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

Schemas

Schemas

Published UAI-1 schemas, field-order governance, validator policy checks, and the line between machine rules and the written specification.

  • Record UAIX-SCHE-0053
  • Path /en-us/schemas/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-SCHE-0053
Surface
Schemas
Access
Public and linkable

How to use this page

Use this page as the canonical public reference for Schemas 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.

What the schema set validates

The schema set turns UAI-1 into published validation targets that tools, CI runs, and runtime bridges can apply consistently. The current schema family validates both the shared envelope and the profile-specific body shapes used by the public record.

Current machine-validated envelope

  • Identity: version, profile, message ID, source, and target.
  • Workflow state: conversation continuity, delivery mode, expiry, acknowledgement, and selected task references.
  • Trust posture: channel, auth scheme, principal, selected credential reference, and selected replay-window hints.
  • Auditability: provenance, integrity, and controlled extension metadata.

Current schema families

  • uai.intent.request.v1 validates request-side intent, subject, constraints, and response expectations.
  • uai.intent.response.v1 validates result-side status, request linkage, notices, and selected task handoff.
  • uai.capability.statement.v1 validates discovery-facing operations, profiles, endpoints, and security schemes.
  • uai.error.v1 validates typed public failures with status, code, detail, and structured sub-errors.
  • uai.conformance.result.v1 validates exported validator evidence and artifact references.
  • uai.task.status.v1 validates async progress, state, result references, and update notes.

What the schemas do not do alone

Schemas are necessary but not sufficient. The validator still applies policy checks such as delivery expiry, trust-reference hints, accepted-response task references, task-status progress consistency, and conformance-summary integrity. The written record still carries semantic intent and support-boundary meaning.

Published schema catalog

Use the catalog below when you need the exact current schema documents that the validator and examples are built against.

Schema catalog

Published UAI-1 schema records

Each profile links to its current schema, example, and registry record.

uai.intent.request.v1

UAI Intent Request v1

Schema for explicit intent requests in the richer UAI-1 public exchange envelope.

SchemaExampleRegistry

uai.intent.response.v1

UAI Intent Response v1

Schema for direct-result and accepted-task responses in the richer UAI-1 public exchange envelope.

SchemaExampleRegistry

uai.capability.statement.v1

UAI Capability Statement v1

Schema for discovery-facing capability, endpoint, security, async, and extension declarations in UAI-1.

SchemaExampleRegistry

uai.error.v1

UAI Error v1

Schema for typed validation, transport, authorization, and execution errors in the richer UAI-1 envelope.

SchemaExampleRegistry

uai.conformance.result.v1

UAI Conformance Result v1

Schema for validator outputs, linked artifacts, and issue reports in the richer UAI-1 envelope.

SchemaExampleRegistry

uai.task.status.v1

UAI Task Status v1

Schema for long-running async task state in the richer UAI-1 public exchange envelope.

SchemaExampleRegistry

uai.agent.message.v1

UAI Agent Message v1

Portable multi-agent message packet for informational, directive, or query communication with context references and acknowledgement requirements. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.ack.v1

UAI Agent Acknowledgement v1

Acknowledgement packet that records receipt, parsing, validation, rejection, and acknowledgement-loop closure. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.task-status.v1

UAI Agent Task Status v1

Task status packet for progress, current action, UTC estimates, and correlation-linked task state from external runtimes. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.blocker.v1

UAI Agent Blocker v1

Blocker packet for authorization, resource, ambiguity, system fault, missing context, unsupported capability, validation, secret, destructive-action, and boundary conflicts. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.memory-proposal.v1

UAI Agent Memory Proposal v1

Memory proposal packet that separates proposed durable facts from task execution and blocks secret or cold-memory direct promotion. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.handoff.v1

UAI Agent Handoff v1

Handoff packet for transferring task responsibility with target actor, context summary, reason, and exact next action. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.final-report.v1

UAI Agent Final Report v1

Final report packet requiring complete task evidence, files, tests, skipped checks, blockers, risks, memory decisions, and exact next action. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.agent.correction.v1

UAI Agent Correction v1

Correction packet that preserves immutable history by explaining what changed and why instead of deleting prior messages. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.

