allenv0/AirPosture

AirPosture: AirPods as posture coach

What it solves

AirPosture addresses the problem of poor posture and neck strain during the day by providing real-time feedback to users, encouraging them to sit better and move more.

How it works

The app utilizes the spatial audio and dynamic head tracking capabilities of compatible AirPods and Beats earphones to monitor head position. It leverages Apple's MLX framework to run private, low-latency AI models locally on iOS to analyze movement and provide gentle nudges to the user.

Who it’s for

People who wear AirPods or compatible Beats earphones and want to improve their posture and build healthier sitting habits.

Highlights

  • Real-time posture coaching using head tracking sensors.
  • Local AI processing via MLX for privacy and low latency.
  • Support for AirPods Pro, AirPods (3rd gen+), AirPods Max, and compatible Beats earphones.
  • Open-source codebase to ensure transparency and accessibility.

Related

  • Project
    quickpose/quickpose-ios-sdk

    An iOS SDK for real-time pose estimation and skeleton tracking, providing pre-built tools for exercise counting and range-of-motion analysis.

  • Project
    LYiHub/pub-local-jarvis

    A local multimodal desktop assistant for Windows that perceives screen and system audio to provide real-time gaming companionship, course notes, and contextual AI interaction.

  • Project
    krumjahn/applehealth

    A terminal AI assistant that turns Apple Health export data into a conversational analysis tool, supporting both local and cloud LLMs for private health metric tracking.

  • Project
    yo-WASSUP/Good-GYM

    An AI fitness assistant that uses RTMPose for real-time pose detection and automatic exercise repetition counting via a webcam.

  • Project
    FutureUniant/WorkShadow

    A local-first desktop work log application that uses AI for semantic search, automated report generation, and Q&A over personal work history while keeping data on the user's machine.