Suits people who want an always-on AI memory and developers who want to hack on it; building from source needs Xcode and Node.js on macOS, or Node.js on Windows.

What can you build with omi?

Run a searchable record of your meetings and conversations with automatic summaries and action items. Ask an AI chat what you discussed or saw on your screen last week. Build a custom Omi app that reacts to live audio streams, such as a Slack or GitHub integration. Assemble and flash your own open-source wearable or camera glasses using the published firmware and designs. Connect your captured memories to other AI tools through the MCP server or the REST API.

BasedHardware /

omi

Open-source app and wearable that records your screen and talks, then summarizes them

13.8k stars
178 stars since 3 Oct
Python
Updated today
Some experience
Productivity & personal

Open on GitHub (opens in a new tab) Website (opens in a new tab)

Omi is a personal memory tool. It listens to your conversations and watches your screen, turns the audio into text, and writes summaries and to-do items from what it captured. You can also chat with an AI that draws on everything you have seen and heard.

The repo is a full stack, not a single app. A Python backend (FastAPI, Firebase, Redis, Deepgram for speech-to-text, and LLMs) does the processing. Clients feed it audio: a Swift macOS app, a Windows app, a Flutter mobile app, and open hardware (an nRF-based wearable and an ESP32-S3 camera glasses kit) that connects over Bluetooth.

The README does not compare Omi to named alternatives. What stands out is that the clients, backend, firmware and hardware designs live in one open repo, along with an app system and SDKs for extending it.

What it does

Screen and conversation capture
Records what is on your screen and what is said around you, then transcribes it in real time.
Summaries and action items
Generates summaries and to-do items from conversations, and offers an AI chat that remembers what it captured.
Many clients
A macOS app in Swift, a Windows app, a Flutter app for iOS and Android, and a browser version at app.omi.me.
Open hardware
Firmware and designs for a wearable and for Omi Glass (ESP32-S3 with camera and audio). The README says the wearable pairs with the phone app for 24h+ continuous capture.
Apps, API and SDKs
A REST API for memories, conversations and action items, device SDKs for Python, Swift and React Native, an MCP server, and docs for building custom apps and chat tools.

What you could build

Run a searchable record of your meetings and conversations with automatic summaries and action items.
Ask an AI chat what you discussed or saw on your screen last week.
Build a custom Omi app that reacts to live audio streams, such as a Slack or GitHub integration.
Assemble and flash your own open-source wearable or camera glasses using the published firmware and designs.
Connect your captured memories to other AI tools through the MCP server or the REST API.

Get started

On macOS 14+ with Xcode and Node.js installed, run the command to build the app, which connects to the cloud backend with no credentials needed. On Windows, the README has separate steps using npm install and npm run dev, and you can also try it in the browser or download the apps.

git clone https://github.com/BasedHardware/omi.git && cd omi/desktop/macos && ./run.sh --yolo

Commands are copied from the project's README. Read it on GitHub for the full setup.