Install sleepKIT and run a first workflow.
Start here →
sleepKITv0.11.1From sleep signals
to Edge AI.
sleepKIT is a Python development kit for building sleep-monitoring AI for Ambiq devices. Turn sensor recordings into features, train and evaluate models, and prepare them for deployment at the edge.
One configurable workflow
- 01Prepare signalsDataset loaders and feature extraction
- 02Build modelsConfigurable architectures and training
- 03Evaluate resultsTask metrics and saved experiments
- 04Prepare for the edgeModel export and task-level demos
What is sleepKIT?
Section titled “What is sleepKIT?”Building a sleep-monitoring model involves recordings and labels, signal processing, a training setup and a way to assess the result. sleepKIT brings those pieces into a configurable Python workflow for wearable and edge applications.
Start with an included task, run it from the command line or adapt the workflow through the Python API. The task and guide pages explain the options in detail, including how to prepare a model for integration on Ambiq devices.
Included tasks
Section titled “Included tasks”Start with a built-in task, or extend the workflow with your own training, evaluation and export routines.
Sleep detectionIdentify sleep and wake periods from wrist-worn motion signals.Explore detection →Sleep stagingExplore feature sets and models for classifying sleep stages.Explore staging →Sleep apneaExplore the task and available resources for apnea event detection.Explore apnea →Bring your own taskRegister a custom task and reuse sleepKIT’s configuration and development workflow.Create a task →
Installation
Section titled “Installation”In a Python 3.12 project, add sleepKIT and check that the command line tool is available:
uv init --python 3.12 my-sleep-projectcd my-sleep-projectuv add sleepkituv run sleepkit --helpThe quickstart covers pip and source-checkout installation, configuration and your first workflow.
Code and Ambiq-authored documentation use BSD-3-Clause, except separately licensed material. Model weights and datasets have their own terms.