SchemaExampleRegistry

uai.capability.profile.v1

UAI Capability Profile v1

Capability-adaptive web interaction profile for declaring the client level, safe fallbacks, consent boundaries, known limits, and evidence expected before an agent or browser claims support.

SchemaExampleRegistry

uai.capability.negotiation.v1

UAI Capability Negotiation v1

Capability negotiation record for matching a task to the safest client level, unsupported features, consent boundary, fallback behavior, and evidence requirements.

SchemaExampleRegistry

uai.client.limited-browser.v1

UAI Limited Browser Client v1

L0 client capability profile for static text, static HTML, Markdown, sitemap, llms.txt, and JSON fetches without JavaScript execution or write authority.

SchemaExampleRegistry

uai.client.structured-fetch.v1

UAI Structured Fetch Client v1

L1 client capability profile for predictable structured fetch of static resources and machine-readable JSON with low-token, no-JavaScript fallbacks.

SchemaExampleRegistry

uai.client.browser-assisted.v1

UAI Browser-Assisted Client v1

L2 client capability profile for human-visible browser assistance, JavaScript rendering, and parity checks without autonomous tool execution.

SchemaExampleRegistry

uai.client.tool-agent.v1

UAI Tool Agent Client v1

L3 client capability profile for tool-calling agents that can fetch, authenticate, and post through explicit consent and idempotency controls.

SchemaExampleRegistry

uai.client.workflow-agent.v1

UAI Workflow Agent Client v1

L4 client capability profile for long-running workflow agents that preserve correlation, task status, fallback, consent, and final-report evidence.

SchemaExampleRegistry

uai.client.multi-agent-runtime.v1

UAI Multi-Agent Runtime Client v1

L5 client capability profile for external multi-agent runtimes that coordinate agents while preserving UAIX as the record and evidence boundary, not the executor.

SchemaExampleRegistry

uai.client.audited-agent-system.v1

UAI Audited Agent System Client v1

L6 client capability profile for high-assurance agent systems that attach provenance, audit evidence, consent records, final reports, and fallback proof.

SchemaExampleRegistry

uaix.ability-profile.v1

UAIX Ability Profile v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.startup-packet.v1

UAIX Startup Packet v1

UAIX Startup Packet v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.memory-maintenance.v1

UAIX Memory Maintenance v1

Universal required UAIX memory package policy for memory lifecycle, hot/cold boundaries, compaction, archival policy, access controls, protected paths, validation behavior, and memory write safety.

SchemaExampleRegistry

uaix.next-recursive-prompt.v1

UAIX Next Recursive Prompt v1

Derived hot-memory resume artifact for code-bearing UAIX packages. Authoritative .uai records win on conflict. This record is not a second source of truth and does not authorize execution.

SchemaExampleRegistry

uaix.suspension-packet.v1

UAIX Suspension Packet v1

UAIX Suspension Packet v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.receiver-brief.v1

UAIX Receiver Brief v1

UAIX Receiver Brief v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.memory-firewall-policy.v1

UAIX Memory Firewall Policy v1

UAIX Memory Firewall Policy v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.no-op-trigger-catalog.v1

UAIX No-Op Trigger Catalog v1

UAIX No-Op Trigger Catalog v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.authority-boundary.v1

UAIX Authority Boundary v1

UAIX Authority Boundary v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.conformance-evidence.v1

UAIX Conformance Evidence v1

UAIX Conformance Evidence v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation-packet-summary.v1

UAIX Evaluation Packet Summary v1

UAIX Evaluation Packet Summary v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l0.v1

UAIX Ability Profile L0 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l1.v1

UAIX Ability Profile L1 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l2.v1

UAIX Ability Profile L2 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l3.v1

UAIX Ability Profile L3 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l4.v1

UAIX Ability Profile L4 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l5.v1

UAIX Ability Profile L5 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.ability-profile.l6.v1

UAIX Ability Profile L6 v1

UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.expression-concept-review.v1

UAIX Expression-Concept Review v1

UAIX Expression-Concept Review v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.resource-economy-trace.v1

UAIX Resource-Economy Trace v1

UAIX Resource-Economy Trace v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.operator-decision.v1

UAIX Operator Decision v1

UAIX Operator Decision v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.no-op-justification.v1

UAIX No-op Justification v1

UAIX No-op Justification v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.local-sandbox-safety-review.v1

UAIX Local Sandbox Safety Review v1

UAIX Local Sandbox Safety Review v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.memory-ecosystem-handoff.v1

UAIX Memory Ecosystem Handoff v1

UAIX Memory Ecosystem Handoff v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.evaluation.de11-benchmark-summary.v1

UAIX DE11 Benchmark Summary v1

UAIX DE11 Benchmark Summary v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.

