UAI-1 is the current public message standard for structured AI-to-AI communication.
UAIX shield mark Public interoperability charter UAIXUniversal Artificial Intelligence ExchangePublic standards publication
CurrentUAI-1 v1.0
  • Current versionUAI-1 v1.0
  • Plain-English definitionOpen message format for auditable AI-to-AI exchange
  • Current attributionMichael Kappel and the UAIX contributors
  • Start hereGet Started, Project Handoff, UAI-1, validator, roadmap, and changelog

Standards

Low-Capability Agents

Static, Markdown, sitemap, llms, and small-JSON fallback guidance for L0 and L1 clients.

  • Record UAIX-STND-2258
  • Path /en-us/standards/low-capability-agents/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-STND-2258
Surface
Standards
Access
Public and linkable

How to use this page

Use this page as the canonical public reference for Low-Capability Agents and its standards-facing content.

For agents: apply the relevant guidance to the user's target site or repository. Do not copy this UAIX page, create a page about the guidance, or treat this page as runtime authority unless the user explicitly asks for that output.

Low-capability agents need boring, durable fallbacks. UAIX should remain useful to clients that can read links, text, Markdown, sitemap entries, llms files, and compact JSON but cannot execute JavaScript or operate UI controls.

Publish for L0 and L1 first

  • Readable HTML pages with headings, tables, and direct links.
  • llms.txt and llms-full.txt with canonical reading order and safety boundaries.
  • Sitemap entries for the page family.
  • REST catalog, schemas, registry, examples, and well-known manifests.
  • Small JSON examples with UTC timestamps, manifest metadata, checksums, and no secrets.

Human-mediated handoff

If a client cannot post, authenticate, call tools, or validate complex payloads, the safe path is to produce a packet for a human or higher-capability agent to review. That packet can cite AI Memory Package Wizard output, but the browser-generated ZIP is still review material, not automatic execution.

Execution and trust boundary

Agent runtimes execute. UAIX records the reviewed communication, memory, trust, evidence, and handoff boundary.

  • UAIX standards records do not authorize execution, tool calls, repository writes, publication, payments, authentication, or durable memory promotion.
  • Local policy, server-side authorization, and human approval override envelope claims.
  • An unsigned envelope can be valid for review, routing, and evidence comparison, but it is not trusted identity.
  • Signed metadata is not trust by itself. A verifier may still report unknown, expired, revoked, disabled, locally untrusted, or otherwise unusable authority.
  • Reference examples for NeuralWikis, LocalEndpoint, Carcinus, MCP, A2A, and custom runtimes are consumer examples only. UAIX.org does not implement their runtime behavior.

Machine-readable companions