBuild toolsRAG pipelines

Read full details

xml

RSS Feedfeed.xml

Core

Continuous discovery for new and updated pages.

An XML feed of every new or recently-updated page on your site, with full content embedded. AI crawlers poll it instead of guessing when to re-crawl.

feed.xml

<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>Geordy AI Optimization Updates</title>
    <link>https://geordy.ai</link>
    <item>
      <title>New Enterprise Formats Released</title>
    </item>
  </channel>
</rss>

Read byGPTBotClaudeBotPerplexityBotFeed readersAI training pipelines

Read full details

json

Manifest.jsonmanifest.json

Core

Identity declaration for installable surfaces.

Declares your site's name, icons, theme color, and entry points. AI agents that surface installable apps or quick-launch tiles read this first.

manifest.json

{
  "name": "Geordy - AI Optimization Platform",
  "short_name": "Geordy",
  "start_url": "/dashboard",
  "display": "standalone",
  "theme_color": "#2a9d8f",
  "categories": ["productivity", "business", "seo"]
}

Read byGoogle LighthouseChrome DevToolsAI categorization systemsApp store indexing

Read full details

txt

Humans.txthumans.txt

Core

Attribution for the people behind the site.

Names the team, tools, and timestamps behind the site. AI engines increasingly use this for trust and authorship signals.

humans.txt

/* TEAM */
Founder & CEO: Alex Morgan
Head of AI Research: Dr. Sarah Chen
Lead Engineer: Jordan Kim

/* SITE */
Last update: 2024-01-15
Standards: AI-optimized formats, Schema.org
Components: Next.js, React, TypeScript

Read byEthical AI systemsAttribution validatorsTrust raters

Read full details

json

OG.jsonog.json

Core

Open Graph metadata, centralized.

All social and AI preview metadata in one place - title, description, image, type. Powers chat surfaces, social embeds, and assistant cards from a single source.

og.json

{
  "title": "Geordy - AI visibility starts here",
  "description": "Generate 16 AI-optimized formats automatically",
  "image": "https://geordy.ai/og-cover.jpg",
  "url": "https://geordy.ai",
  "type": "website",
  "site_name": "Geordy"
}

Read byAI chat surfacesSocial platformsPreview generators

Read full details

rdf

DCAT (RDF Data Catalog)dataset.dcat

Enterprise

Dataset discovery, the W3C way.

RDF-based catalog vocabulary for datasets - endpoints, distributions, licenses. AI agents use this when looking for structured data assets, not articles.

dataset.dcat

@prefix dcat: <http://www.w3.org/ns/dcat#> .
@prefix dct: <http://purl.org/dc/terms/> .

<https://geordy.ai/dataset/ai-crawl-analytics>
  a dcat:Dataset ;
  dct:title "AI Bot Crawl Analytics" ;
  dct:publisher <https://geordy.ai> ;
  dcat:keyword "GPTBot", "Claude-Web", "AI crawling" .

Read byGPTBotClaude-WebPerplexityBotLLM crawlers accessing semantic metadata

Read full details

n3

Notation3 (N3)page.n3

Enterprise

Logic, rules, and inference.

RDF logic-based notation. Lets AI systems reason over relationships in your content rather than just extract them.

page.n3

@prefix geordy: <http://geordy.ai/ns#> .
@prefix schema: <http://schema.org/> .

ex:GeordyAI
  a geordy:AIPlatform ;
  schema:name "Geordy AI Platform" ;
  geordy:supportsAI ex:ChatGPT, ex:Claude .

Read byReasoning enginesKnowledge graph systemsAI agents using inference

Read full details

json

JSON Feedfeed.json

Enterprise

RSS, but JSON-native.

A modern alternative to RSS, easier to parse for JSON-first pipelines. Useful for AI agents that consume live syndication without an XML parser.

feed.json

{
  "version": "https://jsonfeed.org/version/2.0",
  "title": "Geordy AI Optimization Updates",
  "home_page_url": "https://geordy.ai",
  "items": [{
    "id": "https://geordy.ai/blog/enterprise-formats",
    "title": "New Enterprise Formats",
    "date_published": "2024-01-15T10:00:00Z"
  }]
}

Read byModern AI agentsDeveloper-built RAG pipelinesJSON-first crawlers

Read full details

toml

TOMLpage.toml

Enterprise

Minimal, human-friendly config.

An alternative to YAML with cleaner type rules. Ideal for embedding metadata into developer-oriented surfaces.

page.toml

# TOML configuration for Geordy
title = "Geordy AI Platform"

[owner]
name = "AI Optimization Inc."

[database]
server = "192.168.1.1"
ports = [ 8001, 8002 ]
enabled = true

Read byDeveloper toolsAI code agentsBuild pipelines

Read full details

ttl

Turtlepage.ttl

Enterprise

Compact RDF triples.

A concise serialization of semantic relationships. The lingua franca of knowledge graphs.

page.ttl

@prefix geordy: <http://geordy.ai/ns#> .
@prefix schema: <http://schema.org/> .

ex:GeordyAI
  a geordy:AIPlatform ;
  schema:name "Geordy AI Platform" ;
  schema:url "https://geordy.ai" ;
  geordy:optimizesFor ex:GenerativeSearch .

Read byKnowledge graph systemsSemantic search enginesChatGPTClaude

Read full details

cue

CUEschema.cue

Enterprise

Schema definition with validation.

A constraint language for data validation. Lets AI tooling verify your structured data is well-formed before consuming it.

schema.cue

# CUE configuration for Geordy AI Platform
package main

site: {
  name: string
  domain: string
  category: *"GEO / LLMO" | *"AI / ML"
}

site: name: "Geordy AI"
site: domain: "geordy.ai"

Read byAI validatorsBuild pipelinesSchema-aware code agents

Read full details

json

ActivityPubactivity.json

Enterprise

Federated identity for social AI.

Decentralized protocol for publishing activities and identity. Reaches the federated AI ecosystem (Mastodon and beyond).

activity.json

{
  "@context": "https://www.w3.org/ns/activitystreams",
  "type": "Create",
  "actor": {
    "type": "Person",
    "id": "https://mastodon.social/@alice",
    "name": "Alice"
  },
  "object": {
    "type": "Note",
    "content": "<p>Hello, Fediverse!</p>"
  }
}

Read byFederated AIMastodon agentsFediverse crawlers

Read full details

steno

Stenocontent.steno

Enterprise

Compact representation for repeated terms.

A stenography dictionary - shorthand outlines mapped to their full translations. Used to teach AI engines that every variant of a term resolves to the same canonical phrase.

content.steno

{
  "GEO": "Generative Engine Optimization",
  "LLMO": "Large Language Model Optimization",
  "GPT/PWBOT": "GPTBot",
  "KHRAUD/PWEB": "Claude-Web",
  "PER/PLEBGT/PWBOT": "PerplexityBot",
  "TKPWRAO/TKEU": "Geordy",
  "SREPBL/PWEUGT": "AI visibility"
}

Read byChatGPTClaudePerplexity

Read full details

Stop choosing formats. Ship all of them.

One scan, up to sixteen formats, served from your subdomain. Set it up in fifteen minutes.

AI-Optimized File Formats | Geordy GEO Platform