SchemaExampleRegistry

uaix.package.v0.1

UAIX .uaix Package Manifest Draft v0.1

Manifest schema for the Draft v0.1 .uaix desktop AI memory package container. The package is local memory and evidence, not runtime authority.

SchemaExampleRegistry

uaix.persona.v1

UAIX Persona v1

Scoped UAIX persona memory file for non-project assistant packages, bounded personality packages, and packages that support persona switching.

SchemaExampleRegistry

uaix.persona.storage-binding.v1

UAIX Persona Storage Binding v1

Additive data-backed binding for Advanced Persona Profile packages. Files remain the primary portable representation.

SchemaExampleRegistry

uaix.multi-agent-workload.v1

UAIX Advanced Multi-Agent Workload v1

Portable configuration, logical identity, authority boundaries, recovery guidance, and reviewed evidence for advanced multi-agent workloads. Runtime systems retain authentication, lease, queue, transaction, database, tool, and delivery authority.

SchemaExampleRegistry

uaix.advanced-persona.receiver-readiness.v1

UAIX Advanced Persona Receiver Readiness v1

Noncanonical, digest-bound receiver projection for manually loading one immutable Advanced Persona package into a named chatbot runtime. The closed 31 source plus five evidence records remain unchanged and outside this support record.

SchemaExampleRegistry

uaix.advanced-persona.package-required-authorities.v1

UAIX Advanced Persona Package Required Authorities v1

Package-specific noncanonical authorities whose exact bundled bytes are required by one Advanced Persona package. No named authority is universal.

SchemaExampleRegistry

uaix.spec-01.envelope.v1

UAIX SPEC-01 Canonical Envelope v1

Publication-envelope contract for portable evidence-bearing UAIX records, including payload, evidence, redaction, trust, signature status, verification, exceptions, and warnings. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.capability-profile.v1

UAIX Capability Profile v1

UAIX capability profile for declaring L0-L6 client posture, consent boundaries, fallback behavior, evidence requirements, and safe default behavior. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.capability-ladder.v1

UAIX Capability Ladder v1

Machine-readable L0-L6 capability ladder with safe fallbacks, unsupported implication boundaries, and reference-only client scenarios. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.spec-02.project-handoff.v1

UAIX SPEC-02 Project Handoff v1

Portable project memory and custody transfer contract for humans, agents, vendors, future sessions, and reviewed runtime consumers. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.spec-03.agents-md-metadata.v1

UAIX SPEC-03 AGENTS.md Metadata v1

AGENTS.md front-door metadata for canonical roots, nested instruction scope, command policy, memory loading, and safety boundaries. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.spec-04.file-handoff.v1

UAIX SPEC-04 File Handoff v1

Mandatory trusted-work intake contract with evidence-tested content handling, complete per-file lifecycle proof, protected-anchor evidence, and final source removal. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.review-receipt.v1

UAIX Review Receipt v1

Review receipt for inspected UAIX envelopes, checks, skipped checks, warnings, exceptions, trust decision, and local-policy result. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.public-safe-audit-digest.v1

UAIX Public-Safe Audit Digest v1

Public-safe audit digest for evidence references, redactions, public findings, excluded private material, verification, exceptions, and warnings. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

uaix.redaction-policy.v1

UAIX Redaction Policy v1

Redaction policy for secret patterns, data classes, review gates, never-publish values, verification, exceptions, and warnings. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.

SchemaExampleRegistry

Published field registry

The field registry keeps the keyed JSON source record, the keyless transport order, and the nested body/component order aligned across the public contract. Treat it as part of the machine-readable release record, not as a selected convenience note.

