All Projects

ClickML.

A drag-and-drop canvas for building ML pipelines without code — rebuilt from a single-file Streamlit app into a multi-service SaaS.

Machine & Deep LearningActive — Studio rebuild5,000+Next.js 16 + XYFlowFastAPI14 algorithmsSupabase · MongoDB · Redis
19
GitHub stars
GitHub
23
Forks
GitHub
14 models + 12 steps
Canvas components
4
Services
5,000+
Users
3
Pricing tiers

Overview

History

From a single Streamlit file to a real platform

ClickML shipped in 2023 as one Streamlit script — upload data, pick a model, train, download. That version is still live and is what the public GitHub repo and streamlit.app link reflect today.

The current build is a ground-up rebuild: a proper canvas-based pipeline editor backed by a dedicated execution engine, not a script running top to bottom in a single session.

Canvas

Fourteen models, wired up as draggable nodes

Pipelines are built visually — data readers, processing steps, feature engineering, and models all connect on a canvas instead of being written as code.

Data
CSV Reader, Excel Reader
Processing
Cleaning, missing values, scaling, encoding, split
Feature engineering
Extraction, transformation, selection
Wrangling
Merge/Join, Concatenate
Classification
Random Forest, Logistic Regression, SVC, Decision Tree, Gradient Boosting, KNN
Regression
Random Forest, Linear, Ridge, Lasso, SVR, Decision Tree, Gradient Boosting, KNN
Evaluation
Model selector, inference, accuracy/F1 or MAE/RMSE/R²
Backend

One component map, one execution engine

A PipelineEngine dispatches each canvas node to its implementation through a single COMPONENT_MAP, so adding a new node type is a matter of registering a new component class rather than touching the execution path. Auth is Supabase JWT, forwarded per-request so Postgres row-level security enforces access without a separate authorization layer.

How it works

Four services split the concerns: a canvas frontend for building pipelines, a FastAPI engine for running them, a marketing site, and a docs site — orchestrated together via Docker Compose.

Canvas
drag-and-drop nodes, Next.js + XYFlow
Pipeline engine
FastAPI, component-map dispatch
Run
Supabase + MongoDB + Redis

Built with

Next.js 16
canvas studio frontend, App Router
XYFlow
drag-and-drop pipeline canvas engine
FastAPI
pipeline execution engine, Python 3.11
Supabase
Postgres + RLS, auth
MongoDB
transient pipeline state + logs
Redis
caching layer
scikit-learn
14 wrapped classification/regression models