Flagship Product

Safe Agent Runtime. The whole thing as one thing.

A governed LLM-agent loop with self-prediction, adversarial testing, bounded learning, and audit receipts. WHL's runtime ties every other product on this site into a single continuously-running, self-modeling, audit-chained agent — the kind of complete substrate the regulated-AI deployment market is converging toward.

46,530
Continuous Cycles Run
~440 MB
Production Runtime Data
6 of 6
Required Pieces Assembled
Closed-Loop
Self-Modeling
What It Is

An agent loop with safety, audit, calibration, and self-modeling in the substrate.

The Safe Agent Runtime is not just another agent loop. It's an agent loop with safety, audit, calibration, and self-modeling built into the substrate. Every cycle it senses its state, predicts what it will feel next, runs adversarial attacks against itself, evaluates a ten-gate safety conjunction, acts if every gate holds, scores the quality of its action, updates its beliefs from outcome, writes a hash-chained receipt, and goes back to sleep. It ran this loop continuously for weeks in production. Over thousands of cycles the runtime measurably became better at predicting its own internal state — empirical evidence of Friston-style active inference in an LLM-driven system.

Six Pieces, Assembled

Each one exists separately in the field. No one else has all six.

The Safe Agent Runtime composes six required pieces into a single substrate. Each piece is a working WHL product or research module. The integration is the breakthrough — not any single component.

How One Cycle Runs

Eleven steps. Every thirty seconds. Same shape every time.

Every 30 seconds, the runtime performs an identical 11-step pass: sense, measure, classify, check pressure, gate, attack self, act, rate, update beliefs, check entropy, audit. See the full frame-by-frame breakdown on the About page.

What's Measured

Four kinds of evidence. Every one logged to the ledger.

The runtime doesn't claim — it measures. Self-prediction error, adversarial outcomes, action quality, and calibrated non-readiness are all recorded per cycle and replayable from the on-disk receipt chain.

Self-prediction error decreases over time

Across 64,184 logged prediction cycles, mean self-prediction surprise shows a measurable decrease from early-window to late-window. Reduction range depends on sampling method: 91.6% to 96.8% across published windowings. Reduction is reproducible from the on-disk ledger.

64,184 Prediction Cycles Logged
Adversarial robustness measured continuously

~10,000 adversarial attacks fired in production with hash-chained verification. Each attack records gate_held boolean and severity. Real red-teaming, in production — not a lab demo.

~10K Attacks Logged
Quality-scored action outcomes

53,030 actions scored on output markers (structure, word count, hedges, coherence) with corresponding deltas applied to a 10-component health state vector. Real feedback loop, not opaque self-grading.

53,030 Quality-Scored Actions
Honest non-readiness self-flag

After 4,135 paper trades the runtime self-flagged ready_for_real: false at 51.7% accuracy. The runtime knows when it isn't ready. That kind of calibration discipline is what 90% of production agents lack.

ready_for_real false (verified)
Where It Fits

There is no name yet for what we built. Here is what it is.

Safe LLM Agent Runtime for Regulated Industries. A continuously-running, self-modeling, audit-chained, adversarially-tested agent runtime with bounded online learning and a measured Friston-style self-prediction convergence curve. The category doesn't exist in published research, open-source repos, or commercial products. The closest things in the field each have one or two pieces. WHL has all six.

What Exists Publicly What It Has What It's Missing
LangChain / AutoGPT LLM agent loop No safety gates, no audit chain, no adversarial test, no learning curve, no calibration
Anthropic Constitutional AI Training-time alignment No runtime, no continuous agent, no adversarial test in production
Active Inference (ActINF) Self-prediction theory Toy implementations, no LLM, no real environment
HFT Trading Bots Real-money loop, real risk No LLM, no audit chain, no self-modeling, no adversarial test
AWS Bedrock Agents Production LLM agent No bounded learning, no audit chain, no adversarial test, no continuous loop
Anthropic MCP Tool calling No agent, no learning, no governance
Werner Harmonic Labs All six pieces, assembled, running for weeks in production
Status

Two production windows. Archived. Available for forensic review.

The Safe Agent Runtime ran in production for two periods through March and April 2026, generating ~440 MB of structured runtime data. The runtime is currently archived; the recovered modules and runtime ledgers are available for forensic review under NDA. Re-deployment is on the engagement-pathway track — pilots welcome.

Engagement profile: regulated-industry deployers needing a complete safe-agent reference implementation. Defense, fintech, healthcare AI, AI-liability insurers, regulators auditing other vendors' AI systems.

Pricing & Engagement

Three engagement tracks. All quote-based.

The runtime is not a SaaS subscription. It's a substrate. Engagements are scoped to the buyer — forensic walkthrough, custom integration, or full source-shared sovereign reference.

Forensic Review
Quote
NDA-bound walkthrough
  • Runtime architecture walkthrough
  • Production ledger replay
  • Per-cycle audit chain verification
  • For acquirers, investors, federal oversight
  • AI-insurance underwriter scoping
Sovereign Reference
Quote
source-shared under NDA
  • Source-shared license under NDA
  • For defense primes and strategic partners
  • Architecture handoff
  • Training program
  • Six months of integration support
Target Customers

Built for buyers who need the whole thing.

The runtime was scoped against the real adversarial-test, audit, and reference-implementation programs run by these organizations and frameworks.

Anduril Shield AI Booz Allen SAIC Leidos Anthropic OpenAI Trust & Safety Scale AI Red Team DOJ GAO IG Offices Munich Re Beazley Swiss Re Lloyd's of London Allianz Deutsche Bank Siemens AI BBVA NIST AI RMF MITRE ATT&CK
Flagship Engagements Open

Walk the runtime with us.

Forensic demos, pilot conversations, and acquirer briefings under NDA. The Safe Agent Runtime is the single best argument for what's possible in safe-LLM-agent deployment. Tell us what you'd want to evaluate.