Skip to content

Products

Djehuti 10M

One compiled engine, capped at 10,000,000 simulations per run. No install, no source, no hidden dependencies. Just a single binary that does the work.

Djehuti 10M cap · Linux

x86-64 · full AVX2 · AppImage + raw binary

Self-contained Linux build. Run the AppImage on any recent distribution, or use the raw binary directly. No installation, no dependencies.

Formats handled

  • .npy (NumPy) — the primary format
  • .h5 / .hdf5 (HDF5)
  • .mat (MATLAB) — Linux only
  • .vcf (Variant Call Format)
  • .fasta / .fastq (FASTA)
  • .gb / .genbank (GenBank)
  • .json
  • Parquet / Feather / RData via optional python3
  • No CSV / TSV / Excel - convert first with djehuti_prep.py

Formula list

  • Monte Carlo (core, always runs)
  • Heston stochastic volatility
  • Extreme Value Theory (GPD, return levels)
  • Gaussian & C-vine copula
  • SARIMA + GJR-GARCH
  • Markowitz portfolio + VaR/CVaR
  • Engle-Granger cointegration
  • Gaussian HMM regime detection
  • Nelson-Siegel yield curve
  • Random Forest (regression)
  • Bayesian belief update + change-point
  • Correlation (Pearson / Spearman / Kendall)
  • Quantum Monte Carlo
  • Variant calling + population genetics
$299 $499

$200 off with code DJEHUTIGUMGUM

Buy the Linux build on Gumroad

Djehuti 10M cap · Windows

x64 · full AVX2 · single .exe

Single .exe for Windows. No installation, no DLLs. Just run it from the command line on any 64-bit Windows machine with AVX2 (Intel Haswell or later, AMD Excavator or later).

Formats handled

  • .npy (NumPy) — the primary format
  • .h5 / .hdf5 (HDF5)
  • .vcf (Variant Call Format)
  • .fasta / .fastq (FASTA)
  • .gb / .genbank (GenBank)
  • .json
  • Parquet / Feather / RData via optional python3
  • No .mat (MATLAB) — Linux only
  • No CSV / TSV / Excel - convert first with djehuti_prep.py

Formula list

  • Monte Carlo (core, always runs)
  • Heston stochastic volatility
  • Extreme Value Theory (GPD, return levels)
  • Gaussian & C-vine copula
  • SARIMA + GJR-GARCH
  • Markowitz portfolio + VaR/CVaR
  • Engle-Granger cointegration
  • Gaussian HMM regime detection
  • Nelson-Siegel yield curve
  • Random Forest (regression)
  • Bayesian belief update + change-point
  • Correlation (Pearson / Spearman / Kendall)
  • Quantum Monte Carlo
  • Variant calling + population genetics
$299 $499

$200 off with code DJEHUTIGUMGUM

Buy the Windows build on Gumroad

Both builds cap at 10,000,000 Monte Carlo simulations per run. 64-bit, full AVX2 CPU (anything since about 2013).

Preparing your data

Convert CSV / Excel to clean .npy

The engine reads clean binary formats. Use the included for free djehuti_prep.py helper to turn messy spreadsheets into a clean .npy.

prepare data 
# Install dependencies
$ pip install numpy pandas pyarrow openpyxl

# Convert CSV, TSV, Excel, Parquet, Feather to clean .npy
$ python djehuti_prep.py messy.csv clean.npy
$ python djehuti_prep.py data.parquet clean.npy
$ python djehuti_prep.py book.xlsx clean.npy --sheet 0

# Output: clean.npy + clean.cols.json (column names)

System requirements

What you need to run it

Minimum

  • CPU: x86-64 with AVX2 (Intel Haswell 2013+, AMD Excavator 2015+, Ryzen 2017+)
  • RAM: 8 GB (16+ GB recommended for large datasets)
  • Storage: Enough for your data file (engine itself is ~15 MB)
  • OS: Linux: Ubuntu 20.04+ · Debian 11+ · RHEL 8+ · glibc 2.27+
    Windows: Windows 10/11 (64-bit)

Recommended

  • CPU: AMD Zen2+ or Intel Skylake+ (AVX2, more cores = faster)
  • RAM: 16 GB or more
  • Storage: SSD for large files (engine mmap-reads at disk speed)
  • OS: Linux (Ubuntu 24.04+ ideally 26.04 for GGC 15, Debian 11+, any modern distro)
    Windows: Windows 10/11 (64-bit)

Linux compatibility

  • Ubuntu: 20.04 LTS, 22.04 LTS, 24.04 LTS (and newer)
  • Debian: 11 (Bullseye), 12 (Bookworm) and newer
  • RHEL / Alma / Rocky: 8 and 9
  • Fedora: 38 and newer
  • Arch Linux: Current
  • Any modern Linux with glibc 2.27+ (Ubuntu 18.04+, Debian 10+, RHEL 8+)

AVX2 is mandatory. The engine uses AVX2/FMA instructions. Most VPS instances (4-6 core EPYC) are Zen2+ or later and support AVX2 natively.

Linux: AppImage or raw binary (no dependencies)
Windows: Single .exe (no DLLs, no install)

Mac: Not currently supported.