SWT3 - Sovereign Witness Protocol for AI

Don't audit the agent's thoughts. Audit the agent's actions.

AI agents are making production decisions: approving loans, triaging patients, managing infrastructure, writing code. In 2026, 65% of firms reported AI agent security incidents. Only 14.4% of agents go live with full security approval. When something goes wrong, there is no tamper-proof audit trail. Logs are mutable. Metrics are averaged. Nobody can prove what the agent actually did.

GPAI transparency obligations are enforceable now. EU AI Act high-risk enforcement begins December 2, 2027. NIST AI RMF, SR 11-7, and CMMC impose similar obligations. 72% of enterprises believe they have AI governance but lack actual control. Most teams have nothing but dashboards and hope.

SWT3 (Sovereign Witness Traceability) is a deterministic witness protocol for AI systems. It intercepts AI actions, hashes the evidence, and anchors cryptographic proof to an immutable ledger. Your code gets the full response. The auditor gets tamper-proof evidence. Raw prompts and responses never leave your infrastructure.

• Deterministic, not probabilistic. The witness engine uses fixed logic, not AI, to evaluate compliance.
• Zero data retention. Configurable clearing levels strip sensitive content before it leaves your environment.
• Framework-mapped. Every anchor maps to EU AI Act articles, NIST AI RMF functions, and federal controls.

Python

pip install swt3-ai
python -m swt3_ai.demo

TypeScript

npm install @tenova/swt3-ai
npx swt3-demo

No API keys. No account. No network calls. You will see the full witnessing pipeline run locally.

from swt3_ai import Witness
from openai import OpenAI

witness = Witness(endpoint="https://sovereign.tenova.io", api_key="axm_live_...", tenant_id="YOUR_TENANT")
client = witness.wrap(OpenAI())

# Every inference is now witnessed. Your code does not change.
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Summarize this contract"}],
)

Works with OpenAI, Anthropic, AWS Bedrock, Vercel AI SDK, LangChain, LiteLLM (100+ providers), and any OpenAI-compatible endpoint (vLLM, Ollama, Azure OpenAI).

Each inference produces anchors across 40 AI procedures spanning 20 domains:

Plus 9 additional procedures covering fairness, explainability, training data, and bias measurement. See the full procedure registry.

A Level 1 anchor for AI-INF.1 (Inference Provenance). This is what reaches the witness ledger. No prompts, no responses, just cryptographic proof.

{
  "procedure_id": "AI-INF.1",
  "factor_a": 1,
  "factor_b": 1,
  "factor_c": 0,
  "clearing_level": 1,
  "anchor_fingerprint": "c059eb5938c0",
  "anchor_epoch": 1774800000,
  "fingerprint_timestamp_ms": 1774800000000,
  "ai_prompt_hash": "315f5bdb76d078c4",
  "ai_response_hash": "a1b2c3d4e5f60718",
  "ai_latency_ms": 842,
  "ai_model_id": "gpt-4o",
  "ai_context": {
    "provider": "openai",
    "guardrails": ["content-filter", "pii-redaction"]
  }
}

The anchor_fingerprint is computed from SHA256("WITNESS:{tenant}:{procedure}:{fa}:{fb}:{fc}:{ts}"). Anyone with the factors can independently verify the math. Trust is a vulnerability. Math is the remedy.

The clearing engine controls what leaves your infrastructure. Your code always gets the full response. Clearing only affects what reaches the witness ledger.

At Level 1+, raw prompts and responses never leave your infrastructure.

Both SDKs produce identical SWT3 fingerprints. 21 cross-language test vectors validated at build time.

1. Create a free account - instant API key, no credit card
2. pip install swt3-ai or npm install @tenova/swt3-ai
3. Wrap your AI client. Every inference is witnessed.

packages/swt3-ai/       Python SDK (PyPI: swt3-ai)
packages/swt3-ai-ts/    TypeScript SDK (npm: @tenova/swt3-ai)
packages/swt3-ai-rust/  Rust SDK (crates.io: swt3-ai)
packages/swt3-ai-dotnet/ C# SDK (NuGet: swt3-ai)
packages/swt3-ai-ruby/  Ruby SDK (RubyGems: swt3-ai)
packages/swt3-mcp/      MCP Server (npm: @tenova/swt3-mcp)
packages/libswt3/       Protocol reference implementation
config/                 Control definitions and framework crosswalks

Your prompts and responses never leave your infrastructure. The SDK computes SHA-256 hashes locally and transmits only irreversible hashes and numeric factors to the witness ledger. At Clearing Level 3, even the model name is hashed.

• Data Flow and Privacy Architecture - Visual data boundary for legal and DPO review
• Clearing & Data Sovereignty Addendum - Shared responsibility, incident response SLA, regulatory applicability
• Air-Gap Deployment Guide - Zero-egress operation, sneakernet sync, offline verification

• SDK Developer Docs - Quickstart, providers, clearing levels
• Factor Handoff Protocol - Secure factor custody transfer
• CMMC Compliance Overlay - Defense industrial base mappings
• SR 11-7 Compliance Overlay - Model risk management mappings

See CONTRIBUTING.md for development setup and guidelines.

Apache 2.0. See LICENSE. Patent pending.

If you believe AI systems should prove they followed the rules, give us a star.

SWT3: Sovereign Witness Traceability. We don't run your models. We witness them.

TeNova - Defining the AI Accountability Standard.