Deterministic execution governance · v3.1.1 · Receipt spec v1.0 published

The governed path
is the fast path.

ZLAR intercepts AI agent tool calls, evaluates each against Ed25519-signed policy, routes decisions to humans when required, and produces cryptographic proof that governance happened. No AI in the enforcement path. The gate pattern-matches. It cannot be persuaded.

See the proof → View on GitHub Specifications
1,422Test assertions
12ADRs
v1.0Receipt format (published)
5Human invariants

How it works

Intercept. Evaluate. Decide. Prove.

When an AI agent attempts any action — shell command, file write, network request, MCP tool call — ZLAR intercepts before execution and evaluates against signed policy.

intercept
Agent issues a tool call

Framework hook fires before execution. The call never reaches the OS without passing through ZLAR. Works with Claude Code, Cursor, Windsurf, and any MCP client.

evaluate
Gate evaluates against signed policy

Ed25519-signed rules evaluated by regex matching, not reasoning. The agent cannot modify the rules that govern it. Policy supports JSON rules and Cedar formal policy language.

decide
Allow, deny, or route to human

Safe actions pass. Dangerous actions are blocked. Ambiguous actions are routed to the human authority via Telegram. The human approves or denies from their phone.

prove
Governed Action Receipt issued

Every decision produces a v1 envelope receipt — portable cryptographic proof that governance happened, verifiable by anyone with the public key. No platform access required.

Fail closed: gate down = all actions denied.
No AI in the enforcement path. The gate classifies and enforces. It does not reason.
Policy is a human artifact. Agents cannot modify the rules that govern them.
Human invariants protect the decision-maker: daily caps, deliberation floors, response-time variance monitoring.


Scope

What ZLAR governs — and what it doesn't.

ZLAR governs actions that flow through it. Actions that do not flow through it are not governed. This is not a hidden limitation. It is the scope boundary, stated in doctrine.

Within the governed path: cryptographically verifiable evidence for every intercepted action, signed policy, human authority routed when policy calls for it, fail-closed on every error path. The claim is structural and holds when the agent is adversarial, misaligned, or buggy.

outside
Upstream of the contact boundary

ZLAR does not govern the model, the prompt, or the reasoning trace. Governing upstream is governance theater. Governance happens at the contact.

outside
Un-routed paths

Capabilities the deployment has not routed through a ZLAR interception surface reach effect without crossing the gate. Those belong to sandboxes, network controls, and OS permissions.

outside
Out-of-SDK sub-runtimes

When the local process delegates to a sub-runtime that is not a ZLAR-mediated worker, ZLAR sees neither the handoff nor the sub-runtime's actions. A delegation-envelope gate is the named plan; not yet shipped.

Closing these gaps is the deployment owner's job. A deployment that leaves un-routed capabilities has ZLAR running, not ZLAR governing.

doctrine/SCOPE.md  ·  ADR-010 Interception Coverage


Distinctions

Adjacent things that are not this.

The category is crowded with adjacent things that look like governance and aren't. ZLAR is not those things.

not this
A trust score is not authority

A model judging another model is an attack surface disguised as a feature. Both can be talked into the same answer in the same language. The judge must not be smart in the way the agent is smart.

not this
A dashboard is not governance

Watching after the fact is monitoring. Governance stops the action before it becomes real. Receipts come from a gate that already happened — not the other way around.

not this
A vendor governing its own agents is not oversight

The party with revenue at stake cannot be the party that says no. Independent audit is structural, not optional — that is why finance has it, and that is why autonomous agents need it.

not this
A wrapper around an SDK is not authority placement

If the agent can rewrite or bypass the wrapper, the first yes still lives inside the agent's reach. First-allow authority must live outside the governed agent's writable space.

ZLAR is the structural alternative: deterministic gate, signed policy, separately-signed meta-policy, named human authority at the points consequence demands it, receipts an auditor can verify without the vendor in the room.


Receipt portability

Verifiable outside the vendor's interface.

A Governed Action Receipt is a signed artifact — not a screenshot, not a log entry, not a dashboard view. The decision, the rule it cited, the human who authorized it, the timestamp, the delegation chain are all bytes that anyone with the public key can verify.

That is the structural answer to vendor capture. The affected party — citizen, regulator, auditor, opposing counsel — does not depend on the vendor's interface for ground truth. After the session ends. After the vendor pivots. After the deployment is gone.

Verify a real receipt →  ·  Receipt v1 specification →


Shipped and in production

Governance infrastructure, not a dashboard.

Governed Action Receipt

Portable cryptographic proof. v1 envelope format (frozen). Ed25519 signature over canonical payload. Verifiable by anyone with the public key.

Deterministic Gate

Bash gate (Claude Code, Cursor, Windsurf) and MCP gate (any MCP client). Per-entry Ed25519 audit signing. Fail-closed on every error path.

Cedar Policy Engine

28+ formal policy rules in Amazon's Cedar language. Dual-engine evaluation (JSON regex + Cedar). Policy portability across governance layers.

Human Invariants

Five enforced constraints protecting the human decision-maker: H6 (daily cap), H13 (capacity), H14 (response-time variance), H15 (deliberation floor), H17 (authenticity).

Canonicalization Spec

Published specification (RFC 8785 subset). 28 test vectors verified across Node.js, Python, and bash. Cross-language receipt verification.

Semantic Validation

Five-layer verification pipeline. Rule-outcome consistency, authorizer coherence, temporal checks, delegation chain integrity. Signature is necessary but not sufficient.


Get started

See governance work in under 60 seconds.

The quickstart runs the real gate against real tool calls. Two are allowed. Two are denied. A v1 receipt is generated and cryptographically verified. Nothing is simulated.

git clone https://github.com/ZLAR-AI/ZLAR.git && cd ZLAR && bash scripts/quickstart.sh

Requirements: bash 4+, jq, openssl 3.x. Optional: Node.js 18+ (MCP gate, receipt verification). Troubleshooting →


Standards engagement

Regulatory and standards participation.


Technical depth

Inspect everything.


About

ZLAR Inc.

ZLAR is built from 25 years of financial services experience, where independent audit is structural, not optional. The same principle applies to autonomous agents: the entity performing the work cannot credibly audit itself.

Canadian corporation. Apache 2.0 licensed. Open source.

hello@zlar.ai  ·  Founder's writing →