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 tools that preserve your SEO and user experience.

BY THE NUMBERS

Real Impact, Measured Results

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

0%
Token Reduction

From 55KB HTML to 8KB Markdown

0x
Faster Discovery

Single manifest vs full site crawl

$0/mo
Cost Savings

Reduced bandwidth & infrastructure

CORE TOOLS

Four tools 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

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

Tools

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 features. ARW provides a standardized way for AI agents to discover content, tools, and integrations.

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)

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.

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 content signals 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.

PROGRESSIVE CONFORMANCE

Four levels of agent readiness

Implement incrementally. Each level builds on the previous, adding features without breaking existing functionality.

START HERE

ARW-1

Discovery Ready

Basic discovery via llms.txt + machine views. Agents can find your content.

  • llms.txt manifest
  • .md machine views
  • Basic content signals

2 hours to implement

ARW-2

Semantic Ready

Adds chunking, attribution, and rate limits. Agents can understand your content deeply.

  • Content chunking
  • AI-* headers
  • Rate limiting

1-2 weeks

ARW-3

Action Ready

OAuth tools + Schema.org semantics. Agents can act safely with consent.

  • OAuth 2.0 tools
  • Schema.org JSON-LD
  • Transactional flows

4-6 weeks

ARW-4

Protocol Ready

Full protocol interoperability (MCP, ACP, A2A). Universal agent access.

  • MCP integration
  • ACP checkout
  • A2A collaboration

2-3 months

COMING SOON

ARW Cloud: Turn-Key Agent Infrastructure

Zero-config deployment on Cloudflare's global edge network. Drop in a script tag, get instant ARW compliance with automatic content extraction, embedding generation, and semantic search.

5-Minute Setup

Add one script tag. Content automatically extracted and served as .md machine view files.

Edge-First Architecture

D1 database, KV cache, Vectorize embeddings, Workers AI—all on 300+ global locations.

Built-in Analytics

Track agent traffic, measure conversions, understand which agents drive value.

arw-cloud-architecture
┌─────────────────────────────────────────┐
│          ARW Cloud Architecture         │
├─────────────────────────────────────────┤
│                                         │
│  Website          Cloudflare Edge       │
│  ┌─────────┐     ┌─────────────────┐   │
│  │arw-loader├────►│  Edge Worker    │   │
│  │   .js   │POST │                 │   │
│  └─────────┘     │ ┌──────┐┌─────┐│   │
│                  │ │Workers││ KV  ││   │
│  AI Agent        │ │  AI   ││Cache││   │
│  ┌─────────┐     │ └──┬───┘└──┬──┘│   │
│  │GET .llm.├────►│    │       │    │   │
│  │   .md   │     │    ▼       │    │   │
│  └─────────┘     │ ┌──────┐   │    │   │
│                  │ │Vector│   │    │   │
│                  │ │ize   │   │    │   │
│                  │ └──────┘   │    │   │
│                  └────────────┼────┘   │
│                               │        │
│         ◄────────────────────►│        │
│         Sub-50ms latency globally      │
└─────────────────────────────────────────┘

USE CASES

ARW for every industry

From e-commerce to news publishers, ARW provides the infrastructure layer for AI agent interactions across verticals.

E-Commerce

Products appear in AI recommendations with attribution. OAuth checkout protects your transaction flow while enabling conversions.

tools:
- add_to_cart: oauth2
- checkout: oauth2

News & Media

Content helps users via agents while protecting your business model. Excerpts drive traffic back to your site.

content_signals:
training: false
inference: excerpt_only

SaaS Platforms

Documentation helps developers via agents. Trial signups and support tickets flow through OAuth for tracking.

tools:
- signup_trial: oauth2
- create_ticket: oauth2

Healthcare

Patient-facing content with strict training policies. Appointment booking through verified OAuth flows.

content_signals:
training: never
phi_protection: enabled

Finance

Market data and educational content. Strong compliance controls with audit trails for all agent interactions.

compliance:
audit_logging: true
disclaimer_required: true

Developer Tools

API docs and code examples optimized for coding agents. Enable training on open source, protect proprietary content.

content_signals:
training: open_source_only
code_execution: sandboxed

TECHNOLOGY

Built on web standards

No proprietary protocols. ARW uses technologies that every platform already supports.

