omi
AI that sees your screen, listens to your conversations and tells you what to do
What is omi?
AI that sees your screen, listens to your conversations and tells you what to do
Overview of omi
What it is
Omi is an open-source AI wearable platform described as a '2nd brain'. It captures your screen and conversations, transcribes in real-time, generates summaries and action items, and provides an AI chat that remembers everything you've seen and heard. It works on desktop, phone, and wearables. The platform includes a necklace wearable, mobile apps, desktop apps, backend, firmware, and hardware designs, all open source under MIT license. The hosted Omi Cloud service and paid plans are described at omi.me.
Key features
- Captures screen and conversations - Real-time transcription - Generates summaries and action items - AI chat with memory of all captured content - Works on desktop, phone, and wearables - Open-source (MIT) with hardware designs included
Use cases
- Capturing and transcribing meetings and conversations - Generating summaries and action items from discussions - Using AI chat to recall past information from screen and audio - Personal memory augmentation and productivity
Getting started
macOS: sh git clone https://github.com/BasedHardware/omi.git && cd omi/desktop/macos && ./run.sh --yolo Requirements: macOS 14+, Xcode, Node.js Windows: powershell git clone https://github.com/BasedHardware/omi.git cd omi/desktop/windows npm install copy .env.example .env npm run dev Requirements: Node.js Mobile app: bash cd app && bash setup.sh ios # or: bash setup.sh android For full local development with backend, see the repository README.
License and pricing
License: MIT. The project is open source. Hosted Omi Cloud service and paid plans are available at omi.me (not part of the open-source repository).
Based on the project's public README and repository metadata.