basedhardware/omi

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

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 14 minutes ago
Added to GitGenius on September 4th, 2026
Created on March 22nd, 2024
Open Issues & Pull Requests: 626 (-1)
GitHub issues: Enabled
Number of forks: 2,246
Total Stargazers: 13,429 (+0)
Total Subscribers: 90 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 16.7 hours
Mean response time: 21.8 days
90th percentile: 77.7 days
Tracked items: 2,576

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 49% of open issues come from outside the core team, a mix of external reports and the maintainers' own roadmap. Work labelled "desktop" is answered fastest, typically in about 11 hours, while "p3" waits about 8 days. 59% of tracked open issues have had no activity in three months. Only 7% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 424
New in 7 days: 51
Closed in 7 days: 34
Avg open age: 153 days
Stale 30+ days: 318
Stale 90+ days: 228

Recent activity

Opened in 7 days: 49
Closed in 7 days: 34
Comments in 7 days: 24
Events in 7 days: 140

Top labels

  • bug (604)
  • p3 (472)
  • p2 (456)
  • maintainer (298)
  • backend (235)
  • enhancement (224)
  • p1 (193)
  • desktop (184)

Detailed Description

Omi is a wearable AI assistant that captures your screen and conversations, transcribes them in real-time, and provides summaries and action items through an AI chat interface that retains context across all captured interactions.

The tool addresses the problem of information overload by automatically recording and processing what you see and hear, then making that knowledge accessible through conversational AI. It transcribes audio in real-time, generates summaries and actionable items from captured content, and maintains a persistent memory of everything you have interacted with. The system works across multiple form factors including desktop applications, mobile apps, and wearable devices, with a backend API handling processing and storage while device-specific frontends provide the user interface.

Omi suits professionals who need to retain and quickly reference information from meetings, screen work, and conversations without manual note-taking. The project offers native applications for macOS and Windows desktops, iOS and Android mobile apps, and custom firmware for wearable hardware including smart glasses. Development setup is straightforward on macOS with no environment configuration required for basic use, while Windows and full-stack local development require more involved setup. The tool is fully open source, allowing self-hosting of the backend stack if desired.

The project maintains active development across multiple platforms and languages, with distinct codebases for macOS (Swift and SwiftUI), mobile (Flutter), backend services (Python and FastAPI), wearable firmware (C with nRF and Zephyr), and web interfaces (Next.js). The repository includes comprehensive documentation covering quick starts, platform-specific development guides, and contribution guidelines, indicating ongoing investment in developer experience. The codebase spans hardware firmware, mobile and desktop applications, cloud backend infrastructure, and AI persona systems, reflecting a complex multi-platform architecture under continuous development.