omi

AI wearables. Put it on, speak, transcribe, automatically

22 articles 7.7k View on GitHub ↗
22 articles
How Omi's Foreground Task System Enables Background Recording on Mobile

Discover how Omi's foreground task system enables reliable background audio recording on mobile by preventing OS termination and fetching location data.

internals
Feb 26, 2026
How Omi's Calendar Meeting Integration Syncs and Parses Meetings

Discover how Omi's calendar meeting integration syncs Google Calendar events using LangChain. Learn how it fetches, normalizes, and performs operations on your meetings.

how-to-guide
Feb 26, 2026
How Omi Processes Conversation Transcripts with Whisper and Other STT Engines

Discover how Omi processes conversation transcripts using Whisper and other STT engines. Learn about its fallback and normalization pipeline.

deep-dive
Feb 26, 2026
How the Timeout Middleware Handles Long-Running API Requests in Omi

Learn how Omi's Timeout Middleware guards your API against slow requests. It rejects stale connections with 408 and terminates long operations with 504 errors.

internals
Feb 26, 2026
How the OAuth Flow Works for Third-Party Integrations in Omi

Learn how Omi's OAuth 2.0 flow empowers third-party integrations. Discover secure API access with automatic refresh mechanisms and Redis state tokens.

how-to-guide
Feb 26, 2026
Structure of the Plugin System for Omi Apps: FastAPI Architecture Explained

Discover the modular FastAPI plugin system structure for Omi Apps. Learn how third-party integrations register routers and deploy via Modal for seamless frontend discovery.

architecture
Feb 26, 2026
How Omi Handles Voice Activity Detection in Real-Time Transcription Processing

Discover how Omi's real-time transcription processing uses cloud STT providers for voice activity detection, optimizing live audio streams.

deep-dive
Feb 26, 2026
How the LangSmith Observability Integration Works in Omi: Runtime Tracing and Prompt Management

Explore the LangSmith observability integration in Omi, featuring runtime tracing, prompt management, and user feedback. Learn how Omi streamlines LLM application development.

deep-dive
Feb 26, 2026
How Conversation Merging and Deduplication Works in Omi: A Technical Deep Dive

Learn how Omi merges conversations by validating data, combining transcripts, deduplicating photos, and replacing source documents. Discover the technical details of this feature.

deep-dive
Feb 26, 2026
Required Environment Variables for the Omi Backend: Complete Configuration Guide

Configure the Omi backend by understanding over 40 required environment variables. This guide details necessary Stripe API keys and speech-to-text credentials for runtime configuration.

how-to-guide
Feb 26, 2026
How Speech Profile Creation and Recognition Works in Omi: A Complete Technical Guide

Learn how Omi creates speech profiles using voice samples and Soniox models for accurate speaker identification and transcription. Understand the technical process for efficient voice recognition.

deep-dive
Feb 26, 2026
How Omi Tool Integrations Work: A Deep Dive into Gmail, Calendar, and Google Contacts

Discover how Omi tool integrations leverage OAuth 2.0 and LangChain to connect Gmail, Calendar, and Google Contacts for AI-powered chat functions. Explore the underlying technology.

deep-dive
Feb 26, 2026

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:
curl -s "https://instagit.com/install.md"

Works with
Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →