Welcome to Scailable.

We provide instant, production-ready, deployment of AI & ML models (using WebAssembly).

What is Scailable?

With Scailable, we provide automatic, single-line-of-code conversion (or transpiling really) of AI and ML models to WebAssembly; "a safe, portable, low-level code format designed for efficient execution and compact representation.". This allows you to deploy your AI and ML models directly from your python or [R] workspace and run them anywhere.

We enable you to generate extremely fast inferences on our cloud, on yours, or even on the edge. We provide extremely low latency, production-ready, inferences from most common machine learning models. We currently support sklearn, statsmodels, xgboost, tensorflow, and BART models.

The easiest way of getting started is by following our getting-started tutorial: Scailable 101: Getting started.

Scailable BETA: We are learning.

Scailable is currently in beta. Not every "beta" is the same, so we would like to make clear what we mean by beta. For us, "beta" means that real users (you) work with our software and identify issues that we were unable to find on our own. And, then, we do something about the issues you find. We fix them. We learn how to make our product better. Thanks to you.

Want to join? Sing up for an account at https://admin.sclbl.net 🤖.

Explore our functionality and performance.

Often, actions speak louder than words. So, we put up a number of demo's to showcase what Scailable can do for you.

  1. Predicting a developers salary. Based on the most recent Stack Overflow survey, we created a simple model to predict the yearly salary of developers; give it a spin! This simple front-end supports our getting started tutorial: Scailable 101: Getting started.
  2. Scailable supports running complex models (such at Bayesian Additive Regression Trees) in the cloud, on the edge, or on a browser. Check how we can flexibly generate posterior predictives for automatic property valuation models, anytime, anywhere.
  3. Sometimes what you need is performance. We provide nothing less. The inferences from our models are extremely fast; check out some of our benchmarks.

Contact us

If you want us to help you generate extremely low latency inferences let us know! Please, fill out the form below, or give us a call at (+31) 0619196802.

Created in the Netherlands with ♥. For questions, contact us at go [at] scailable [dot] net.