The open-source iOS app connecting Meta Ray-Ban smart glasses to AI assistants — cloud or fully on-device.
Your glasses. Your AI. Your rules.
"Ok Vision, what am I looking at?"
| Use Case | Example |
|---|---|
| Instant Translation | Point at a menu or sign abroad and get real-time translation |
| Hands-Free Cooking | "What's the next step?" while your hands are covered in dough |
| Smart Shopping | "Is this a good deal?" - get price comparisons and reviews |
| Travel Guide | "Tell me about this building" - instant history and facts |
| Accessibility | Describe surroundings, read text aloud, identify objects |
| Meeting Assistant | "Remember this person is John from Marketing" |
| Learning | "What plant is this?" - identify flora, fauna, landmarks |
| DIY Helper | "How do I fix this?" - show the problem, get step-by-step help |
| Fitness Coach | "Is my form correct?" - real-time posture feedback |
With OpenClaw's 56+ tools: Send emails, control smart home, set reminders, search the web - all hands-free through your glasses.
- Local (MLX): A choice of on-device models via Apple MLX — Qwen 2.5 (0.5B/3B), Gemma 2 2B, Gemma 4 E2B, SmolVLM2 2.2B — so you can trade capability for memory/speed. Private, offline, zero API cost. Pick SmolVLM2 to unlock on-device vision — photo Q&A and a fully-offline live video mode (see below).
- Apple Intelligence: Apple's on-device Foundation Model (iOS 26+). No download, no memory pressure (OS-managed), private and offline. Uses guided generation + Apple's native tool-calling.
- OpenClaw: Wake word activation, 56+ tools, task execution via WebSocket
- Gemini Live: Real-time voice + vision with native audio streaming
- OpenAI: GPT-4o text + vision over the Chat Completions API — works with any OpenAI-compatible endpoint (OpenRouter, Groq, local servers, etc.). Also drives live video via the Realtime API (
gpt-realtime) — continuous voice + camera frames (see below).
Say "Ok Vision, start video stream" to enter a live mode where the glasses camera stays on and the AI answers questions about what you're seeing. Ask freely — no wake word between questions — until you say "stop video". Live video routes to whichever backend you've selected:
- Gemini Live — native continuous audio + 1fps video (cloud).
- OpenAI — the Realtime API (
gpt-realtime): streaming voice + camera frames over WebSocket. Uses the same OpenAI key/base URL you already set (so OpenAI-compatible gateways work too). - Local (SmolVLM2) — fully on-device live video: Apple speech-to-text in, on-device SmolVLM2 answers on the latest frame, spoken back with your chosen voice. No cloud, no cost, works with no signal.
With SmolVLM2 selected as your local model, "Ok Vision, take a photo and tell me what this is" captures a frame from the glasses and answers entirely on-device — nothing leaves the phone. Other local models stay text-only and hand camera questions to a cloud backend. (Images are resized on-device to keep the vision encoder within iOS memory limits.)
- A natural, offline, private voice (Kokoro-82M) running on-device via MLX — selectable from a Speech Engine dropdown with a voice picker.
- Apple's system voice stays the default (with Premium/Enhanced voice support); Kokoro is the upgrade when you want lifelike speech with nothing leaving the phone.
- The models search the web whenever they're unsure or asked about current things — news, weather, prices, scores — and never answer "I can't access real-time data" without trying.
- Tavily (free tier) returns real live content for the model to summarize; DuckDuckGo is the keyless fallback.
- Smart flow: local models reformulate + retry a weak query; the OpenAI backend runs a real function-calling loop (call
web_search→ refine → answer).
- Multi-turn context on the on-device and OpenAI backends: "What's the capital of France?" → "What's its population?" just works.
- Bounded per session so local memory stays safe; Apple keeps context via a reused native session.
- Teach it faces hands-free: "Ok Vision, remember this person as Sara"
- Recognize them later: "Ok Vision, who is this?"
