ARW

Why ARW Quick Start vs llms.txt Case Study Contact Docs v2

OPEN STANDARD • MIT LICENSED

The infrastructure layer for the agent-ready web

85% token reduction. 10x faster discovery. Full observability.
ARW provides efficient, observable infrastructure for AI agents — structured discovery, machine-readable content, and OAuth actions that preserve your SEO and user experience.

Read the docs npx arw@alpha init

BY THE NUMBERS

Real Impact, Measured Results

See how ARW transforms agent-web interactions with concrete efficiency gains

Token Reduction

From 55KB HTML to 8KB Markdown

Faster Discovery

Single manifest vs full site crawl

$0/mo

Cost Savings

Reduced bandwidth & infrastructure

CORE CAPABILITIES

Four capabilities that transform agent-web interaction

Discovery

/llms.txt acts as a table of contents for AI agents. 10x faster than crawling entire sites. Single source of truth.

Efficiency

.llm.md files reduce content from 55KB HTML to 8KB Markdown. 85% token reduction. Lower costs for everyone.

Actions

Secure OAuth-protected operations. Add to cart, checkout, book appointments. User-authorized. Publishers maintain control.

Observability

Track agent behavior via AI-* headers. Know which agents visit, what they consume, policy compliance.

IMPLEMENTATION

How agents discover and use your content

The web/HTTP layer remains the universal entry point agents use to discover specialized capabilities. ARW provides a standardized way for AI agents to discover content, capabilities, and actions.

1# CloudCart Electronics
2
3> E-commerce platform for electronics
4
5We sell computers, peripherals, accessories.
6
7## Products
8
9[Keyboards](/products/keyboards): Browse keyboards
10[Mice](/products/mice): Browse mice
11[Monitors](/products/monitors): Browse monitors
12... (50+ product categories)
13
14## Support
15
16[Shipping Info](/support/shipping): Details
17[Returns](/support/returns): Policy
18... (20+ support pages)

FOR EVERYONE

Built for publishers, AI platforms, and developers

For Publishers

Reach users through AI agents

Agents are already browsing your site. ARW ensures they get accurate information, attribute your brand, and can complete transactions.

For AI Platforms

Build better agent experiences

Stop scraping HTML and guessing at structure. ARW provides clean, structured data that reduces errors and lowers costs.

For Builders

Simple implementation, powerful results

Add llms.txt in 2 hours. Progressive enhancement—each step adds value without breaking existing functionality.

PROGRESSIVE ENHANCEMENT

Implement incrementally, publish with confidence

Progressive enhancement means you can start with basic discovery and add features incrementally. Time to first value: 2 hours.

Get started View examples

Frequently Asked Questions

Who can implement ARW?: Any website operator. ARW is open source (MIT licensed) and works with any tech stack—Next.js, WordPress, Rails, Django, static sites. Start with basic discovery and add features incrementally.
Which AI agents support ARW?: ARW uses standard HTTP, Markdown, OAuth, and Schema.org—technologies all agents already support. As the specification matures, AI companies can add native ARW recognition for enhanced features.
Does ARW work with Agentic Commerce Protocol?: Yes. ARW and ACP are complementary. ARW's llms.txt advertises ACP checkout endpoints, enabling discovery via the web layer while ACP handles standardized transaction flows.
What about content policies and training?: ARW policies are declared directly in llms.txt and enforced via HTTP headers. Training and inference permissions are specified per-site, with clear attribution requirements and rate limits.

Become a contributor

We built ARW as a collaborative, open source standard and we welcome your feedback on how to improve it. Whether you're a publisher protecting your content, an AI company building better agents, or a developer implementing the spec, your input helps shape the future of the agent web.

ARW