# Docs

## Docs

- [Create action item](https://docs.omi.me/api-reference/action-items/create-action-item.md): Create a new action item (task/to-do). Push notifications are sent to the Omi app if a `due_at` date is provided.
- [Create action items (batch)](https://docs.omi.me/api-reference/action-items/create-action-items-batch.md): Create multiple action items in a single request. Maximum 50 per batch.
- [Delete action item](https://docs.omi.me/api-reference/action-items/delete-action-item.md): Permanently delete an action item. This action cannot be undone.
- [List action items](https://docs.omi.me/api-reference/action-items/list-action-items.md): Retrieve your action items (tasks/to-dos) with optional filtering.
- [Update action item](https://docs.omi.me/api-reference/action-items/update-action-item.md): Update an action item's description, completion status, or due date. Setting `completed: true` automatically sets `completed_at`.
- [Create API key](https://docs.omi.me/api-reference/api-keys/create-api-key.md): Create a new developer API key. The full key is only returned once — store it securely immediately.
- [List API keys](https://docs.omi.me/api-reference/api-keys/list-api-keys.md): Retrieve all your developer API keys. Secret key values are not returned — only the prefix is shown.
- [Revoke API key](https://docs.omi.me/api-reference/api-keys/revoke-api-key.md): Permanently revoke (delete) a specific API key. Any requests using this key will immediately stop working.
- [Create conversation from text](https://docs.omi.me/api-reference/conversations/create-conversation-from-text.md): Create a new conversation from text content. The text is processed through the full AI pipeline: discard detection, structured generation, action item extraction, memory extraction, app integration, and webhooks.
- [Create conversation from transcript segments](https://docs.omi.me/api-reference/conversations/create-conversation-from-transcript-segments.md): Create a conversation from structured transcript segments with speaker diarization. Unlike text-based conversations, transcript segments are stored and can be retrieved with `include_transcript=true`.
- [Delete conversation](https://docs.omi.me/api-reference/conversations/delete-conversation.md): Permanently delete a conversation and its associated data. This action cannot be undone. Consider using PATCH with `discarded: true` to hide instead.
- [Get conversation](https://docs.omi.me/api-reference/conversations/get-conversation.md): Retrieve a single conversation by ID, optionally including transcript segments.
- [List conversations](https://docs.omi.me/api-reference/conversations/list-conversations.md): Retrieve your conversation transcripts. Only returns completed, non-discarded conversations.
- [Update conversation](https://docs.omi.me/api-reference/conversations/update-conversation.md): Update a conversation's title or discard status. At least one field must be provided.
- [Create Action Item](https://docs.omi.me/api-reference/endpoint/action-items/create.md): Create a new action item (task/to-do). Push notifications are sent to the Omi app if a `due_at` date is provided.
- [Create Action Items (Batch)](https://docs.omi.me/api-reference/endpoint/action-items/create-batch.md): Create multiple action items in a single request. Maximum 50 per batch.
- [Delete Action Item](https://docs.omi.me/api-reference/endpoint/action-items/delete.md): Permanently delete an action item. This action cannot be undone.
- [List Action Items](https://docs.omi.me/api-reference/endpoint/action-items/list.md): Retrieve your action items (tasks/to-dos) with optional filtering.
- [Update Action Item](https://docs.omi.me/api-reference/endpoint/action-items/update.md): Update an action item's description, completion status, or due date. Setting `completed: true` automatically sets `completed_at`.
- [Create Conversation](https://docs.omi.me/api-reference/endpoint/conversations/create.md): Create a new conversation from text content. The text is processed through the full AI pipeline: discard detection, structured generation, action item extraction, memory extraction, app integration, and webhooks.
- [Create from Transcript Segments](https://docs.omi.me/api-reference/endpoint/conversations/create-from-segments.md): Create a conversation from structured transcript segments with speaker diarization. Unlike text-based conversations, transcript segments are stored and can be retrieved with `include_transcript=true`.