- Runs entirely on-device (Apple Vision
computeDistance) — no cloud, no photos leave your phone - Intent is parsed by the on-device model (agentic) — any phrasing works, and it only triggers for a person actually in view
- Reliable wake word activation ("Ok Vision") for privacy — primed recognition + self-restart so it keeps listening (survives idle, replies, and glasses off/on)
- Barge-in support - interrupt AI anytime by saying "Ok Vision"
- Conversation mode - follow-up questions without wake word
- "Ok Vision stop" - stop AI mid-speech
- Audio routes correctly whether you're using the glasses or the phone alone (loud speaker, not the earpiece)
- Pick a local model, download it on demand, and delete it to reclaim storage anytime from Settings — swap between a tiny 0.5B model and a larger one as you like.
- Photo capture on voice command ("take a photo")
- Live video streaming to Gemini (1fps)
- Seamless glasses registration via Meta AI app
- Auto-reconnect with exponential backoff (12 attempts)
- Network monitoring (auto-pause on WiFi drop)
- App lifecycle handling (suspend/resume connections)
- Secure credential storage
- All API keys configurable in-app
- No code changes needed to use
- Example config files included
| Screen | Description |
|---|---|
| Voice Assistant | Tap the orb or say "Ok Vision" — live transcripts, distinct listening/thinking/speaking states |
| Settings | Configure AI backend, web search, glasses, voice control, and advanced options |
| AI Backends | Choose Local (MLX), Apple Intelligence (on-device), OpenClaw (tools), Gemini Live (low latency), or OpenAI |
| Local Models | Download and manage on-device models (Qwen, Gemma, SmolVLM2, FastVLM) with real sizes and one-tap switching |
- macOS with Xcode 15+
- Physical iOS 18+ device (simulator doesn't support Bluetooth; on-device MLX models need iOS 18)
- Meta Ray-Ban smart glasses
- Meta Developer account for glasses registration
- An AI backend — one of:
- Local (MLX) — no account/key needed; a choice of on-device models (Qwen 2.5, Gemma, SmolVLM). Runs on a recent iPhone (e.g. 15 Pro/16/17)
- Apple Intelligence — no key or download; needs iOS 26+ on an Apple-Intelligence device (iPhone 15 Pro and newer)
- OpenClaw instance
- Gemini API key
- OpenAI API key (or any OpenAI-compatible endpoint)
git clone https://github.com/rayl15/OpenVision.git
cd OpenVision/meta-vision
# Copy config templates
cp Config.xcconfig.example Config.xcconfig
cp OpenVision/Config/Config.swift.example OpenVision/Config/Config.swift- Go to Meta Developer Console
- Create an app or use existing one
- Enable "Wearables" capability
- Copy your App ID and Client Token
# Your Apple Team ID (from Xcode or Apple Developer Portal)
DEVELOPMENT_TEAM = ABC123XYZ
# Your app's bundle identifier
PRODUCT_BUNDLE_IDENTIFIER = com.yourname.openvision
# Meta App ID from developer console
META_APP_ID = 1234567890
# Client Token - MUST be in this format: AR|APP_ID|TOKEN
CLIENT_TOKEN = AR|1234567890|abcdef123456789
# URL scheme for Meta AI callback
APP_LINK_URL_SCHEME = openvisionopen OpenVision.xcodeproj- Select your iOS device (not simulator)
- Build and run (⌘R)
- On first launch, go to Settings → Glasses → Register
- This opens Meta AI app to grant access
- Return to OpenVision
For Gemini Live:
- Get API key from AI Studio
- Settings → AI Backend → Gemini Settings
- Paste your API key
For OpenClaw:
- Install OpenClaw
- Settings → AI Backend → OpenClaw Settings
- Enter gateway URL and auth token
For OpenAI (text, vision + live video):
- Get an OpenAI API key
- Settings → AI Backend → OpenAI, paste the key (and optionally a base URL / models)
- Say "Ok Vision, start video stream" to use live video over the Realtime API
For on-device vision (SmolVLM2):
- Settings → AI Backend → Local (MLX)
- Pick SmolVLM2 2.2B and tap download (~2.6 GB, one time)
- Say "take a photo and tell me what this is", or "start video stream" — all on-device
You: "Ok Vision" → Wake word activates listening
You: "What's the weather today?" → AI processes and responds via TTS
You: "Take a photo" → Captures from glasses, analyzes
You: "Ok Vision stop" → Interrupts AI mid-speech
[Silence for 30s] → Conversation ends
Works with whichever backend is selected — Gemini Live, OpenAI Realtime, or fully on-device SmolVLM2.
