Get Started
Introduction
Run AI functions on-device
Function helps you run stateless Python functions (a.k.a “predictors”) on-device. Features include:
- Cross platform: Function supports running on-device across Android, iOS, macOS, Linux, Windows, and the browser.
- Zero dependencies: Function compiles these prediction functions into self-contained binaries, meaning you can make predictions with zero dependencies.
- Hardware acceleration: Function is designed to use all available compute acceleration hardware (e.g. GPU, NPU) and instruction sets (e.g. CoreML, DirectML, CUDA).
Installing Function
We provide SDKs for common development environments:
We are working on providing a Swift client for running AI functions on-device on iOS.
Most of our client SDKs are open-source. Star them on GitHub!
Creating an Access Key
Head over to Function to create an account by logging in. Once you do, generate an access key:
Making your First Prediction
Let’s run the @fxn/greeting
predictor which accepts a name
and returns a
friendly greeting:
You should see a friendly greeting. Congrats on your first prediction 🎉
Join our waitlist to bring your custom Python functions and run them on-device.