KYVLT FOR CHATGPT, CODEX, AND AI AGENTS

Authority that survives every model change.

KYVLT gives compatible agents stable passports, bounds multi-agent delegation, enforces policy outside the conversation, and returns a verifiable receipt for each final decision.

A complete control loop

Before, during, and after an agent action

Identify

Give each agent a stable declared passport without granting authority.

Bound

Set risk, territory, rate, reversibility, and delegation depth.

Prove

Bind each final decision to the action, policy snapshot, and actor chain.

TRY THESE PROMPTS

Three concrete workflows

Create a seven-day mandate that lets my agent prepare calendar events but requires my approval before creation.
Check whether this €300 booking fits a €400 budget, then ask me before authorizing it.
Stage this email under my mandate, but do not send it until I approve the exact recipients and body.

14 TOOLS · OAUTH 2.1 · MCP

From agent passport to action receipt.

The tools list passports and My Rights leads, draft and simulate mandates, govern proposed actions, wait for human decisions, verify evidence, record real outcomes, and revoke authority.

WHY KYVLT

Control that lives outside the conversation

  • Deterministic limits checked on the server.
  • Configurable human approval for sensitive actions.
  • Immediate revocation and no plaintext mandate-token storage.
  • Public proof separated from private action authorization.

Essential limitation

KYVLT governs only agents and services that call its API or tools. It cannot intercept an unconnected AI, and it does not replace the security, consent, or payment controls of Gmail, Google Calendar, a merchant, or a bank.