You: "Ok Vision, start video stream" → Enters live video mode (uses your selected backend)
[Glasses camera streams; the AI sees continuously]
You: "What am I looking at?" → AI sees and responds
You: "And is this a good deal?" → Keep asking — no wake word needed
You: "Stop video" → Exits live video mode
On the Local (SmolVLM2) backend this runs entirely on-device (speak toward the phone; audio and vision never leave it). On Gemini/OpenAI the camera frames stream to the cloud provider.
[Select Local → SmolVLM2 in Settings]
You: "Ok Vision, take a photo and tell me what this is"
[Glasses capture a frame → SmolVLM2 answers on-device → spoken reply]
| Command | Action |
|---|---|
| "Ok Vision" | Activate listening (wake word) |
| "Ok Vision stop" | Stop AI while speaking |
| "Take a photo" | Capture and analyze view (on-device with SmolVLM2, else cloud) |
| "What do you see?" | Describe current view |
| "Remember this person as Sara" | Enroll a face (on-device) |
| "Who is this?" | Identify the person in view (on-device) |
| "Forget Sara" / "Who do you know?" | Remove / list known faces |
| "What's today's news?" / "Weather in Tokyo?" | Web search (on-device backends) |
| "What's its population?" (as a follow-up) | Uses conversation memory |
| "Start video stream" | Enter live video mode (Gemini / OpenAI Realtime / on-device SmolVLM2) |
| "Stop video" | Exit live video mode |
Commands are routed by the on-device model, so you don't need exact wording — natural phrasing works, and it searches the web on its own when it doesn't know.
| Backend | Voice | Vision | Cost / Privacy | Best For |
|---|---|---|---|---|
| Local (MLX) | Wake word + Apple STT | On-device photo + live video (SmolVLM2); else via a cloud backend | Free · fully on-device | Private chat, face commands, offline vision — pick Qwen/Gemma/SmolVLM |
| Apple Intelligence | Wake word + Apple STT | via a cloud backend | Free · on-device, no download | Private chat on iOS 26+ devices, lowest setup |
| OpenClaw | Wake word + Apple STT | Photo on request | Self-hosted | Tasks, 56+ tools, control |
| Gemini Live | Native VAD (always on) | Continuous 1fps video | Cloud API | Natural, low-latency conversation |
| OpenAI | Wake word + Apple STT · Realtime VAD in live mode | Photo on request (GPT-4o) · live video (Realtime gpt-realtime) |
Cloud API · OpenAI-compatible | Cloud text + vision, live video, cross-checking |
Face recognition, web search, and conversation memory all run on the on-device backends (Gemma, Apple) — private, no photos or queries leave your phone unless you pick a cloud backend. With SmolVLM2, photo Q&A and live video are on-device too.
| Setting | Description |
|---|---|
| AI Backend | Choose Local (MLX), Apple Intelligence, OpenClaw, Gemini Live, or OpenAI |
| Local (MLX) | Pick a model (Qwen 2.5, Gemma, SmolVLM), download it, or delete to reclaim storage. SmolVLM2 adds on-device photo + live video |
| Apple Intelligence | On-device model status (no key or download needed; iOS 26+) |
| Web Search | Tavily key for real live results (news/prices/scores); DuckDuckGo fallback |
| OpenClaw Gateway | WebSocket URL (e.g., wss://localhost:18789) |
| OpenClaw Token | Authentication token |
| Gemini API Key | Google API key |
| OpenAI | API key, chat model (default gpt-4o-mini), base URL (OpenAI-compatible), and realtime model (default gpt-realtime) for live video |
| Custom Instructions | Additional system prompt |
| Memories | Key-value context for AI |
| Setting | Description |
|---|---|
| Wake Word | Activation phrase (default: "Ok Vision") |
| Wake Word Enabled | Toggle wake word requirement |
| Activation Sound | Play chime on wake word |
| Conversation Timeout | Auto-end after silence (15s-2min) |
| Setting | Description |
|---|---|
| Glasses Registration | Register/unregister with Meta AI |
| Connection Status | View connected devices |
| Camera Controls | Manual stream start/stop |
┌─────────────────────────────────────────────────────────────────┐
│ OpenVision App │
