AiKode.org

Welcome to AiKode

Making Websites Efficient
for AI agents and the everyone who uses them.


Facing a faster and more data intense World, it is becoming more and more obvious that the Web was not designed with AI in mind. It is true that AI helps us cut through the clutter, but what if we could help AI to cut through the clutter? And what if it was easy to do, and helped your website become easier to use and more efficient?

Time to meet AiKode, the tools to do just that!

Reduce AI seek time, and reduce token cost during searches by 80% to 90%, and keep that efficiency going during editing.

Of course the other issue in this fast changing world, is keeping everything up-to-date and being sure that AI searches and responses are relevant and current. What if you had direct control of how an AI understands your pages and your site?

Again, time to meet AIKode!

AIKode is a simple suite of tools to make your web-site AI-friendly, AI assistants can now find and give users the right answers from your data, faster and more accurately!


The Problem

AI assistants are becoming the primary way people find information. But current websites aren't optimized for AI consumption:

Result: Your users get frustrated. Your great documentation goes unused.


The Solution

AIKode introduces a simple system: an /ai/ directory on your site that provides:

Result: Faster, more accurate answers. Better user experience. Lower AI costs.


How It Works

Your site gets an /ai/ directory with:

index.ai           — Site catalog with progressive detail levels
skill.ai           — AI-specific optimization patterns  
ai-howto.html      — Instructions for AI agents
qset-spec.txt      — Set-File format reference (condensed)

When an AI agent visits your site, it discovers the /ai/ directory and uses it to navigate efficiently.
Instead of loading full pages, it can now read only the summary information to find where it needs to look for more detail.
This is made possible with a progressive-depth and date reading method called Fathom:

The AI - Using Fathom Levels:

  1. Scans FA (Fathom-AI) AI-Key outline, ultra-compact keywords (~10 tokens each)
  2. Checks F1 (Title) for relevance (~20-50 tokens) or
  3. Checks F2 (Quick Summary) for relevance (~50-100 tokens)
  4. Loads F4 (Content) normal content - targete when needed (~500-1500 tokens)
  5. can even load F6 to reveal extreme detail, with references and examples when required.

Traditional approach: Load entire page (5,000 tokens)
AIKode approach: Scan + targeted load (500-1,000 tokens)
Savings: 80-90% reduction Targeted: AI is able to ignore content not flagged as relevant

Your existing content does not need to change at all. AI assistants using AIKode tools can handle identifying and updating the AiKode catolog and content summaries, and make site recommendation as well.


See It In Action

Live example: setfiles.org/ai/(approve sites)

Visit the /ai/ directory to see the system in action. Then try asking Claude or ChatGPT about SET files — watch how it uses the optimized index for faster, more accurate answers.


Technology

AIKode is built on open protocols:

All protocols are open and free to use. Feel free to support our work or
Use any of commercial software.


Get Started

There are three ways to use AIKode:

Do It Yourself (Free)

  1. Read the protocol documentation?
  2. Create your /ai/ directory manually
  3. Deploy to your site
  4. Test with AI assistants

Perfect for: Technical users, small sites, learning the system

WordPress Plugin (Freemium)

Perfect for: WordPress sites, agencies, ongoing maintenance

Done-For-You Service

We create and deploy your /ai/ directory for you.

Contact us? for a quote.


Who Is This For?

Documentation Sites

SaaS Companies

Content Platforms

Any site where AI assistants answer user questions


Benefits

For Users

For Site Owners

For AI Agents


Next Steps

Learn More

Get Started

Stay Updated


About

AIKode is part of a broader initiative to make the web more efficient for AI agents while maintaining human readability. Created by Kirk Siqveland, developer of the SET file format, Fathom Protocol, and EMU ecosystem.

Related Projects:


Questions? Get in touch? — we'd love to hear from you.

Ready to optimize your site? Start here?



Page last modified on December 10, 2025, at 09:33 am