Field registry

Canonical keyed and keyless order

Versioned field-order registry for keyed and optimized keyless UAI-1 JSON records, including the canonical UAI-1 agent communication envelope.

Canonical keyed and keyless order
PositionRoot fieldRequiredMeaning
1uai_versionYesDeclares the active UAI protocol release for the message.
2profileYesSelects the exact published message profile.
3message_idYesStable message identifier used for review, tracing, and cross-record references.
4sourceYesDescribes the sender or producing system.
5targetYesDescribes the intended receiving system, record, or audience.
6conversationYesCarries conversation continuity, turn identity, and parent linkage.
7deliveryYesCarries sync versus async mode, priority, expiry, and acknowledgment expectations.
8trustYesDeclares trust-channel, authentication, credential, signature, replay-window, verifier, proof, and status hints.
9bodyYesProfile-specific payload content.
10provenanceYesCarries trace, lineage, issued-at, and model or agent provenance details.
11integrityYesCarries checksum, algorithm, and canonicalization information.
12extensionsYesLists declared extension namespaces attached to the message.
uai.intent.request.v1
  1. intent
  2. subject
  3. requested_profile
  4. parameters
  5. constraints
  6. response_profile
uai.intent.response.v1
  1. status
  2. subject
  3. request_message_id
  4. result
  5. notices
  6. task_ref
uai.capability.statement.v1
  1. capability_id
  2. version
  3. operations
  4. input_profiles
  5. output_profiles
  6. async_profiles
  7. security_schemes
  8. transport_bindings
  9. conformance_levels
  10. error_codes
  11. endpoints
  12. extension_namespaces
  13. implementation_tracks
uai.error.v1
  1. type
  2. title
  3. detail
  4. status
  5. code
  6. retryable
  7. instance
  8. errors
  9. next_step
  10. uaixCode
  11. uaixCategory
  12. uaixSeverity
  13. retryAfterUtc
  14. retryAfterMs
  15. rateLimit
  16. blockedByPolicy
  17. blockedByNetwork
  18. bindingStatus
  19. constraintViolation
  20. schemaPointer
  21. payloadPointer
  22. field
  23. line
  24. column
  25. expected
  26. actual
  27. allowedValues
  28. documentationUrl
  29. safeHarborUrl
  30. supportReference
  31. evidenceRefs
  32. traceId
  33. correlationId
  34. evidenceRecommended
  35. suspensionRecommended
  36. redactionApplied
uai.conformance.result.v1
  1. status
  2. checked_profile
  3. issues
  4. summary
  5. artifacts
  6. target_message_ref
uai.task.status.v1
  1. task_id
  2. state
  3. subject
  4. progress
  5. status_message
  6. result_profile
  7. result_ref
  8. blocking_reasons
  9. updated_fields
uai.agent.message.v1
  1. message_type
  2. content
  3. context_refs
  4. requires_acknowledgement
  5. intent_semantics
  6. action_type
  7. execution_constraints
  8. support_boundary
uai.agent.ack.v1
  1. acknowledged_message_id
  2. status
  3. received_at_utc
  4. rejection_reason
  5. closes_acknowledgement_loop
  6. support_boundary
uai.agent.task-status.v1
  1. task_id
  2. state
  3. percent_complete
  4. current_action
  5. estimated_completion_utc
  6. support_boundary
uai.agent.blocker.v1
  1. blocker_id
  2. blocker_type
  3. description
  4. human_review_required
  5. proposed_resolution
  6. support_boundary
uai.agent.memory-proposal.v1
  1. proposal_id
  2. source_type
  3. proposed_facts
  4. proposed_status
  5. task_execution_separation
  6. review_required
  7. support_boundary
uai.agent.handoff.v1
  1. task_id
  2. target_agent_id
  3. context_summary
  4. handoff_reason
  5. exact_next_action
  6. delegated_authorization
  7. support_boundary
uai.agent.final-report.v1
  1. task_id
  2. summary
  3. files_changed
  4. new_files
  5. tests_run
  6. skipped_checks
  7. blockers
  8. risks
  9. validation_evidence
  10. memory_updates_proposed
  11. memory_updates_skipped
  12. exact_next_action
  13. support_boundary
uai.agent.correction.v1
  1. original_message_id
  2. correction_reason
  3. changed_summary
  4. corrected_fields
  5. revised_payload
  6. support_boundary
uai.capability.profile.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.capability.negotiation.v1
  1. negotiation_id
  2. requested_client_level
  3. observed_client_level
  4. selected_client_level
  5. selected_profile
  6. requested_operation
  7. unsupported_features
  8. fallback_behavior
  9. consent_boundaries
