Runtime assurance

AI you can stand behind.

Glacis governs your AI agents in the path of action and seals evidence of every governed call. When a customer, auditor, or board asks “How do you know?”, you can answer without sending us your data.

Evidence is signed today. Independent witnessing is next. This sentence changes when that ships.

First receipt without an account Evidence is never metered OVERT is open and royalty-free

The record keeps itself.

Our own agents run governed, including the ones that shipped this page. No reports written. No evidence filed. The record follows the work.

1M+

signed evidence records from governing our own AI agents

A published lower bound, not a simulated live counter.

  • PolicyInline
  • DecisionsBlock + redact
  • VerificationOffline
  • Data movementHashes only

People fear what AI can do. What stops them is not knowing who can answer for it.

Incident review

The audit log says a human approved it. The human never saw it.

Vendor renewal

“The model has not changed since the evaluation.” It has changed four times.

Postmortem

Somewhere between demo and deployment, a guardrail was switched off and never switched back on.

Boilers got inspection plates. Aviation got black boxes. Once failure became answerable, entire industries became buildable.

The work happens. The record follows.

Glacis sits where AI acts, applies your policy before the action completes, and leaves behind evidence another party can check.

01

Govern

Policy runs inline on governed inference, tool calls, and agent actions. Blocks and redactions happen before completion.

02

Record

Each governed action seals a signed, hash-chained, content-free receipt. Prompts and outputs stay inside your boundary.

03

Answer

Anyone can verify a receipt offline in a browser or CLI. No Glacis account and no network call are required.

Agent action Send support summary to CRM Requested
Policy Customer identifiers must stay inside the support boundary Applied
Decision Remove two identifiers, then allow Redacted
Record Policy, decision, signer, and chain position sealed Signed
Inspect the machine-readable record
{
  "operation_type": "tool_call",
  "policy": { "id": "customer-boundary-v1", "mode": "enforce" },
  "decision": "redact_then_allow",
  "content_included": false,
  "signature_algorithm": "Ed25519",
  "witnesses": []
}

Start with one governed action. You — or your agent.

The first useful result arrives before the account setup. Start on one machine, then decide whether the rest of the team needs it.

You

Install Glacis and mint a real signed receipt locally. No account. No network.

pip install glacis

Your agent

Give Claude Code, Codex, or Cursor the quickstart and let it perform the install with you watching.

Open the quickstart →

Your team

Add shared policy, workspaces, and fleet coverage when one governed path becomes many.

See team options →

Free forever: mint and verify, unmetered · Paid: workspaces, team policy, and fleet · Next: independent witnessing

What the record proves — and what we refuse to claim.

It proves

  • Which policy was in force at the moment of action
  • What the controls decided
  • Its position in a tamper-evident chain
  • Who signed it, checkable against a pinned key

We will not claim

  • That your system is “safe”
  • Coverage of paths we do not govern
  • “Witnessed” before an independent log witnesses it
  • “Compliance” when the evidence supports only your case

If the claim outruns the product, the build fails. A test reads our marketing. Another keeps every receipt’s witness list empty until an independent witness exists.

We steward OVERT, an open, royalty-free standard for evidence that can travel across vendors, models, clouds, and review systems.

Inspect the standard →
A scale-armored glacier ridge across calm water

Go build something you can stand behind.