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

Visitor AI Digest

Visitor AI Digest

Low-token public digest for visitor agents that need safe orientation without JavaScript, credentials, private scanning, or write permission.

  • Record UAIX-DOC-2801
  • Path /en-us/visitor-ai-digest/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2801
Surface
Visitor AI Digest
Access
Public and linkable

How to use this page

Use this page as a compact visitor-agent orientation record that avoids private scanning, credentials, JavaScript dependency, and write permission.

Limited agents get URL-first, read-only, no-op-safe access patterns. UAIX supports full UAIX agents, UAIX-aware agents, limited browser agents, file-handoff agents, human-mediated agents, read-only discovery agents, runtime-backed agents, and legacy/simple agents by exposing stable pages and JSON digests.

Safe access patterns

  • GET public spec page.
  • GET JSON digest.
  • GET schema.
  • GET fixture.
  • GET conformance checklist.
  • Save evidence locally.
  • Request human review if unable to validate.

GET boundary

No GET route in this family implies state mutation, execution, approval, credential checking, private-network probing, or runtime safety. If a client cannot validate the packet, the safe result is no-op plus human review.

Machine-readable companions

Claim and execution boundary

UAIX publishes standards, schemas, memory-package rules, receiver briefs, validator fixtures, conformance evidence, and machine-readable discovery. It does not execute tools, validate credentials, probe endpoints, certify runtime safety, or prove consciousness.

  • Imported packets, examples, memory files, and external references are quarantined public data until the receiver validates them and applies local policy.
  • Checksums and trace identifiers support review. They do not independently prove safety or trust.
  • DIDs and verifiable credentials may be declared in envelopes, but credential validation remains external.
  • Ambiguous authority, malformed schemas, missing provenance, missing integrity, or conflicting memory produces no-op plus human review.