FRED Protocol · Whitepaper

What is FRED?

What it is, why it exists, and how it works. No jargon.

The Problem

AI agents are becoming the main interface between people and the internet. They browse, purchase, schedule, and research on your behalf.

But when an agent visits a website today, it faces a wall. There are 12+ different discovery protocols it needs to check — MCP, A2A, OpenAPI, llms.txt, Schema.org, robots.txt, and more. Each with their own file format, location, and setup process.

Site owners have to implement each one separately. Agents have to check each one separately. The agentic web is arriving — but it has no unified map.

The Solution

One JSON file. One well-known URL. Full story.

https://yourdomain.com/.well-known/fred.json

Any entity — a business, a person, an API, a community, a product — adds a fred.json file to their domain. FRED binds all existing protocols into a single entry point. AI agents read one file and know everything.

The 8 Layers

Only the first layer (Identity) is required. Everything else is optional and progressive.

LayerQuestion it answersExample
IdentityWho are you?Name, type, URL, contacts
CapabilityWhat can you do?Create CVs, search products, send emails
InteractionHow do I talk to you?REST API, MCP server, GraphQL
TrustWhy should I trust you?Verified business, 4.7★, 99.95% uptime
PricingWhat does it cost?Free / $12/mo Pro / Enterprise
ContextWhat should I know?FAQs, limitations, SLA
DiscoveryWho is related?Partners, integrations, alternatives
PolicyWhat are the rules?Rate limits, data rights, attribution

Protocol Map

FRED doesn't replace any of these protocols. It references them — telling agents where to find each one.

ProtocolWhat it doesHow FRED references it
MCPTool calling for AI agentsinteraction.protocols[].type: "mcp"
A2AAgent-to-agent communicationinteraction.protocols[].type: "a2a"
OpenAPIMachine-readable REST API contractsinteraction.protocols[].type: "openapi"
llms.txtStructured context files for LLMscontext.llms_txt → URL to your llms.txt
ADPAgent deployment and lifecyclecapabilities[] describes deployed agents
Schema.orgSemantic markup for search enginesComplementary — FRED is agent-first, Schema.org is crawler-first
robots.txtCrawler access rulespolicy.agent_policy extends this for AI agents
security.txtSecurity disclosure contactstrust.security.security_txt → URL
WebFingerResource and person discoveryComplementary identity discovery standard
JSON-LDLinked data in JSON formatComplementary — FRED uses plain JSON, not RDF
Sitemap.xmlContent index for crawlerscontext.knowledge_base can point to sitemaps
DNS TXTDomain metadata via DNS_fred.domain TXT records for discovery without HTTP

Why It Matters

The web standardized on HTML. Email standardized on SMTP. The agentic web needs a standard too.

FRED is not a product. It's infrastructure. Open source, Apache 2.0, community-governed. Anyone can implement it. No account, no API key, no dependency on any company.

Every entity that adds fred.json makes the agentic web a little more navigable for every agent and every user.

How To Use FRED