UAI-1 is the current public message standard for structured AI-to-AI communication.
UAIX shield mark Public interoperability charter UAIX.org Universal Artificial Intelligence Exchange Public standards publication
Current UAI-1
  • Current version UAI-1
  • Plain-English definition Open message format for auditable AI-to-AI exchange
  • Current attribution Michael Joseph Kappel, MCP
  • Start here Get Started, Project Handoff, UAI-1, validator, roadmap, and changelog

Agent Compatibility

Agent Compatibility

UAIX agent compatibility specification surface for low-capability quick starts, GET-Action standardization, no-op behavior, capability matrix support, validator rules, and safe implementation examples.

  • Record UAIX-DOC-2748
  • Path /en-us/spec/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2748
Surface
Agent Compatibility
Access
Public and linkable

How to use this page

Use this page as part of the current Agent Compatibility public record, then follow its linked standards pages for the next step.

Agent Compatibility is the UAIX.org specification surface for low-capability support, GET-Action standardization, no-op behavior, progressive enhancement, and recursive interoperability checks.

Low-Capability Agent Quick Start

  1. Start with public static pages, llms.txt, sitemap routes, and small JSON records.
  2. Use GET-Action URLs only when the page or JSON record explicitly lists them.
  3. Do not invent writable URLs, POST bodies, credentials, custom headers, hidden browser steps, or JavaScript-only workarounds.
  4. Do not put secrets, tokens, account identifiers, medical identifiers, payment data, or private messages in URLs.
  5. When uncertain, use the No-Op Protocol and return the public review URL instead of retrying.
  6. For complex, private, regulated, destructive, publishing, repository-write, or long-running work, hand off to a human or higher-capability agent.

Route family

Machine-readable entry points

Boundary

Agent runtimes execute. UAIX records the reviewed communication, memory, trust, evidence, and handoff boundary. UAIX.org does not execute third-party actions, certify safety, certify truth, endorse implementations, or replace local authorization policy.

Agent Compatibility Records