Core Standards

HTTP/REST

Universal protocol layer

Standard HTTP methods and headers. Works with any web framework, CDN, or hosting provider.

YAML + Markdown

Human and machine readable

llms.txt uses YAML for structured data. Machine views use Markdown for efficient content delivery.

OAuth 2.0

Industry-standard auth

Standard OAuth flows for tools. User consent required. Technically enforced permissions.

Schema.org

Semantic vocabulary

JSON-LD with Schema.org types for tools. Compatible with existing SEO and structured data.

Developer Tools

ARW CLI

Rust-based CLI for generating, validating, and managing ARW files.

$ npx arw@alpha init
$ npx arw@alpha generate
$ npx arw@alpha validate
$ npx arw@alpha serve

Validators

Python Validatorvalidate-arw.py
Node.js Validatorvalidate-arw.mjs
JSON Schemasarw_model.yaml

Inspector Tools

Web InspectorAvailable
Chrome DevTools ExtensionAvailable
VS Code ExtensionComing Soon
VISION 2025+

The Agentic CMS Evolution

ARW is the foundation for a new category: content management systems built for AI agents, not just human browsers.

Current State

  • Static content optimized for SEO
  • No agent analytics or tracking
  • Manual content optimization
  • Zero monetization of AI traffic

Near-Term (2025)

  • Agent Analytics Dashboard
  • Tool Registry for tools
  • Knowledge Assets management
  • Basic monetization tiers

Future State (2026+)

  • Agent Identity & Accounts
  • Multi-Agent Coordination
  • Dynamic pricing & billing
  • Full agentic commerce platform

Agentic CMS Architecture Layers

Tool Registry

Declare what agents can do with your content and services

Knowledge Assets

Structured content optimized for agent consumption

Tool Schemas

Type-safe definitions for agent operations

Agent Analytics

Track behavior, measure value, optimize content

Agent Accounts

Identity, authentication, and billing per agent

Monetization

Turn agent traffic into sustainable revenue

ROADMAP

Building the agent-ready future

A phased approach to universal agent access—from infrastructure to ecosystem.

NOW

Phase 1: Foundation

Core specification, CLI tools, validators, and reference implementations.

  • • ARW v1.0 specification complete
  • • Rust CLI with WASM support
  • • JSON Schema validation system
  • • Chrome DevTools extension
Q1 2025

Phase 2: Adoption

Framework integrations, package distribution, and developer experience.

  • • NPM package distribution
  • • Next.js / Nuxt / Astro plugins
  • • WordPress plugin
  • • ARW Cloud beta launch
Q2-Q3 2025

Phase 3: Analytics & Tools

Agent analytics platform, OAuth tool framework, and monetization tools.

  • • Agent Analytics Dashboard
  • • Tool execution framework
  • • Billing & monetization
  • • Enterprise features
2026+

Phase 4: Universal Access

Standards adoption, multi-agent coordination, and full agentic commerce.

  • • W3C standardization track
  • • Agent Identity system
  • • Multi-agent orchestration
  • • Full protocol ecosystem

THE ECONOMIC CASE

The Coasean Singularity

NBER research shows AI agents reduce transaction costs toward near-zero. ARW enables this transformation by providing the infrastructure for efficient agent-web interaction.

90%
Search Cost Reduction
85%
Communication Cost Reduction
80%
Contracting Cost Reduction
90%
Verification Cost Reduction
Read the Analysis

Investment Thesis

"ARW is essential infrastructure for the agent economy, not an optional enhancement. As agent traffic grows from 40% to 70%, websites without ARW will be at a severe competitive disadvantage."
Agent Traffic (2024)40%
Agent Traffic (2027)70%
Typical Monthly Savings$450+

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.

Contact us