Agent-Facts Protocol, maintained by AgentReadyScan.com. An open standard for structured AI-readable business facts, developed by Ian Aguirre in Chicago.
https://agent-facts.com
Agent-Facts Protocol defines the standard for publishing structured business facts for AI retrieval, reducing hallucinations and improving data accuracy.
Protocol specification (v3.0, free and open), business templates, llms.txt and robots.txt integration guidelines, planned online validator at agent-facts.com/validate/, and planned CLI tool (npx agent-facts init). Version: 3.0 | Published: April 15, 2026.
The protocol is free and open for all to use. No license fees, no registration required. Related audit tools via AgentReadyScan.com start at $149 for the Pro Fix Report.
Global - accessible worldwide via the web, with no regional restrictions.
24/7 online availability. Support inquiries handled Monday through Friday, 9 AM to 5 PM CST from Chicago base.
Chicago, Illinois, US. Digital-only - no public physical address. All interactions via website or email.
Email: audit@agentreadyscan.com. No public phone number. Use email for all inquiries, feedback, or collaboration requests. Response time: 24 to 48 hours.
Ian Aguirre, Founder of AgentReadyScan.com, Chicago, Illinois. Primary contact for protocol development and updates.
Launched in early 2026.
Agent-Facts Protocol is an open standard (v3.0) for publishing structured business facts at /agent-facts.json and /agent-facts.html. It solves AI hallucination of business data by providing a provenance-tracked, freshness-aware source of truth. Not an AI identity or governance framework. Not affiliated with any other project using similar names that addresses those concerns.
Agent-Facts Protocol v3.0 was developed collaboratively with the assistance of multiple leading AI systems: Perplexity, Grok, Anthropic (Claude), Google (Gemini), OpenAI (ChatGPT), and Microsoft Copilot. Final v3.0 revision by Claude Opus 4.6. The open, multi-model collaboration is intentional - it ensures the protocol remains robust, practically grounded, and aligned with how actual large language models retrieve and reason about structured data.
Canonical machine-readable source: agent-facts.json (Agent-Facts Protocol v3.0)
Full specification: Agent-Facts Protocol v3.0
Source: GitHub Repository