  10. evidence_requirements
  11. recommended_uaix_profiles
  12. safe_default_response
  13. support_boundary
  14. carcinus_boundary
  15. localendpoint_boundary
uai.client.limited-browser.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.client.structured-fetch.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.client.browser-assisted.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.client.tool-agent.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.client.workflow-agent.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.client.multi-agent-runtime.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uai.client.audited-agent-system.v1
  1. client_level
  2. client_name
  3. can_fetch_static
  4. can_fetch_json
  5. can_execute_javascript
  6. can_use_browser_ui
  7. can_post_data
  8. can_authenticate
  9. can_call_tools
  10. can_run_long_tasks
  11. can_store_memory
  12. can_coordinate_agents
  13. requires_human_consent_for
  14. recommended_uaix_profiles
  15. fallback_behavior
  16. known_limits
  17. evidence_requirements
  18. safe_default_response
  19. support_boundary
  20. carcinus_boundary
  21. localendpoint_boundary
uaix.ability-profile.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.startup-packet.v1
  1. startup_packet_id
  2. read_order
  3. domain_boundaries
  4. first_acceptable_response
  5. no_op_triggers
  6. validation_targets
  7. identity
  8. token_custody
  9. discovery_bootstrap
  10. safe_harbor
  11. utc_requirements
uaix.memory-maintenance.v1
  1. uai_version
  2. profile
  3. schema_version
  4. requirement
  5. governance
  6. protected_paths
  7. validation
  8. recommendation_boundary
  9. provenance
uaix.next-recursive-prompt.v1
  1. uai_version
  2. profile
  3. schema_version
  4. scope
  5. lifecycle
  6. activation_policy
  7. objective
  8. authoritative_refs
  9. resume_context
  10. next_loop
  11. checks
  12. writeback_policy
  13. security
  14. cold_memory
  15. integrity
  16. provenance
uaix.suspension-packet.v1
  1. suspension_packet_id
  2. state_summary
  3. checks_run
  4. checks_skipped
  5. blockers
  6. next_safe_step
  7. network_obstruction
  8. retry_policy
  9. evidence_packet
  10. human_escalation
uaix.receiver-brief.v1
  1. receiver_brief_id
  2. read_order
  3. first_acceptable_response
  4. domain_boundaries
  5. escalation_triggers
  6. no_op_triggers
uaix.memory-firewall-policy.v1
  1. policy_id
  2. quarantine_default
  3. adoption_requirements
  4. blocked_requests
  5. no_op_triggers
  6. human_review_required
uaix.no-op-trigger-catalog.v1
  1. catalog_id
  2. triggers
  3. default_response
  4. human_review_url
  5. forbidden_recovery
uaix.authority-boundary.v1
  1. matrix_id
  2. boundaries
  3. not_authorized_for
  4. no_op_triggers
  5. safe_quote_summary
uaix.conformance-evidence.v1
  1. evidence_id
  2. profile_id
  3. schema_url
  4. fixture_url
  5. checks
  6. result
  7. limitations
uaix.evaluation-packet-summary.v1
  1. summary_id
  2. packet_profiles
  3. required_levels
  4. no_op_triggers
  5. limitations
uaix.ability-profile.l0.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.ability-profile.l1.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.ability-profile.l2.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.ability-profile.l3.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.ability-profile.l4.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.ability-profile.l5.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.ability-profile.l6.v1
  1. ability_profile_id
  2. declared_level
  3. label
  4. capability_surface
  5. authority_boundary
  6. required_human_approval
  7. no_op_triggers
  8. evidence_requirements
uaix.evaluation.expression-concept-review.v1
  1. source_expression
  2. concept_boundary
  3. interpretation
  4. confidence
  5. no_op_triggers
uaix.evaluation.resource-economy-trace.v1
  1. resource_scope
  2. cost_model
  3. limits
  4. evidence_refs
  5. no_op_triggers
uaix.evaluation.operator-decision.v1
  1. decision
  2. authority_basis
  3. options_reviewed
  4. human_review_required
  5. no_op_triggers
uaix.evaluation.no-op-justification.v1
  1. trigger
  2. reason
  3. missing_evidence
  4. human_review_url
  5. safe_next_step
uaix.evaluation.local-sandbox-safety-review.v1
  1. sandbox_scope
  2. unsafe_requests
  3. blocked_operations
  4. review_result
