SWT3 - Sovereign Witness Protocol for AI

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

The Problem

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.

The Protocol

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.

Try It (10 Seconds, No Account)

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.

Three Lines to Production

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).

K8s Hardware Attestation

AI compliance doesn't stop at the model layer. Regulators want to know what hardware ran the inference, whether it was authorized, and whether the compute environment changed between audit periods. Today, no platform provides cryptographic proof of which silicon processed which workload. SWT3 does.

Deploy a DaemonSet that discovers accelerator hardware on every node and mints AI-HW.1 attestation anchors. Zero application code changes. One Helm install.

helm install swt3-witness oci://ghcr.io/tenova-labs/charts/swt3-witness \
  --set config.endpoint="https://sovereign.tenova.io" \
  --set config.apiKey="axm_live_..." \
  --set config.tenantId="YOUR_TENANT"

The DaemonSet auto-discovers 6 accelerator types per node:

Discovery Path	Silicon	Method
NVIDIA GPU	A100, H100, H200, B200, GB200, NVL72	nvidia-smi
Google TPU	v4, v5e, v5p, v6e, Trillium	TPU_NAME env
AMD MI	MI300X, MI325X, MI250	rocm-smi
AWS Trainium	Trainium2, Inferentia2	neuron-ls
Intel Gaudi	Gaudi3, Gaudi2	hl-smi
PCI Fallback	Any 3D controller / processing accelerator	/sys/bus/pci

Each node reports its silicon vendor, topology, memory, and per-accelerator detail. Non-accelerator nodes produce a valid anchor attesting "no accelerator detected" -- absence of hardware is also auditable evidence. Mixed-silicon clusters (NVIDIA + TPU + AMD in the same cluster) are fully supported.

What this proves to your auditor:

• Which hardware ran each AI workload (EU AI Act Art. 15(4), NIST 800-53 SI-7)
• Whether the compute environment changed between assessments (drift detection)
• That inference didn't silently migrate to unauthorized or unqualified silicon
• Full hardware provenance from silicon to model, combined with AI-HW.3 (TPM attestation)

The witness context includes silicon_vendor, discovery_method, and accelerators[]. All device identifiers are SHA-256 hashed before leaving the node. Serial numbers, UUIDs, and bus IDs are never transmitted in plaintext.

See the Cross-Silicon K8s Attestation Guide for GKE, EKS, AKS, and on-prem deployment patterns.

What Gets Witnessed

Each inference produces anchors across 103 AI procedures spanning 52 namespaces:

