omi
AI that sees your screen, listens to your conversations and tells you what to do
- 14k
- Python
- MIT
- 3 h ago
AI that sees your screen, listens to your conversations and tells you what to do
An open source AI wearable device that captures what you say and hear in the real world and then transcribes and stores it on your own server. You can then chat with Adeus using the app, and it will have all the right context about what you want to talk about - a truly personalized, personal AI.
Remote control for Claude Code, Codex, Grok, and Cursor on Mac or PC. View sessions, send tasks, and drive them remotely from your phone. OpenClaw supported.
Mirror your body in data. One standard, every source, one complete picture of you: a self-hosted health record built from lab reports, wearables and genetics, with every number traced to its source and a built-in MCP server. Run it with Docker and one LLM key, or keep every model local on llama.cpp.
App which allows you to use your health devices beyond subscriptions. Supports Workout Tracking, Nutrition Tracking, Wellness Excercise, Sleep, Recovery, Strain, and Many more.
Open-source AI navigation glasses under $35 — they say what they see, and say 'uncertain' instead of guessing. Safety-first, printable enclosure, community build kit.
This application is developed to display the images created by MidJourney. The application is developed with Compose Multiplatform and works on many platforms including Android and iOS platforms.
MCP server for querying Apple Health data with natural language using DuckDB under the hood.
Read-only WHOOP MCP server for recovery, sleep, HRV, strain, workouts, and personal health analytics in Claude, Codex, and GitHub Copilot.
Official Code for ACM SIGGRAPH 2024 paper "Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging"
DIY touch interface built with conductive materials such as conductive paint
Open, minimal sEMG wristband like the Meta Neural Band: 8-ch ADS1298 + nRF52832 BLE, dry gold electrodes on a flex, 3D-printed band. KiCad, FreeCAD, Zephyr, Python, simulations.
Pure Dart wearable protocol decoder — WHOOP 4.0/5/MG, generic Bluetooth HR straps, and the Oura ring. Bytes off the device in, named records out. Zero deps, runs on-device.
Platform agnostic Rust driver for the MAX3010x high-sensitivity pulse oximeter and heart-rate sensor for wearable health
Tasrif is a python library for processing of wearable data from fitness trackers and wearable health devices
Recovery, strain, sleep and more — computed from a WHOOP band's raw sensor stream using published, cited methods only. Pure Dart, deterministic, nothing invented.
FaleraOS (formerly OreoOS) by Elixpo: open-source MicroPython OS and hardware for the ESP32-S3 Falera Badge, with apps, an App Store, OTA updates, KiCad hardware and RV565 video.
Arduino sketches for the STM32WB-based Katydid (aka Connected Motion Sense) wearable IoT platform
This is a sample project that supports a Wear OS app and utilizes the BLoC architecture pattern, Dio for network management, and Drift for database handling.
WHOOP 4.0 BLE protocol reference + a single-file reference client. Give a post-subscription strap a second life.
Optional companion worker for OpenStrap — legacy import, an update pointer, and opt-in telemetry. The app computes everything on-device and does not need this.
Code Rain Ring: a metal 3D-printed ring with a Matrix code-rain OLED display
The project is a test implementation of Jetpack Compose for a Wear OS app that includes API requests (dynamic list), Hilt for dependency injection, and Room Database.
Digital twin of an nRF54L15 smart ring, cycle-accurate firmware simulation with register-level sensor models and an honest BLE-contention demonstration
Wear OS Tiles made simple: ProtoLayout builders for progress, stats and shortcuts, fresh data updates and previews.
Personal health dashboard on Cloudflare Workers + D1, fed daily from the Google Health API (Samsung Health, Polar Flow and scales via Health Connect, plus Fitbit history)
Wear OS Compose components: curved text, rotary-scroll lists, progress rings, swipe-to-dismiss pages and a stopwatch sample for round screens.
A companion app for a speculative wearable biosensor designed to detect the migraine prodrome window before an attack begins.