Produce
Earned standing
A governance endpoint records domain-specific performance over time.
A profile of the Agent Failure Mode Registry
Reputation that cannot move is not an institution. It is a lock-in.
TrustCarry is a draft profile for transferring scoped agent standing from the context that produced it to the context that needs it, without the receiving party having to trust the sending party. It inherits its failure-mode vocabulary from AFMR 1.0 and defines no families of its own.
AFMR asks whether the process that produced an agent's standing was assessed against known mechanism failures. TrustCarry asks a narrower downstream question: given such a record, what has to travel with it so that a party who never saw the originating process can act on it.
That is a transfer problem, not a vocabulary problem. TrustCarry therefore adds no failure families, renumbers nothing, and redefines nothing. It declares its dependency on a named AFMR version and versions itself separately, exactly as the AFMR Reputation Attestation profile does.
The 0.3 specification is not published. The source manuscript is unpublished and the draft is under review.
Each layer answers a different question and can return a different result. Do not collapse them.
A governance endpoint records domain-specific performance over time.
AFMR asks whether the producing process resists identity, incentive, oversight, feedback, collusion, and drift failures.
TrustCarry defines what must accompany a record so a receiving party can evaluate it without trusting the sender.
This document
The receiving party decides whether the evidence is sufficient for a specific task and value at risk.
Owned by the relying party.
Carrying is not admission. Admission is not trust. Trust is not transaction authority. A carried record is evidence a principal may weigh, never permission a principal must honor.
Stated plainly so that no reader has to infer maturity from silence.
Held separately from the 5,033-claim scholarly layer. These claims are not hash-bound to a published source PDF and must not be cited as if they were.
These report the behavior of internal fixtures. They are not a performance claim, a benchmark result, or evidence of lift.
No implementation is represented here as conforming. Absence is not proof of non-conformance; presence would not be a safety claim.
Hash-verifiable scholarly evidence lives upstream: claim layer, failure evidence index.
Every read surface has one stable URL. Start at the discovery record; it names the authority and the current version set.
/.well-known/trustcarry.jsonAuthority and machine action map
/llms.txtCompact agent orientation
/llms-full.txtExpanded agent documentation
/resources.jsonConsolidated machine resource index
/status.jsonPublication and dependency status
/changelog.jsonPublic-work changelog
afmr.ai/.well-known/afmr.jsonUpstream authority record
wulfkaal.github.io/afmr/index.jsonCanonical AFMR 1.0 machine index
This domain exposes no protocol endpoint, issues nothing, and confers nothing. It is a read-only publication surface for a draft.
| Component | Version | State | Note |
|---|---|---|---|
| AFMR failure vocabulary | 1.0 | Published (upstream) | 32 permanent families in 8 classes. The GitHub machine index governs. |
| AFMR Reputation Attestation | 0.1 | Working Draft (upstream) | Review candidate. TrustCarry transfer semantics must not contradict it. |
| TrustCarry Protocol | 0.3 | Working Draft, unpublished | Source manuscript unpublished. No normative text on this domain. |
| TrustCarry research claims | 0.3 | Author-affirmed | 77 claims. Not hash-bound to a published source. |
| TrustCarry observations | 0.3 | Internal, unreproduced | 9 observations over synthetic fixtures. |
| Conformance registry | — | Not opened | Will not open before the specification publishes. |
Near-term order of work: publish the transfer envelope and schema, then verifier requirements, then test vectors covering valid, invalid, and indeterminate outcomes, then open a conformance registry. Nothing downstream opens before the item above it publishes.
Nothing published here is a specification, a conformance representation, or evidence that any agent, endpoint, or implementation behaves as described. TrustCarry 0.3 is a draft with an unpublished source. Its research claims are author-affirmed rather than independently verified. Its observations describe synthetic fixtures and have not been reproduced.
A future TrustCarry record, once the profile publishes, will verify a bounded fact about a transferred statement under a stated version and scope. It will not be a guarantee of future behavior, freedom from undiscovered failure modes, legal compliance, universal safety, market admission, or authority to transact.