- [Delete Conversation](https://docs.omi.me/api-reference/endpoint/conversations/delete.md): Permanently delete a conversation and its associated data. This action cannot be undone. Consider using PATCH with `discarded: true` to hide instead.
- [Get Conversation](https://docs.omi.me/api-reference/endpoint/conversations/get.md): Retrieve a single conversation by ID, optionally including transcript segments.
- [List Conversations](https://docs.omi.me/api-reference/endpoint/conversations/list.md): Retrieve your conversation transcripts. Only returns completed, non-discarded conversations.
- [Update Conversation](https://docs.omi.me/api-reference/endpoint/conversations/update.md): Update a conversation's title or discard status. At least one field must be provided.
- [List Folders](https://docs.omi.me/api-reference/endpoint/folders/list.md): Retrieve all folders for the authenticated user. This endpoint is strictly read-only and returns an empty list if the user has no folders yet. System folders (Work, Personal, Social) are initialized lazily through other paths (the mobile app opening the conversations screen, or the conversation post…
- [Create API Key](https://docs.omi.me/api-reference/endpoint/keys/create.md): Create a new developer API key. The full key is only returned once — store it securely immediately.
- [List API Keys](https://docs.omi.me/api-reference/endpoint/keys/list.md): Retrieve all your developer API keys. Secret key values are not returned — only the prefix is shown.
- [Revoke API Key](https://docs.omi.me/api-reference/endpoint/keys/revoke.md): Permanently revoke (delete) a specific API key. Any requests using this key will immediately stop working.
- [Create Memory](https://docs.omi.me/api-reference/endpoint/memories/create.md): Create a new memory. Memories are timeless facts about the user — preferences, relationships, personal details, and notable insights.
- [Create Memories (Batch)](https://docs.omi.me/api-reference/endpoint/memories/create-batch.md): Create multiple memories in a single request. Maximum 25 memories per batch.
- [Delete Memory](https://docs.omi.me/api-reference/endpoint/memories/delete.md): Permanently delete a memory. This action cannot be undone.
- [List Memories](https://docs.omi.me/api-reference/endpoint/memories/list.md): Retrieve your memories with optional filtering by category. Returns memories sorted by most recent first.
- [Update Memory](https://docs.omi.me/api-reference/endpoint/memories/update.md): Update a memory's content or visibility. At least one field must be provided.
- [List folders](https://docs.omi.me/api-reference/folders/list-folders.md): Retrieve all folders for the authenticated user. This endpoint is strictly read-only and returns an empty list if the user has no folders yet. System folders (Work, Personal, Social) are initialized lazily through other paths (the mobile app opening the conversations screen, or the conversation post…
- [API Reference](https://docs.omi.me/api-reference/introduction.md): Complete reference for the Omi Developer API. Build integrations with memories, conversations, action items, and more.
- [Create memories (batch)](https://docs.omi.me/api-reference/memories/create-memories-batch.md): Create multiple memories in a single request. Maximum 25 memories per batch.
- [Create memory](https://docs.omi.me/api-reference/memories/create-memory.md): Create a new memory. Memories are timeless facts about the user — preferences, relationships, personal details, and notable insights.
- [Delete memory](https://docs.omi.me/api-reference/memories/delete-memory.md): Permanently delete a memory. This action cannot be undone.
- [List memories](https://docs.omi.me/api-reference/memories/list-memories.md): Retrieve your memories with optional filtering by category. Returns memories sorted by most recent first.
- [Update memory](https://docs.omi.me/api-reference/memories/update-memory.md): Update a memory's content or visibility. At least one field must be provided.
- [Building the Device](https://docs.omi.me/doc/assembly/Build_the_device.md): Step-by-step guide to assemble your own Omi device from parts.
- [Parts List](https://docs.omi.me/doc/assembly/Buying_Guide.md): Everything you need to build your own Omi device. Availability and prices may vary by region.
- [Build Your Own Omi Device](https://docs.omi.me/doc/assembly/introduction.md): As an open-source community, we empower enthusiasts to create their own Omi devices. This guide focuses on building the DevKit 1, as later versions use custom PCBs not suited for DIY assembly.