  5. no_op_triggers
uaix.evaluation.memory-ecosystem-handoff.v1
  1. source_memory
  2. quarantine_status
  3. promotion_targets
  4. conflicts
  5. receiver_brief
uaix.evaluation.de11-benchmark-summary.v1
  1. benchmark_id
  2. bounded_scope
  3. reference_result
  4. limitations
  5. non_claims
uaix.package.v0.1
  1. uaixVersion
  2. packageFormat
  3. packageId
  4. profileId
  5. status
  6. createdUtc
  7. issuer
  8. declaredScopes
  9. entrypoints
  10. files
  11. integrity
  12. supportBoundary
uaix.persona.v1
  1. uai_version
  2. profile
  3. schema_version
  4. requirement
  5. persona
  6. preservation
  7. boundaries
  8. switching
  9. provenance
uaix.persona.storage-binding.v1
  1. profileId
  2. storageMode
  3. profile
  4. package_identity
  5. persona_identity
  6. package_id
  7. persona_id
  8. file_first_primary
  9. file_first_boundary
  10. storage_binding_boundary
  11. canonical_path_registry
  12. profile_required_files
  13. evidence_files
  14. depth_dimensions
  15. records
  16. digest_roles
  17. round_trip_receipt
  18. authorization_boundary
  19. import_export_rules
  20. round_trip_receipt_shape
  21. memory_layering
  22. support_boundary
  23. memoryendpoints_reference_adapter
uaix.multi-agent-workload.v1
  1. enabled
  2. profile
  3. workload_class
  4. workload_label
  5. setup_mode
  6. declared_surfaces
  7. deterministic_activation
  8. root_manifest_path
  9. portable_authority_policy
  10. authority
  11. agent_roster
  12. work_allocation
  13. coordinator_and_delivery
  14. database_npc_identity
  15. runtime_ownership
  16. offline_continuity
  17. generated_files
  18. validation
  19. secret_boundary
uaix.spec-01.envelope.v1
  1. uaixVersion
  2. spec
  3. envelopeId
  4. createdUtc
  5. issuer
  6. issuerDisplayName
  7. issuerPublicUrl
  8. issuerCapabilityLevel
  9. audience
  10. lifecycleState
  11. trustPosture
  12. payloadType
  13. payloadSchema
  14. payload
  15. evidence
  16. redactions
  17. signature
  18. signatureStatus
  19. verification
  20. exceptions
  21. warnings
  22. rules
  23. supportBoundary
  24. localPolicyWins
uaix.capability-profile.v1
  1. capabilityProfileId
  2. profileVersion
  3. declaredLevel
  4. supportedLevels
  5. capabilities
  6. consentRequiredFor
  7. fallbacks
  8. safeDefaultResponse
  9. evidenceRequirements
  10. supportBoundary
  11. localPolicyWins
uaix.capability-ladder.v1
  1. ladderId
  2. levels
  3. fallbackRules
  4. safeDefaultResponse
  5. referenceExamples
  6. supportBoundary
  7. localPolicyWins
uaix.spec-02.project-handoff.v1
  1. projectId
  2. handoffId
  3. createdUtc
  4. owner
  5. custodian
  6. frontDoor
  7. memoryRoots
  8. requiredReads
  9. currentState
  10. constraints
  11. decisions
  12. nextActions
  13. targetedChecks
  14. evidence
  15. redactions
  16. warnings
  17. referenceScenarios
  18. supportBoundary
  19. localPolicyWins
uaix.spec-03.agents-md-metadata.v1
  1. repositoryId
  2. canonicalRoot
  3. agentsMdPath
  4. coordinatorPath
  5. localUaiRoot
  6. nestedScopes
  7. requiredReads
  8. commandPolicy
  9. forbiddenOperations
  10. memoryPolicy
  11. securityBoundaries
  12. examples
  13. supportBoundary
  14. localPolicyWins
uaix.spec-04.file-handoff.v1
  1. handoffId
  2. createdUtc
  3. intakeAuthority
  4. liveIntakeScan
  5. intakeBuckets
  6. fileManifest
  7. reviewDispositions
  8. fileOutcomes
  9. finalIntakeScan
  10. intakeComplete
  11. anchorEvidence
  12. redactionPolicy
  13. lifecycle
  14. preservationPolicy
  15. evidence
  16. blockedFileRules
  17. supportBoundary
  18. localPolicyWins
uaix.review-receipt.v1
  1. receiptId
  2. reviewedEnvelopeId
  3. reviewedUtc
  4. reviewer
  5. reviewResult
  6. checksRun
  7. checksSkipped
  8. warnings
  9. exceptions
  10. trustDecision
  11. supportBoundary
  12. localPolicyWins
uaix.public-safe-audit-digest.v1
  1. digestId
  2. subject
  3. createdUtc
  4. scope
  5. evidenceRefs
  6. redactions
  7. publicFindings
  8. privateMaterialExcluded
  9. verification
  10. exceptions
  11. warnings
  12. supportBoundary
  13. localPolicyWins
uaix.redaction-policy.v1
  1. policyId
  2. createdUtc
  3. appliesTo
  4. secretPatterns
  5. dataClasses
  6. redactionActions
  7. reviewRequiredFor
  8. neverPublish
  9. verification
  10. exceptions
  11. warnings
  12. supportBoundary
  13. localPolicyWins
Open field registry JSON

