The Trust Fabric for the Agentic Economy

The substrate that links identity, policy, evidence and the trust index into one consistent, on-chain view.

• Deterministic policy-core
• Identity (DIDs)
• Signed evidence on Hedera
• The Trust Index

Issues each agent a verifiable, self-certifying DID and proves control of its key — the root every other engine trusts.

• did:hedera / did:key
• Key proof (verify-key / BYOK)
• Public DID resolver
• HCS registry anchoring

Binds an agent to its owner and to a VC-issued mandate — with instant revocation.

• Verified principal (KYC/KYB), or a disclosed free-tier allowance
• VC-issued mandate (scope, caps, merchants)
• Resource scope — which systems and data
• Sub-delegation that can only narrow
• Delegated issuance

A signed, portable snapshot of an agent's identity, ownership, declared purpose and current capabilities — composed from data the platform already tracks.

• Signed identity + capability snapshot
• Composed from existing identity/version/assurance data
• Independently revocable from containment
• Reissued as the agent's profile changes

Issues, presents and verifies W3C Verifiable Credentials — with selective disclosure and on-chain anchoring.

• Verifiable Credentials (identity, entity, mandate)
• BBS selective disclosure
• Ed25519 platform issuer
• Anchoring & revocation

The deterministic core: composes Standards & SOPs from atoms and returns allow / observe / block / escalate — no LLM in the decision.

• Atom → molecule → SOP/Standard
• allow / observe / block / escalate
• Deterministic & re-derivable
• Live edits, no redeploy

The authorize gate that runs the policy on every signed action, in cooperative or trustless mode, with human-in-the-loop escalation.

• The authorize gate (MAGP)
• Escalation → owner approval
• Standards compliance check
• Cooperative & trustless modes

A signed, single-use proof that one exact action was authorized — bound to that authorization alone, carrying no raw payload content.

• Issued only on allow / observe
• Bound 1:1 to a single authorization
• No amount, merchant or payload data
• Paired Execution Receipt proves payloadMatch

Encrypted-at-rest storage for the upstream credentials your agents need — released just-in-time, only to a gateway, only against a currently-active Action Passport.

• AES-256-GCM at rest
• One release path, gated on two factors
• Tenant derived from the passport, never the caller
• Every attempt audited, plaintext never logged

Signs every decision, batches them into a Merkle root, anchors it on Hedera, and lets anyone verify a record offline.

• Ed25519-signed receipts
• Merkle batching
• HCS anchoring
• Offline verification (magp-evidence)

Turns the signed evidence into a reconstructable, regulator-ready record — with inclusion proofs against an anchored root.

• Immutable audit / regulator log
• Merkle inclusion proofs
• Reason-code decision trail
• Downloadable, offline-verifiable

A scoped, revocable seat for a regulator or supervisor — with a hash-chained log of everything they read.

• Grant-based, time-bounded access
• Scoped to decisions, controls or proofs
• Hash-chained access log
• Readable by the supervised organisation

Computes a signed, HCS-28 trust score per agent from its verified identity and governance track record.

• HCS-28 Trust Index
• Weighted adapters + coverage
• Drift monitoring
• Signed, publishable records

Routes risk in proportion to impact — high-risk actions and low-trust counterparties escalate to a human, they don't fail silently.

• Risk-tiered escalation
• Policy thresholds (atoms)
• Trust-guidance routing
• Incident & near-miss reporting
• Proportional, not binary

Authoritative, federatable on-chain registries for agent identities and published trust records.

• HCS-2 identity registry
• Agent DID registry
• HCS-28 trust registry
• Federatable / discoverable

Issues living certifications backed by assurance-graded verification, continuous evidence and the Trust Index.

• Assurance-graded KYC/KYB
• Living certificates
• Digital trust marks
• Auto-revoke on drift

A public, no-KYB environment that hands you a governed agent — first allow / observe / block / escalate in minutes.

• Public no-KYB endpoint
• Shared, pre-issued test agent
• Live allow / observe / block / escalate
• Same code to production

Contains a misbehaving agent immediately — revoke its mandate, fail closed, and keep the signed record.

• Instant mandate revocation
• Fail-closed containment
• Escalation queues
• Post-incident evidence

The signal backbone — verification and status webhooks, escalation polling and evidence-flush events.

• Verification / contact webhooks
• Escalation status polling
• Evidence batch flush
• Real-time trust signals

Security-by-design: signed, fail-closed, PII encrypted at rest, only commitments on-chain, and quantum-resistant channels.

• Ed25519 + hybrid post-quantum
• Encryption at rest (AES-256-GCM)
• On-chain commitments, not PII
• Fail-closed by default

Runs on Hedera (testnet or mainnet), self-hostable, with configurable, sovereign HCS topics.

• Hedera testnet / mainnet
• Self-hostable / sovereign
• Configurable HCS topics
• Cloud / on-prem / federated