Desktop statistical analysis
ChakataStat is a desktop app for serious data analysis — a fast, spreadsheet-style editor backed by a native Rust engine, with a broad Analyze program, an in-app AI assistant, and full reproducibility built in.
Windows · Linux · Free to use
Numbers you can defend
A statistics package is only worth as much as its numbers. Every release is checked, end to end through the real engine, against values computed independently by established reference packages — and against certified values published by a national metrology institute.
191
statistics pinned to independently computed reference values, across 47 procedure families — each with its own recorded tolerance.
45
NIST Statistical Reference Datasets run end to end and scored by digits of agreement against their certified values.
1,575
automated tests across the engine and the application, run green on Windows, macOS and Linux before a release ships.
Reference values are computed with SciPy, statsmodels, scikit-learn, lifelines and pingouin, and stored with the tolerance and provenance of each one. Where a statistic has more than one valid definition — a quantile method, a continuity correction, a contrast type — the engine's convention is documented rather than hidden behind a loose tolerance.
One application, five ways to reach the same catalog: the GUI, an editable syntax console, the AI assistant, an MCP server for external agents, and a headless batch runner.
Descriptives, regression, GLM and mixed models, survival and time series, multivariate methods, confirmatory factor analysis, meta-analysis and Bayesian tests — 95 analysis tools in one catalog, each reporting the conventional effect sizes beside the test they describe.
A fast, Excel-like sheet with a Variable View for metadata, value labels, missing-value handling, and self-documenting column tooltips.
Histograms, scatterplots, boxplots, line, bar, error-bar and Q-Q charts in a unified Chart Builder — plus scree plots, dendrograms, forest and funnel plots beside their analyses.
A provider-neutral agent — Claude, or any OpenAI-compatible backend, including a local Ollama that never leaves your machine — that runs real analyses on your open dataset in plain language, and renders the resulting tables and charts inline in the reply.
Every action emits an editable, re-runnable command. Export to HTML, Markdown, LaTeX or a Python script.
A native Rust engine — an in-house columnar store with Parquet I/O over Apache Arrow — does the heavy lifting on a worker thread, so the interface never freezes on a long fit.
One command stream
The menus, the syntax console, the AI assistant, the MCP server and the headless batch runner are not five integrations — they are five front doors onto one command layer. Whichever you use, the same engine runs the same call, so a result you got by clicking is a result you can re-run in a script.
// Recorded automatically as you click, and editable in place.
descriptives variables=[Age, BMI, SystolicBP]
independent_ttest variables=[SystolicBP], grouping=Hypertensive// Plain language. The reply carries the real tables and charts.
Compare systolic blood pressure between the hypertensive
and non-hypertensive groups, and show me the effect size.# The dataset stays in the native engine; nothing runs in Python.
import ChakataStat as ig
with ig.open("health_study.ckd") as ds:
print(ds.descriptives(variables=["Age", "BMI", "SystolicBP"]))
ds.independent_ttest(variables=["SystolicBP"], grouping="Hypertensive")
df = ds.to_polars() # one hop to the wider ecosystem# No window. CI-friendly exit code, report written to disk.
ChakataStat --run analysis.cks health_study.csv --out report.html
# Or serve the same tools to an external agent over MCP:
ChakataStat --mcp health_study.csvA real dataset, in the real application — not a mock-up. Pick a view; click the shot to enlarge it.
95
analysis tools, one catalog
Descriptive Statistics, Compare Means and Correlate; Regression (linear, logistic, Poisson, regularized, robust, nonlinear, instrumental variables, mediation); General Linear Model, Linear Mixed Models and GLMM; Factor / PCA and confirmatory factor analysis, Cluster and Discriminant analysis; Survival (Kaplan-Meier, Cox, parametric); Time Series (ARIMA, seasonal decomposition); Meta-Analysis (fixed effects, DerSimonian-Laird or REML random effects, with forest and funnel plots); Bayesian tests; and Nonparametric methods — with the conventional effect sizes reported by default beside the tests they describe.
Available for Windows and Linux — macOS is coming soon.
Store installs are signed and update automatically. On Linux you can also grab the Debian/Ubuntu .deb from the releases page; Windows is Microsoft Store-only.