Djehuti 10M — Cross-industry analysis engine
Launch price $299 $499 $200 off

Djehuti

10M SIMS cap

One binary. One file in > the analysis out.
Cross‑industry, offline, zero disk writes.

213M sims/sec on our 10‑year‑old Ryzen 12.4× faster than pandas 1.4M correlations/sec

What it does

Cross‑industry analysis

Quant, insurance, energy, telecom, genomics, climate, manufacturing — the same engine adapts to your domain. Run the modules you need.

Amnesiac mmap, zero disk writes

Mapped read‑only (MAP_PRIVATE | MAP_NORESERVE). Never copied, never decompressed fully. No temp files, no caches — each run leaves no trace.

Read from chunk, no full decompress

Large files (VCF, FASTA, HDF5) stream directly from the mmap. Swap‑friendly, RAM‑efficient, and fast — even on 8GB machines.

Performance, proven

Runs on what you already own.

213M

simulations per second on a Ryzen 5 1600X

50M draws in 234 ms — real DJIA params

12.4×

faster than pandas

177×177 Pearson matrix in 10.99 ms vs 136.50 ms

1.4M

correlations per second

2534 observations, full 177×177 matrix

Tested on a 10‑year‑old AMD Ryzen 5 1600X with 8GB DDR4. Pure AVX2. No custom kernel.
The more cores and RAM you have, the faster it runs. AVX‑512 builds coming soon.

Modules

What's inside

Selectable modules. Run what you need with --modules. The Monte Carlo core runs automatically.

Name Domain What it computes
montecarlo core high-throughput simulation of the series
correlation cross Pearson / Spearman / Kendall, partial correlation, significance
bayesian cross Normal-Normal belief update + change-point
heston quant Heston stochastic-volatility calibration + simulation
evt quant/risk Extreme Value Theory (POT / GPD) + return levels
copula quant Gaussian and C-vine copula dependence
timeseries quant/ML SARIMA + GJR-GARCH volatility
portfolio quant Markowitz portfolio + VaR / CVaR
cointegration quant Engle-Granger cointegration / pairs
hmm ML Gaussian hidden Markov regime detection
fixedincome quant Nelson-Siegel yield curve
randomforest ML Random Forest regression / classification
qmc numeric Quantum Monte Carlo (harmonic oscillator)
variants genomics VCF variant calling / cohort summary
popgen genomics population genetics

--modules heston,evt,copula · --modules all · --modules 0x1400

Formats

What it reads

Linux

  • .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

Windows

  • .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

Data preparation

Convert CSV / Excel to clean .npy

The engine reads clean binary formats. Use the included 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)

Recipes

Cross‑industry module combos

The engine's strength is the mix. Pick the modules that match your question. The Monte Carlo core runs automatically.

Industry --modules recipe Reads as
Finance / quant heston,evt,copula,cointegration,portfolio pricing + tail risk + dependence + pairs + allocation
Insurance evt,copula,bayesian extreme losses + dependence + capital scenarios
Energy / utilities timeseries,evt,hmm demand forecast + peak extremes + load regimes
Telecom timeseries,randomforest,bayesian,correlation,hmm traffic forecast + churn drivers + anomaly + KPI links + usage regimes
Agriculture timeseries,randomforest,evt,popgen,correlation yield forecast + driver attribution + drought/flood + breeding genetics
Water / hydrology evt,timeseries,hmm,correlation flood/drought return levels + flow forecast + wet/dry regimes
Climate / environment timeseries,evt,hmm,correlation trend + extremes + regimes + scenarios
Healthcare / genomics popgen,variants,bayesian,randomforest population structure + variant summary + inference + classification
Manufacturing / quality evt,randomforest,correlation process variation + defect extremes + driver analysis
Retail / e-commerce timeseries,randomforest,bayesian demand seasonality + drivers + change-point + scenarios
Public sector / economics cointegration,timeseries,correlation,evt long-run equilibria + forecasts + shocks
Mining / commodities timeseries,evt,copula,cointegration price dynamics + spikes + co-movement + spreads
Research / academia* all the full cross-sector mix

* We are actively working on Djehuti 2 Academic version, with more capabilities and enhanced formulas for each module — especially the genomics module. Stay up to date!

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 GCC 15), Debian 11+, any modern distro
    Windows: Windows 10/11 (64-bit)

Linux compatibility

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.

Quick start

terminal
# Linux — run the AppImage
$ ./Djehuti-10M-x86_64.AppImage data.npy

# Windows — run the .exe
C:\> djehuti2-10M.exe data.npy

# Pick modules
$ ./Djehuti-10M data.npy --modules heston,evt,copula

# See all options
$ ./Djehuti-10M --help

Get the engine.

Limited licensing offer to the first 50 buyers only.
Free updates for 1-year & Free upgrade to the 50M SIMS build when out. Then price will change.

Lifetime license / no subscription / no cloud.

$299 $499

Launch offer — $200 off

Refund Policy - 14-day money back guarantee

To get your refund:

  1. Contact us within 14 days of purchase
  2. Include your Gumroad order number
  3. Describe the issue (error messages, system specs, logs, etc.)

We will first try to resolve your issue within 48-72 hours. If we can't, we will process the refund.

Not eligible for refund:

  • "I changed my mind" or "I don't need it anymore"
  • Performance expectations (benchmarks shown are from our test system; actual performance depends on your hardware)
  • Requests after 14 days
  • Attempts to reverse-engineer the build, crack, or bypass the sim cap
  • Issues caused by user's system configuration (we provide support to help resolve these)
  • Issues related to incompatibility despite the fact we have already written a detailed system requirement section