- [App Setup](https://docs.omi.me/doc/developer/AppSetup.md): Set up the Omi Flutter app for development. Build automatically with our dev backend, or manually with your own.
- [Real-Time Audio Streaming](https://docs.omi.me/doc/developer/AudioStreaming.md): Stream audio bytes from your Omi device to any backend service in real time.
- [Contribution Guide](https://docs.omi.me/doc/developer/Contribution.md): Contribute to Omi and earn rewards! Some tasks have paid bounties.
- [Cursor Configuration (.cursor)](https://docs.omi.me/doc/developer/Cursor.md): How Omi uses the .cursor folder (rules, skills, commands, and agents) to guide AI assistance in this repository.
- [DevKit 2 Testing](https://docs.omi.me/doc/developer/DevKit2Testing.md): Test storage, button, and SD card functionality on the Omi DevKit 2.
- [App-Device Protocol](https://docs.omi.me/doc/developer/Protocol.md): BLE protocol specification for communicating with Omi wearable devices
- [Action Items](https://docs.omi.me/doc/developer/api/action-items.md): Create and retrieve action items (tasks/to-dos) via the Developer API
- [Conversations](https://docs.omi.me/doc/developer/api/conversations.md): Create and retrieve conversations via the Developer API
- [Folders](https://docs.omi.me/doc/developer/api/folders.md): Retrieve user-defined folders for organizing conversations via the Developer API
- [API Keys](https://docs.omi.me/doc/developer/api/keys.md): Manage your Developer API keys
- [Memories](https://docs.omi.me/doc/developer/api/memories.md): Create and retrieve memories via the Developer API
- [Quick Start](https://docs.omi.me/doc/developer/api/overview.md): Access your Omi data programmatically with the Developer API. Build custom integrations, analytics dashboards, and automation workflows using your memories, conversations, and action items.
- [Real-Time Audio Streaming](https://docs.omi.me/doc/developer/apps/AudioStreaming.md): Stream raw audio bytes from your Omi device to any backend for custom speech processing, VAD, or audio analysis.
- [Chat Tools](https://docs.omi.me/doc/developer/apps/ChatTools.md): Add custom chat tools to your Omi app that extend Omi's capabilities in user conversations.
- [Data Import APIs](https://docs.omi.me/doc/developer/apps/Import.md): Programmatically create and read conversations and memories in users' Omi accounts using the Integration Import APIs.
- [Integration Apps](https://docs.omi.me/doc/developer/apps/Integrations.md): Build webhook-based apps that connect Omi to external services. Process memories, real-time transcripts, or raw audio.
- [Building Apps for Omi](https://docs.omi.me/doc/developer/apps/Introduction.md): Create apps that extend Omi's capabilities - from custom AI personalities to real-time integrations. Publish to the app store and earn from your creations.
- [Sending Notifications](https://docs.omi.me/doc/developer/apps/Notifications.md): Send push notifications to Omi users from your apps - both direct text notifications and AI-generated proactive notifications.
- [OAuth Authentication](https://docs.omi.me/doc/developer/apps/Oauth.md): Integrate your application with Omi using OAuth 2.0 to securely access user data with explicit consent.
- [Open Source Your App](https://docs.omi.me/doc/developer/apps/OpenSource.md): Contribute your Omi app to the open-source repo. Share your code with the community, get visibility, and help other developers learn from your work.
- [Prompt-Based Apps](https://docs.omi.me/doc/developer/apps/PromptBased.md): Customize Omi's behavior with prompts - no server required. Create specialized AI personalities and memory processors.
- [Publish Your App](https://docs.omi.me/doc/developer/apps/Submitting.md): Submit your app to the Omi app store. Learn the review process, guidelines, and best practices for a successful submission.
