LCOS-Core is public proof of mechanism for governed antigenic systems.
Our own unified, OpenAI-compatible LLM router (sovereign-first, honest provenance).
Λ (Lambda-Spine) aggregator universal kernel — weighted geometric mean over axis scores in [0,1] with an ADVISORY governance gate + A1-A4 axiom self-checks. Λ = Conjecture 1 (advisory, uniqueness open) · NOT proven trust. Mirrors HF SZLHOLDINGS/szl-lambda-gate · Apache-2.0.
SZL khipu-sda-core — sovereign clean-room anomaly/SDA engine (Domain-Superiority). Signed receipts + Λ-gated honest confidence. Doctrine v11. Clean-room from permissive lineage; inspired by True Anomaly Mosaic (not affiliated).
Governed RMSNorm/LayerNorm universal kernel — correctness-verified normalization with optional SHA3-256 hash-chained provenance receipts. Mirrors HF SZLHOLDINGS/szl-governed-norm. Λ = Conjecture 1 (advisory) · Apache-2.0.
SZL Living Anatomy — 3D navigable governed-AI organ substrate. Visualizes the 5 organs (reasoning cortex, trust gate, receipt bus, consensus, egress) powering a11oy + killinchu. Doctrine v11 LOCKED · 8 proven formulas · Λ = Conjecture 1.
Energy-metered governed inference receipts — NVML joules, tokens/joule, advisory policy gate. Hash-chained, DSSE-signed. Honest UNAVAILABLE when NVML unset. Λ = Conjecture 1 · Apache-2.0.
Add a description, image, and links to the governed-inference topic page so that developers can more easily learn about it.
To associate your repository with the governed-inference topic, visit your repo's landing page and select "manage topics."