WitnessOS
WitnessOS by Empire Labs Pty Ltd

Every agent action, provable.

WitnessOS is not an operating system for machines. It is the operating layer for governed agent action, the kernel between "the agent wants to" and "the agent may".

Deterministic policy, human approval, tamper-evident receipts and independent timestamps. Auditor-verifiable with zero trust in us.

WitnessOS governed action and evidence overview
WITNESSOS / EVIDENCE RECEIPT SAMPLE RECEIPT
action governed.action
policy result ALLOW
approval BOUND
chain INTACT
timestamp RFC 3161
ACTION HASH
7f2a91c4...e86b03d9

INDEPENDENTLY TIMESTAMPED
REVOCATION CHECKED AT RECORD TIME
FAIL CLOSED VERIFY WITHOUT EMPIRE TRUST
Why now

Dashboards are not audit trails.

AI governance is moving from guidance to evidence. Audit, risk and insurance teams will ask organisations to prove what autonomous systems actually did, not simply show what a platform says happened.

Trust is a feeling. Proof is a fact. WitnessOS replaces blind trust with cryptographic evidence.
"Show me, don't tell me."

When an agent spends money, sends a message or touches a governed action, who can prove what happened, who approved it and when? Self-attested logs that a vendor could edit are not enough.

How it works

Govern first. Act second. Prove always.

01

Action proposed

The agent proposes an action with its target, parameters, scope and asserted intent.

02

Policy evaluated

Deterministic, OPA/Rego-compatible policy returns Allow, Deny, Conditional or Escalate.

03

Receipt created

The evaluation produces a tamper-evident receipt with the action hash, policy version, context, decision, timestamp and chain of custody.

04

Governed response

Execution proceeds only when sanctioned. Denied actions receive structured remediation from advisory to failsafe, with every escalation recorded.

Evidence ladder / E0 to E4

Evidence gets stronger. Never overstated.

The public ladder closes at E4. Every grade describes the evidence a receipt can support, and unprovable gates cap the grade down, never up.

E0
Declared The agent reports the action itself. No independent observation.
E1
Observed A sidecar or SDK witnessed the action. Gaps are possible.
E2
Enforced The gateway authorised and routed the action; the credential broker enforced policy.
E3
Corroborated The destination provider confirmed the outcome, by external receipt or state probe.
E4
Anchored On top of E3 corroboration: externally timestamped via RFC 3161 and Merkle-checkpointed, independently verifiable.
Fail closed by default If a proof gate cannot be satisfied, the grade is capped down.
Governed allowlist Only sanctioned action types can reach E4. Everything else stops at E3.
Zero trust in Empire Labs Receipts verify independently, with no access to an Empire Labs database.
Tamper-tested Altered records cannot reach the top grade.
Watchdog coverage If the evidence gate degrades, operators are alerted. There is no silent drift.
Capabilities

Controls for accountable autonomy.

POLICY

Policy engine

OPA-native Rego policy-as-code, evaluated deterministically before action.

EVIDENCE

Evidence receipts

SHA-256 signed, tamper-evident and exportable as audit bundles.

REMEDIATION

RemediLevel R0 to R6

Structured escalation from advisory guidance to hard failsafe.

BINDING

Machine binding

TPM or fingerprint binding for governed licensing.

INTEGRATION

API-first

Designed for REST, WebSocket and SDK integration.

CONTROL

Layered policy

System, environment and action-level policy tiers.

Governed connectors in production. Payments, refunds and messaging are governed action types: policy, approval and evidence apply before any connector runs. Enterprise deployments add their own action types and connectors to the governed allowlist, and the same evidence ladder applies to everything they touch.
x402 payments Stripe refunds Gmail/Workspace messaging

Status: all three lanes are governed and anchored. Published receipts grade E2: E4 requires legitimate E3 corroborated evidence plus independently authenticated external anchoring. WitnessOS Gateway v0.1.0 and witnessos-verifier v0.3.5 introduce the hardened Evidence Grade model.

Global alignment

Built for the evidence the world now demands.

