v0.2.3 beta Apache 2.0

Visual data science,
block by block.

Build, iterate, and share reproducible pipelines without the boilerplate.

LOAD CSV path = "data.csv" delimiter = "," CLEAN DATA drop_na = True normalize = True KMEANS n_clusters = 5 standardize = True SELECT COLUMNS columns = ["a","b","c"]
Inspector
Output

Why Forge

For newcomers

See your pipeline, not just your code

Visual blocks make data science approachable. Drag, connect, run.

For experienced DSs

Edit a parameter. Run only what changed.

Targeted re-execution — not full notebook reruns. Iterate in seconds, not minutes.

For AI-assisted workflows

Let AI agents do data science through Forge's MCP

Claude Code, Codex, and other AI agents can build, run, and interpret pipelines programmatically.

Three steps to your first pipeline.

01

Drag blocks onto the canvas

Pick from 70+ built-in blocks or write your own Python. Each block is a self-contained step.

Load CSV
Filter Rows
02

Connect them into a pipeline

Draw edges between blocks to define data flow. Forge handles dependencies automatically.

LOAD CSV ZSCORE UMAP KMEANS
03

Run & iterate

Change a parameter, hit "Run Stale" — only downstream blocks re-execute. No more full reruns.

Stale
Running
Complete

From quick experiments to production pipelines.

Data cleaning & transformation

Wrangle messy CSVs into structured datasets with reusable blocks.

ML model training & evaluation

Train, tune, and compare models with visible data flow at every step.

Exploratory data analysis

Prototype fast. See intermediate results without re-running everything.

Reproducible research workflows

Save and share pipelines as JSON. Same inputs, same outputs, every time.

Custom Python blocks

Extend Forge with your own code. Full Python - no sandbox, no limits.

Visualization & plotting

Scatter plots, heatmaps, bar charts, histograms - 11 built-in plot types, plus 3D.

Free & open source.

Forge is free and open source under the Apache 2.0 license. Built by a data scientist, for data scientists.

Premium features (team collaboration, cloud execution) coming soon.

System requirements
Windows 10+ · macOS 11+ (Big Sur) · Python 3.12+ · ~100 MB disk space