Procedure	Domain	What It Proves	Regulatory Mapping
AI-INF.1	Inference	Prompt and response captured (provenance)	EU AI Act Art. 12
AI-INF.2	Inference	Latency within threshold (detects model swaps)	NIST AI RMF MEASURE 2.6
AI-MDL.1	Model	Deployed model matches approved hash (integrity)	EU AI Act Art. 9
AI-MDL.2	Model	Model version identifier recorded (tracking)	EU AI Act Art. 72
AI-MDL.5	Model	Weight file SHA-256 verified (tamper detection)	EU AI Act Art. 15(4)
AI-MDL.6	Model	LoRA/PEFT adapter stack attested	EU AI Act Art. 12(2)(b)
AI-MDL.7	Model	Quantization method recorded	EU AI Act Art. 15(3)
AI-GRD.1	Guardrail	Required safety filters were active (enforcement)	NIST AI RMF GOVERN 1.5
AI-GRD.2	Safety	No content filter or refusal triggered	EU AI Act Art. 14
AI-GRD.3	Gatekeeper	Pre-call guardrail gate enforced	EU AI Act Art. 9(2)
AI-RAG.1	Retrieval	RAG context chunks and corpus attested	EU AI Act Art. 12(2)(a)
AI-RAG.2	Retrieval	Retrieval relevance scoring verified	EU AI Act Art. 10(2)
AI-TOOL.1	Tool Use	Agent tool/function call recorded (latency, success)	NIST AI RMF MANAGE 4.1
AI-ID.1	Identity	Witness instance identity attested (agent accountability)	EU AI Act Art. 13
AI-ACC.1	Access	Resource access granted or denied with scope	EU AI Act Art. 9(4)(c)
AI-REV.1	Revocation	Previously-issued anchor revoked with reason	EU AI Act Art. 12(3)
AI-SEC.1	Security	Adversarial threat detection performed	EU AI Act Art. 15(4)
AI-SEC.2	Security	Input validated and sanitized before inference	EU AI Act Art. 15(3)
AI-SKILL.1	Skills	Loaded skill/tool/plugin manifest attested	EU AI Act Art. 12(2)(b)
AI-SKILL.2	Memory	Active memory sources bound to decision	EU AI Act Art. 12(2)(a)
AI-SKILL.3	Alignment	RLHF/DPO reward model binding recorded	EU AI Act Art. 9(4)(a)
AI-CHAIN.1	Chain	Multi-agent handoff witnessed with cycle tracking	EU AI Act Art. 12(2)(a)
AI-VIO.1	Violation	Policy violation detected during inference	EU AI Act Art. 9(4)(a)
AI-CHR.1	Charter	Agent charter/system prompt hash attested	EU AI Act Art. 13
AI-MDL.8	Model	Model verified against approved registry	EU AI Act Art. 51
AI-HITL.3	Oversight	Reviewer identity bound to human review	EU AI Act Art. 12(3)(d)
AI-SAFE.1	Safety	Stop mechanism tested, safe state confirmed	EU AI Act Art. 14(4)(e)
AI-HW.1	Hardware	GPU/accelerator inventory attested at startup	EU AI Act Art. 15(4)
AI-TRUST.1	Trust	Mutual compliance trust verified between agents	EU AI Act Art. 9(4)(c)
AI-TRUST.2	Trust	Trust handshake details recorded	EU AI Act Art. 12(2)(a)
AI-MARK.1	Content	Content provenance marking attested	EU AI Act Art. 50(2)
AI-BASE.1	Baseline	Agent behavioral baseline monitored	NIST AI RMF MEASURE 2.6
AI-ENV.1	Environment	Runtime environment fingerprint recorded	EU AI Act Art. 15(4)
AI-ENV.2	Environment	Dependency manifest attested	EU AI Act Art. 15(3)
AI-DATA.3	Data	Training data lineage attested	EU AI Act Art. 10(2)
AI-DATA.4	Data	Data quality metrics recorded	EU AI Act Art. 10(3)
AI-CHAIN.2	Chain	Chain-of-trust credential verified	EU AI Act Art. 9(4)(c)

Plus 65 additional procedures covering fairness, explainability, inference volume, model drift, human oversight, cybersecurity, supply chain, content marking, agent lifecycle, financial transactions, and cross-border routing. See the full procedure registry.

View an Anchor

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.

Clearing Levels

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

Level	Name	On the Wire	Use Case
0	Analytics	Hashes + factors + model + provider + guardrails	Internal analytics
1	Standard	Hashes + factors + model + provider	Default. Production apps
2	Sensitive	Hashes + factors + model only	Healthcare, legal, PII workloads
3	Classified	Numeric factors only. Model ID hashed.	Defense, air-gapped environments

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

SDKs

Language	Package	Install
Python	swt3-ai	pip install swt3-ai
TypeScript	@tenova/swt3-ai	npm install @tenova/swt3-ai
Swift	swt3-ai	Swift Package Manager
Rust	swt3-ai	cargo add swt3-ai
C#	swt3-ai	dotnet add package swt3-ai
Ruby	swt3-ai	gem install swt3-ai
MCP Server	@tenova/swt3-mcp	npx @tenova/swt3-mcp

7 SDKs, identical fingerprints. 207 cross-language test vectors validated at build time.

Get Started

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.

Regulatory Coverage

Framework	Coverage
EU AI Act	Articles 9, 10, 12, 13, 14, 15, 50, 51, 53, 72
NIST AI RMF	GOVERN, MAP, MEASURE, MANAGE (10 subcategories)
NIST 800-53	SI-7, AU-2, AU-3, AC controls
CMMC v2.0	Level 2 practice mappings
SR 11-7	Model Risk Management (5 examination areas)
ISO 42001	Annex A AI management controls

Repository Structure

packages/swt3-ai/        Python SDK (PyPI: swt3-ai)
packages/swt3-ai-ts/     TypeScript SDK (npm: @tenova/swt3-ai)
packages/swt3-ai-swift/  Swift SDK (Swift Package Index)
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/swt3-witness/   K8s DaemonSet (GHCR + Helm)
packages/libswt3/        Protocol reference implementation
config/                  Control definitions and framework crosswalks

Compliance & Privacy

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

Documentation

• 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

Contributing

See CONTRIBUTING.md for development setup and guidelines.

License

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.