- [GitHub](https://docs.omi.me/doc/developer/apps/examples/Github.md): Create GitHub issues using voice commands through your OMI device
- [Omi Mentor](https://docs.omi.me/doc/developer/apps/examples/OmiMentor.md): Get personalized AI mentorship during your conversations with OMI
- [Slack](https://docs.omi.me/doc/developer/apps/examples/Slack.md): Send Slack messages using voice commands through your OMI device
- [Backend Setup](https://docs.omi.me/doc/developer/backend/Backend_Setup.md): Set up the Omi backend infrastructure for local development. This guide covers Google Cloud, Firebase, OAuth, and all required services.
- [Storing Conversations & Memories](https://docs.omi.me/doc/developer/backend/StoringConversations.md): This document outlines how Omi stores conversation data and extracts memories from conversations.
- [Backend Deep Dive](https://docs.omi.me/doc/developer/backend/backend_deepdive.md): Welcome to the Omi backend! This document provides a comprehensive overview of Omi's architecture and code, guiding you through its key components, functionalities, and how it all works together to power a unique and intelligent AI assistant experience.
- [Chat System Architecture](https://docs.omi.me/doc/developer/backend/chat_system.md): A comprehensive technical deep dive into how Omi's intelligent chat system processes questions, routes them through LangGraph, calls tools, and generates contextual responses.
- [Listen + Pusher Pipeline](https://docs.omi.me/doc/developer/backend/listen_pusher_pipeline.md): Sequence diagrams for the /v4/listen WebSocket and Pusher processing pipeline
- [Real-time Transcription](https://docs.omi.me/doc/developer/backend/transcription.md): A comprehensive guide to Omi's real-time audio transcription system, covering WebSocket connections, STT providers, speaker diarization, message formats, and building external custom STT services.
- [For agents](https://docs.omi.me/doc/developer/cli/agents.md): Stable agent contract — JSON output, exit codes, retry semantics.
- [Command reference](https://docs.omi.me/doc/developer/cli/commands.md): Every verb, every flag.
- [Install](https://docs.omi.me/doc/developer/cli/install.md): Install omi-cli and confirm the binary is on your PATH.
- [Introduction](https://docs.omi.me/doc/developer/cli/introduction.md): Talk to Omi from your terminal. Designed for humans and agents alike.
- [Quickstart](https://docs.omi.me/doc/developer/cli/quickstart.md): Get from zero to your data — pick browser OAuth or paste a dev API key.
- [Troubleshooting](https://docs.omi.me/doc/developer/cli/troubleshooting.md): Common failure modes and how to fix them.
- [Compile Firmware](https://docs.omi.me/doc/developer/firmware/Compile_firmware.md): Build and flash custom firmware for your Omi device using nRF Connect.
- [Examples](https://docs.omi.me/doc/developer/mcp/examples.md): Example prompts and integrations with the Omi MCP server
- [Introduction](https://docs.omi.me/doc/developer/mcp/introduction.md): Connect AI assistants to your Omi data using the Model Context Protocol
- [Setup](https://docs.omi.me/doc/developer/mcp/setup.md): Connect your AI assistant to the Omi MCP server
- [Tools Reference](https://docs.omi.me/doc/developer/mcp/tools.md): Complete reference for all Omi MCP tools
- [Troubleshooting](https://docs.omi.me/doc/developer/mcp/troubleshooting.md): Debug and fix common MCP connection issues
- [Cloud Audio Storage](https://docs.omi.me/doc/developer/savingaudio.md): Set up Google Cloud Storage for saving audio files from your Omi device.
- [React Native SDK](https://docs.omi.me/doc/developer/sdk/ReactNative.md): Cross-platform mobile SDK for connecting to Omi devices via Bluetooth Low Energy
- [Python SDK](https://docs.omi.me/doc/developer/sdk/python.md): Connect to Omi devices over Bluetooth, decode Opus audio, and transcribe in real-time using Deepgram
- [SDK Overview](https://docs.omi.me/doc/developer/sdk/sdk.md): Build on top of Omi with official SDKs for Python, Swift, and React Native
- [Swift SDK](https://docs.omi.me/doc/developer/sdk/swift.md): Native iOS/macOS SDK for connecting to Omi devices with local Whisper transcription
- [Update Omi Firmware](https://docs.omi.me/doc/get_started/Flash_device.md): Keep your Omi device up to date with the latest firmware. Use the app for easy updates or follow the manual process.
