Evidence, not adjectives.

Every claim is backed by working code, measured benchmarks, and where appropriate cryptographically auditable reduction-to-practice. Five technical reports below — one preparing arXiv submission. Source on github.com/thornveil-ai.

What's actually defensible.

Each Thornveil system carries one or more subsystems where the engineering work materially differentiates it from open-source alternatives. Named subsystem, the differentiator, and the empirical evidence behind each.

Mycelium

Substitute-on-failure MoE expert dispatch

Day-27 RTP with HMAC-chained audit log, 2026-05-08

Auspex

Scope-as-code engagement compilation + 13-check Signet gate

Autonomous AD takeover with auditable replay, 2026-05-16

RigRun

Compile-time classification-gated routing with cross-domain guard

Type-system enforced · 44 NIST 800-53 controls implemented

RigRun

8-signal confidence pipeline with adversarial self-audit

~4,220 LOC across 8 signals · cross-app parity in Go/Dart/TS

Signet

HMAC-chained tamper-evident audit ledger with RFC 3161 anchoring

2,400 LOC across chain.py + verifier.py + compactor.py · 7-state break taxonomy

HawkStack

Compute-aware neural topology recipe (3-parameter)

15 verified zoo checkpoints · R²=0.9895 power-law fit on NUDT-SIRST

Pyros

24-layer adaptive control loop (PID + Holt + UCB1 + ε-greedy)

Race-clean CI across Linux/macOS/Windows · PAVA calibration validated vs sklearn

Meridian

Phase 10 trade-secret primitives — attest, secdef, beacon, vehicle-id, log

~5,500 LOC across 5 crates · not shipped in ArduPilot or PX4

Navigator

14-step agent-production pipeline with Opus calibration + 5-probe adversarial hardening

9 production domain-expert agents generated by the pipeline

10
engineering systems
5
technical reports written
2
Apache-2.0 OSS releases