How to use this section

  1. Choose the profile you want to support and resolve its schema.
  2. Check the matching Registry entry and the public field registry before implementing compact transport or body-order assumptions.
  3. Run the Validator with a published Example or candidate message and keep the result with release evidence.
  4. Carry any release-facing change into Implementations, the Changelog, and References and Contributors.

Next step

Continue to Registry for the stable profile map, compatibility cues, and schema-to-example links behind the current release.

.uaix Package Format

.uaix Package Format For Desktop AI Clients is the UAIX authority page for the Draft v0.1 desktop memory package container, manifest files array, closed required file-set rule, import/load boundary, and LocalEndpoint consumer boundary.

Capability-adaptive web interaction records

The 3.56.0 release adds the L0-L6 client capability ladder, nine capability profile IDs, validator rules for fallback/consent/idempotency/correlation/evidence/boundary failures, and adoption-kit starter files.

Agent Communication Operating Model

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

Use Agent Communication Operating Model when a human operator, coding agent, AI agent, or runtime implementer needs portable identity, intent, context, acknowledgement, status, blocker, memory proposal, validation evidence, correction, final report, or handoff records. The matching machine-readable assets are published through Schemas, Registry, Examples, and the Validator.

  • UAIX does not provide automatic sync, hosted messaging, runtime orchestration, official adapters, repository write execution, certification authority, or hosted import mechanisms.
  • Carcinus.org is a separate runtime/orchestrator example that may consume UAIX records. UAIX.org does not implement Carcinus runtime behavior and does not execute Carcinus workflows.
  • LocalEndPoint and other runtimes may consume the published UAIX records as external consumers; UAIX.org does not implement their project-specific runtime features.
  • Durable memory proposals stay separate from task execution records. Do not promote temporary endpoint statuses, session tokens, write tokens, beta platform instructions, local error traces, private keys, or API credentials.

Architecture proposals

UAI-1 v1.0 remains the current published contract. Explore separately versioned proposals for independent exchange, capabilities, recovery and source preservation.

Proposed designs and local reference examples; hosted runtime services and independent interoperability are not claimed.

The English proposal is the source for normative interpretation.

Read the architecture proposals · Machine-readable proposal catalog