Downloads and demos

Try LuxiBook on your own machine.

LuxiBook is the product try: a closed-binary deterministic option-book pricer with a signed receipt on every run. Every run emits a signed receipt: a SHA-256 fingerprint of the output numbers, sealed with an Ed25519 signature from the install that produced them. LuxiRisk is a free, secondary LuxiQuant project further down this page. Inference evidence lives on Evidence and Research.

1 · LuxiBook · public demonstration

LuxiBook: deterministic option-book pricing with receipts

LuxiBook takes a CSV position book, prices it with European Black-Scholes / Black-76, returns five Greeks per position, and attaches a signed receipt to the run. You bring time to expiry, rate, and volatility. No live market feed, no implied-volatility solver, no VaR.

Downloads

FilePlatform
luxi-book-macos-arm64macOS Apple Silicon (CPU)
luxi-book-linux-x86_64Linux x86_64 (CPU)
luxi-book-linux-x86_64-cudaLinux + NVIDIA GPU (--mode gpu)
example_book.csvExample position book
*.sha256 checksums (repository folder)Matching checksums for every file, in the download folder

There is no macOS GPU binary. The CUDA build needs a live NVIDIA driver. Binaries are unsigned: on macOS, right-click the file and choose Open the first time.

Run it

# Mac CPU
chmod +x luxi-book-macos-arm64
./luxi-book-macos-arm64 price --book example_book.csv --out report.csv --receipt receipt.json

# Linux CPU
./luxi-book-linux-x86_64 price --book example_book.csv --out report.csv --receipt receipt.json

# Linux CUDA
./luxi-book-linux-x86_64-cuda price --book example_book.csv --out report.csv --receipt receipt.json --mode gpu

Verified public example book (2026-08-16)

Running the published example_book.csv through the published v0.2.1 binaries produced the same output hash on H200, H100, A100, RTX 5090 and RTX 4090, on both the LuxiBook CPU and CUDA pricing paths. Internal LuxiBook measurement. All twenty receipts from the original matrix remain published in the repository.

FieldValue
Bookexample_book.csv (10 rows, published)
Output hash - example book4a21b1e708fa5c694bf48237df5e5bd3b94599e6273d07986283c6c6b8e3c97a
Book total - example book151.70016507843832
ATM_CALL price10.4505835721856215
Enginev0.2.1. The stored receipts record engine_version 0.2.0 because they were measured before the version string was bumped.
Receipts published20, each Ed25519-signed, across 5 installs
Receipts folderdownloads/luxibook/evidence/v0.2.1-phi-fix-matrix
DateAugust 16, 2026
MachineArchitectureCompute capabilityCPU pathCUDA path
NVIDIA H200Hopper9.0matchmatch
NVIDIA H100Hopper9.0matchmatch
NVIDIA A100Ampere8.0matchmatch
NVIDIA RTX 5090Blackwell12.0matchmatch
NVIDIA RTX 4090Ada8.9matchmatch

Every row is one physical machine with its own install key. The published folder preserves all 20 signed receipts from the original two-book matrix. Each machine's compute capability is recorded in its receipt. Apple Silicon has a published binary and was covered by an earlier check, but it is not part of this matrix; there is no macOS GPU binary.

Scope of the receipt claim. The verified public pin applies to example_book.csv, these machines, and the LuxiBook pricing kernel. It is not evidence that Risk State Engine numerical risk aggregation runs on these GPUs. LuxiBook is not desk VaR, live markets, or a fund product.

2 · LuxiRisk · free secondary project

LuxiRisk: free offline position-sizing CLI

LuxiRisk is a free LuxiQuant project that demonstrates accessible, reproducible risk analysis. It is an offline command-line tool for liquidation price, position sizing, and maximum dollar loss. Every calculation can carry an Ed25519 signed receipt (lxr1_…).

This remains a separate legacy demonstration, not a retail crypto company. For the institutional try, use LuxiBook.

Binaries are unsigned, so expect the usual macOS Gatekeeper or Windows SmartScreen friction on first launch.

3 · Evidence

Inference evidence lives elsewhere

Luxi Inference prefill and decode measurements are on Evidence and Research. Independent TestFort, internal matched, and internal absolute results are kept separate. Board joules are GPU-board energy, not wall-plug. Prefill positions are not decode tokens.