Limited Agent Access

Machine-readable companions

• Capability framework JSONL0-L6 records, no-op guidance, schemas, fixtures, and claim warnings.
• Capability catalogProfile identifiers, schemas, examples, and packet templates.
• UAI-1 profilesSelectable validator profile inventory.
• Field registry exportCompact/keyless field order maps and reconstruction notes.
• Evaluation packetsSeven packet templates with fixture and schema routes.
• No-op triggersCanonical stop reasons and human-review default.
• Authority boundariesEcosystem role matrix and claim-boundary routing.
• Conformance targetsStatic validator targets and evidence requirements.
• Well-known UAIX manifestLow-token discovery entry point.
• llms.txtAgent reading order and safety summary.

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.