Sanna

Your Agents Are Making Decisions You Can't Control or Prove

An AI agent approves a loan, triages a patient, sends a contract to a counterparty — or books a flight and moves money on your behalf. Two things should have happened before that output left your system: something should have stopped it if it violated policy, and something should have recorded proof that it didn't.

Neither happened. There's no runtime enforcement — your governance rules live in a wiki, not in the execution path. And there's no evidence trail — you have logs and metrics, but nothing a regulator, auditor, or counterparty would accept as proof the agent operated within its authority.

AI governance legislation is accelerating worldwide — laws are already live or taking effect in the US, EU, South Korea, Vietnam, and more are coming. Your compliance team is asking for runtime enforcement and verifiable evidence. Your customers will too. The gap between what your agents are doing and what you can enforce and prove is a liability waiting to surface.

Two Equal Pillars

Five Lines to Governed AI

Wrap the functions you want to govern. Every call is checked against your constitution, and a signed receipt is generated automatically.

from sanna import sanna_observe, SannaHaltError

@sanna_observe(
    constitution_path="constitution.yaml",
    constitution_public_key_path="~/.sanna/keys/<key-id>.pub",
)
def my_agent(query: str, context: str) -> str:
    return "Based on the data, revenue grew 12% year-over-year."

try:
    result = my_agent(query="What was revenue growth?", context="...")
    print(result.output)   # The original return value
    print(result.receipt)  # Cryptographic governance receipt
except SannaHaltError as e:
    print(f"HALTED: {e}")  # Constitution violation detected

// Signed, offline-verifiable proof generated for every governed action
{
  "spec_version": "1.0",
  "receipt_id": "a7e3b1f0-4c2d-4a8e-9f1b-3d5e7a9c2b4d",
  "receipt_fingerprint": "30dedec9373c4d9b",
  "status": "PASS",
  "checks_passed": 5,
  "checks_failed": 0,
  "context_hash": "a43401a2a64954e9...c3797e1231415",
  "output_hash": "5eebc757bbbe8b82...2f38a69f89",
  "constitution_ref": {
    "document_id": "financial-services-v2",
    "policy_hash": "8f3a9b2c1d4e5f6a",
    "signature_verified": true
  },
  "enforcement": {
    "action": "allowed",
    "reason": "All checks passed",
    "failed_checks": [],
    "enforcement_mode": "halt"
  },
  "receipt_signature": {
    "signature": "ed25519:2f8c4d9e1a7b...",
    "scheme": "receipt_sig_v1"
  }
}

Three Steps

Four Ways to Deploy

Shipped, Not Slideware

Five independent security review cycles. A published formal specification. Production-grade cryptographic engineering tested across two languages, multiple runtimes, and 48 cross-language interoperability tests.

Enterprise-Grade, Open Source

Sanna ships with the governance lifecycle tooling that regulated industries require. All of it is free, open source, and available today.

Four Repos. One Standard.

Sanna is a multi-language ecosystem built around a single open specification. Every component generates and verifies the same receipt format.

Built for Anyone Running Agents

Receipt format designed for the evidence and audit requirements emerging across AI governance legislation worldwide — and new laws are being enacted every quarter. Portable receipts. Vendor-neutral verification. Constitutions your compliance team — or just you — can actually read.