- [Chat Tips & Best Practices](https://docs.omi.me/doc/get_started/chat_tips.md): Learn how to get the best results from Omi chat. Discover prompting strategies, example questions, and tips based on how the system works internally.
- [Introduction](https://docs.omi.me/doc/get_started/introduction.md): Welcome to Omi - the world's most advanced open-source AI wearable
- [Omi DevKit 1](https://docs.omi.me/doc/hardware/DevKit1.md): DevKit 1 is a necklace form factor device that can be worn around the neck. It runs on Xiao nRF52840, is powered by a rechargeable battery, and connects to your phone to stream the audio data.
- [Omi DevKit 2](https://docs.omi.me/doc/hardware/DevKit2.md): DevKit 2 builds on DevKit 1 with 8GB onboard storage, a speaker, and a programmable button. This enables standalone recording mode while maintaining the necklace form factor.
- [Omi](https://docs.omi.me/doc/hardware/OmiConsumer.md): The Omi Consumer Version 1 (CV1) is the latest hardware, built for everyday use. Powered by a dual-core nRF5340 SoC with Wi-Fi 6 and dual microphones for high-quality audio capture.
- [Painting OMI device](https://docs.omi.me/doc/hardware/PaintingOMI.md): A comprehensive guide on how to paint your OMI device for a custom look.
- [Assembly & BOM](https://docs.omi.me/doc/hardware/consumer/assembly.md): Bill of Materials and assembly reference for building the Omi from components.
- [Electronics](https://docs.omi.me/doc/hardware/consumer/electronics.md): PCB design files for the Omi mainboard, charger board, and flexible PCB — Altium source, Gerber files, and schematics.
- [Open Source Hardware](https://docs.omi.me/doc/hardware/consumer/index.md): Complete open-source design files for the Omi Consumer — PCB schematics, Gerbers, mechanical STEP files, BOM, and assembly guides.
- [License](https://docs.omi.me/doc/hardware/consumer/license.md): The Omi hardware design files are released under the MIT license.
- [Mechanical & Packaging](https://docs.omi.me/doc/hardware/consumer/mechanical.md): STEP files for the Omi enclosure, charger dock, and retail packaging — organized by manufacturing process.
- [Hardware & Assembly](https://docs.omi.me/doc/hardware/omiGlass.md): Open source smart glasses with 6x the battery life of Meta Ray-Bans. Build your own AI-powered glasses with the XIAO ESP32 S3 Sense.
- [Flash Firmware](https://docs.omi.me/doc/hardware/omiglass/flash-firmware.md): Flash the latest OmiGlass firmware using PlatformIO
- [Disclaimer](https://docs.omi.me/doc/info/Disclaimer.md): Important information about using Omi devices and software.
- [License](https://docs.omi.me/doc/info/License.md): Omi is open source software available under the MIT License.
- [Privacy Policy](https://docs.omi.me/doc/info/Privacy.md): At Omi, your privacy and the security of your data are our top priorities. This Privacy Policy explains how we collect, use, and protect your information.
- [Support](https://docs.omi.me/doc/info/Support.md): Get help with Omi through our community channels or contact us directly for commercial inquiries.
- [Integrate 3P Wearables](https://docs.omi.me/doc/integrations.md): A guide to integrating any wearable device, like Plaud, Limitless, or your own custom hardware, with the Omi open-source ecosystem.
- [Get Started with Omi](https://docs.omi.me/getstartedwithomi.md): Choose your device and get started with Omi

## OpenAPI Specs

- [openapi](https://docs.omi.me/api-reference/openapi.json)
- [package](https://docs.omi.me/package.json)
- [package-lock](https://docs.omi.me/package-lock.json)