# Omi

AI that sees your screen, listens to your conversations and tells you what to do

Repository: https://github.com/BasedHardware/omi
Canonical: https://ross.abutalabs.com/products/omi
Homepage: https://omi.me
Language: Python
License: MIT
License Family: permissive
Topics: ai, app, flutter, friend, mobile, necklace, omi, python, summary, transcription, wearable, bci, c, nextjs, personas, smartglasses
Last push: 2026-08-27T00:02:41+00:00
Link (homepage): https://omi.me

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 63
- inputs: {"age_days": 894, "days_push": 7, "days_rel": 6, "gap_med": 0, "n_releases_24m": 946}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13264, forks 2205 (observed 2026-08-28T04:11:02.887099+00:00)

## What it is
Omi is an open-source AI wearable and companion app ecosystem (necklace pendant, smart glasses, desktop and mobile apps) that captures conversations and screen activity, transcribes them in real time, and generates summaries, action items, and an AI chat with full memory. It spans a Flutter mobile app, desktop apps, a Python backend, and companion hardware projects.

## Use cases
- transcribe my conversations in real time with a wearable
- summarize meetings and extract action items automatically
- an AI assistant that remembers everything I've seen and heard
- build my own AI wearable pendant or smart glasses
- capture and search everything said during my workday
- personal memory assistant that listens all day
- self-hosted alternative to AI wearables like Friend

## When to choose
- you want an open-source, privacy-conscious AI wearable with your own data
- you need real-time transcription plus summaries and follow-up tasks across devices
- you want to hack on or extend wearable hardware and its companion software
- you want a memory-augmented AI chat across desktop, mobile, and wearables

## When to avoid
- you need a small, lightweight library to embed in your own product
- you are uncomfortable with always-on audio capture or its privacy implications
- you need a fully offline solution with no cloud backend dependency
- you only need simple speech-to-text without memory or agent features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, chatbot, rag, machine-learning, audio-processing
- domain: artificial-intelligence, developer-tools, mobile-development, hardware, cross-platform
- platform: windows, cross-platform, python
- tags: wearable, wearable-ai, transcription, quantified-self, smartglasses, pendant, second-brain, memory-assistant, flutter-app, open-source-hardware, ai-agents, natural-language-processing, macos, android, ios, mobile, desktop, flutter

## Member repositories
- BasedHardware/omi (main) score 88
- BasedHardware/OpenGlass (mirror) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:02.887099+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:24.129130+00:00, confidence not recorded.
  - readme: https://github.com/BasedHardware/omi (fetched 2026-08-28T04:11:02.887099+00:00, sha 3cfd337e95db)
  - homepage: https://omi.me (fetched 2026-08-29T08:08:31.988004+00:00, sha d31544754817)
- Data as of 2026-08-30T08:39:29.467469+00:00.