WitnessOS implements technical standards (RFC 3161 timestamping, OPA/Rego policy, SHA-256 chaining, X.509-style verification) and produces evidence designed to support organisations meeting global obligations: EU AI Act Article 12 record-keeping + Article 14 human oversight, GDPR accountability, NIST AI RMF, ISO/IEC 42001, ISO 27001/SOC 2 audit evidence.

Post-quantum readiness

Every agency now owes a cryptographic inventory.

The Australian Information Security Manual requires a cryptographic bill of materials to be produced and made available to consumers of software. It also requires a post-quantum transition plan to be developed, implemented and maintained. The milestones are dated: a refined plan by the end of 2026, transition commenced by the end of 2028, complete by the end of 2030. We produce the inventory and the plan as signed records that you verify without trusting us.

Inventory

Algorithms, protocols, libraries, certificates and key custody for one boundary, in CycloneDX 1.6.

Quantum exposure

Each asset graded by quantum exposure against the lifetime of the data it protects.

Transition plan

Sequencing, owners and milestones against the 2026, 2028 and 2030 dates.

Signed record

The inventory and the plan bound to one root and independently timestamped.

Drift detection

A changed estate fails verification and names the exact asset that moved.

Proof and positioning

Shipped evidence, not a promise.

E4 evidence supported

Strict mode can issue E4: corroborated E3 evidence plus an independently authenticated RFC 3161 anchor.

Tamper resistance tested

Altered records cannot reach E4.

Governed allowlist

Unsanctioned action types fail closed.

Watchdog monitored

Evidence degradation cannot drift silently.

400+ automated tests

Including real-CA timestamp verification.

Open standards vocabulary. WitnessOS is built on the Empire Stack vocabulary: ACI, the Agent Communication Interface with AJSON manifest authoring, and AIP, the Agent Interaction Protocol.
Questions people ask

Agent governance, transactions and evidence

What is WitnessOS?

WitnessOS is the runtime governance layer for autonomous agents, developed by Empire Labs Pty Ltd. It sits between an agent wanting to act and the agent being allowed to act, applying deterministic policy, human approval and tamper-evident evidence to every governed action.

What is an agent transaction?

An agent transaction is any governed action an autonomous agent performs, such as a payment, refund or message. WitnessOS records each one as a signed, chained evidence receipt with an independent timestamp, so the transaction can be verified later without trusting the operator.

How does WitnessOS handle AI commerce and payments?

WitnessOS governs payment and commerce actions through connectors, including x402 payments, Stripe refunds and messaging. Evidence receipts are produced before a connector runs, giving AI commerce the audit trail it needs: what was spent, who approved it, and proof the record was not altered.

What does E4 evidence mean?

E4 is the top grade on the public WitnessOS evidence ladder. It requires legitimate E3 corroborated evidence plus independently authenticated external anchoring: an RFC 3161 timestamp from an authority the verifier trusts, with revocation checked at generation time, and it re-verifies offline with zero trust in Empire Labs.

Is WitnessOS an agent operating system?

No. WitnessOS is not an operating system for machines. It is the operating layer for governed agent action, the kernel between "the agent wants to" and "the agent may". It governs, approves and proves actions rather than running the agent itself.

Explore the full site

Summary to substance

The landing page is the one-minute summary. Each page below goes deeper, in the same governed-proof story.

PRODUCTS

What we build

The tools you can run today, and what each one proves.

PRICING

Numbers, published

Free tools, scoped services and the design-partner programme.

CASE STUDY

Governing 9 agents

How Empire Labs governs its own autonomous fleet with WitnessOS.

ROADMAP

Shipped and next

Hardened E4 evidence released in WitnessOS Gateway v0.1.0 and witnessos-verifier v0.3.5: legitimate E3 corroborated evidence plus independently authenticated external anchoring. Published demonstration receipts predate it and verify at E2, with the connector layer and trust network ahead.

Technical assessment

Can you prove what your agents did?

Book a 30-minute technical assessment to map governed actions, policy gates and evidence requirements for your environment.