What is it exactly ? A self-contained engine that reads data file, runs a cross-sector analysis mix (Monte Carlo, quant, time series, genomics, and more), and prints a human readable log plus a machine readable JSON block. It maps your file read-only (no copy, no decompress needed) and writes nothing to disk. There is no install and no source: you just run one binary.All modules have been verified against their native public libraries on real data only (full engine verification link to our website below).Built for what you already have. Djehuti runs on an 8GB RAM, 10-year-old Ryzen and still delivers 213M simulations per second, that's a personal supercomputer n a single binary. Offline, read-only, zero disk writes.213 million sims/sec on my 10-year-old Ryzen 1600X 6 cores 12 threads. 1.4 million correlations per second on 177×177 real data*. No cloud, no cluster, no monthly bill. The more cores you have, the faster it runs. (full engine verification link to our website below)*Speed here was with a custom compilation with optimization flags, the users build does not comes with specific flags except OpenMP, SIMD and AVX2 acceleration + cache lock which are part of the build.Linux & Windows build availableboth capped to 10M SIMS.Early buyers will enjoy 1-year of free updates and free upgrade to the 50M SIMS build.Higher SIMS cap : 50/100/500M and unlimited SIMS coming soon Engine verification link to our website : Click here 1) Modules list :How to read the module list ?| 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 2) Formats handledLinux .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 3) Preparing your dataConvert CSV / Excel to clean .npyThe 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) 4) Cross-sector recipes :The engine's strength is the mix: it runs several models on the same file at once, outputcombinations the free single-purpose libraries do not produce by default. Pick the modules thatmatch the question. The Monte Carlo core is added automatically, so you do not name it.How to read the module recipes example ?| 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, that will have more capabilities and enhanced formulas for each modules especially the genomics module. Stay up to date !5) System requirements :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 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.