Harborlight Firewall
Tamper-evident machine-state logging for AI-agent environments — a two-binary witness + enforcer design with Merkle-chained records, gossip mesh, and a transparency mirror. The public core of the SGAIL Firewall.
Portfolio
The work.
A spectrum from published open-source detection models to private infrastructure and active research. Public repos are linked; private and pre-release work is described at a high level and available on request.
Flagship — SGAIL Firewall
Our core product line: real-time enforcement and tamper-evident witnessing for AI-to-AI systems.
Harborlight Node
Edge-first, offline advisory node: an LLM operates advisory-only behind a policy gate and witness ledger, with one-way cloud sync. Working prototype for high-assurance edge deployments.
Private — request access
Adversarial-input defense
A coherent family of MIT-licensed, published detection primitives. These are the models our training datasets are built from.
split-brain-harness
Dual-hemisphere security layer wrapping any LLM: prompt injection, insider-threat, authority impersonation, and multi-turn escalation detection. Drop-in OpenAI-compatible proxy, offline, single binary. Benchmarked on three adversarial datasets.
deobfuscate
Multi-pass text deobfuscation / encoding-evasion detector for LLM security pipelines. Strips homoglyph, base64, Morse, and leet evasions and returns an audit report. ~2k prompts/sec.
deobfuscate-vision
Image-borne prompt-injection detection: extracts every machine-readable text channel — white-on-white, sub-pixel fonts, alpha overlays, EXIF, QR — and scores it with the deobfuscate engine. The multimodal companion crate.
unicode-interference
Detects hidden non-Latin and homoglyph characters via forward/reverse script-identification interference. Zero-dependency, no_std library and CLI.
glyph-validator
Python CJK glyph geometric-coherence validator: a deterministic NumPy/OpenCV gateway (no LLM) that catches malformed or spoofed CJK glyphs before they enter a pipeline.
Research & concepts
Active research not yet released. Shared here as direction, not shipping products.
topological-rag
A four-pathway topological RAG orchestrator (Rust workspace + FastAPI sidecar): an advisory-only LLM boundary with adversary (hallucination-flagging) and synthesizer pathways, backed by a witness log.
Pre-release
Gatekeeper V2
Intent-centered supervisory system for AI-to-AI and AI-to-tool interactions: hash-chained event log with drift and trust scoring. Local-first, TypeScript.
Pre-release
R-LLM
Dual-hemisphere split-brain LLM security classifier: two lenses reconcile a verdict, with a superposition-collapse probe. The research root beneath the split-brain harness.
Research
GovTech & intellectual property
Domain-specific systems and formal disclosures. Sensitive systems are described at capability level only.
SLATE
Tamper-evident chain-of-custody evidence management: a local node with Ed25519-signed, court-defensible exports. Built for public-safety evidence integrity.
HIFAS
Hawaii Integrated Fraud Analytics System: a deterministic, court-defensible verdict engine where AI surfaces candidates and the rules engine decides. Sensitive government domain — described at capability level only.
Private — NDA required
Thumb-Server
Topological Photonic Thumb-Server — a formal 35 U.S.C. §102 prior-art disclosure (inventor Christopher Howard). Published to establish IP position, not a shipping product.
Want to build on this stack?
Pilots, dataset work, and research collaborations are all on the table. Start a conversation with the lab.
Engage SGAIL Labs