├─────────────────────────────────────────────────────────────────┤
│ Views (SwiftUI) │
│ ├── VoiceAgentView Main conversation interface │
│ ├── SettingsView Configuration panels │
│ └── HistoryView Past conversations │
├─────────────────────────────────────────────────────────────────┤
│ Services │
│ ├── OpenClawService WebSocket client, auto-reconnect │
│ ├── GeminiLiveService Native audio/video WebSocket │
│ ├── OpenAIService Chat Completions + web_search loop │
│ ├── OpenAIRealtimeService Live voice + video (gpt-realtime) │
│ ├── GemmaLocalService On-device MLX models (LLM + VLM) │
│ ├── AppleFoundationService Apple Intelligence (iOS 26 model) │
│ ├── LocalAgent Shared agentic routing + conversation │
│ ├── WebSearchService Web search (Tavily + DuckDuckGo) │
│ ├── KokoroTTSService On-device neural voice (Kokoro/MLX) │
│ ├── FaceRecognitionService On-device faces (Apple Vision) │
│ ├── VoiceCommandService Wake word detection, Apple STT │
│ ├── TTSService Apple text-to-speech │
│ ├── AudioCaptureService Microphone input for Gemini │
│ └── AudioPlaybackService Speaker output for Gemini │
├─────────────────────────────────────────────────────────────────┤
│ Managers │
│ ├── GlassesManager Meta DAT SDK wrapper │
│ ├── SettingsManager JSON persistence with debounce │
│ └── ConversationManager Chat history storage │
├─────────────────────────────────────────────────────────────────┤
│ External │
│ ├── Meta DAT SDK Glasses camera & registration │
│ ├── Apple MLX On-device Gemma 4 inference │
│ ├── Apple Vision On-device face recognition │
│ ├── Apple Speech Speech recognition │
│ └── AVFoundation Audio capture & playback │
└─────────────────────────────────────────────────────────────────┘
- Ensure Meta AI app is installed and you're signed in
- Enable Developer Mode in Meta AI app settings
- Check that your Meta App ID matches the developer console
- Verify
CLIENT_TOKENformat:AR|APP_ID|TOKEN - Check all Config.xcconfig values are filled in
- Ensure bundle ID matches what's in Meta Developer Console
- Check Bluetooth connection in iOS Settings
- Ensure glasses are set as audio output device
- Try disconnecting and reconnecting glasses
- Verify API key is correct
- Check internet connection
- Ensure you have Gemini API access (not all regions supported)
- App auto-reconnects up to 12 times with exponential backoff
- Check if OpenClaw server is running
- Verify gateway URL uses
wss://(notws://) for secure connection
OpenVision/
├── App/ App entry point, URL handling
├── Config/ Configuration files
├── Models/ Data models (Settings, Conversation)
├── Services/
│ ├── AIBackend/ Connection state, errors
│ ├── OpenClaw/ WebSocket client
│ ├── GeminiLive/ Native audio WebSocket
│ ├── Voice/ Wake word, STT
│ ├── Audio/ Capture & playback
│ └── TTS/ Text-to-speech
├── Managers/ Singletons (Settings, Glasses)
├── Views/
│ ├── VoiceAgent/ Main UI
│ ├── Settings/ Config screens
│ ├── History/ Chat history
│ └── Components/ Reusable UI
└── Utilities/ Extensions, helpers
- @MainActor - All managers and services are main-actor isolated
- Callbacks - Services use callbacks (not Combine) for events
- Singleton managers - GlassesManager, SettingsManager, etc.
- Exponential backoff - OpenClaw reconnects with jittered delay
# Build for device
xcodebuild -scheme OpenVision -destination 'platform=iOS,name=iPhone' build
# Install on connected device
xcrun devicectl device install app --device <DEVICE_ID> \
~/Library/Developer/Xcode/DerivedData/.../OpenVision.appContributions are welcome!
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
- Follow Swift API Design Guidelines
- Use
@MainActorfor UI-related code - Add documentation comments for public APIs
- Keep services focused and single-responsibility
MIT License - see LICENSE for details.
- Meta Wearables DAT SDK - Glasses integration
- Apple MLX - On-device model inference (Qwen, Gemma, SmolVLM)
- Kokoro TTS - On-device neural voice (Kokoro-82M via MLX)
- Apple Foundation Models - On-device Apple Intelligence
- Google Gemini - Live audio/video AI
- OpenClaw - AI assistant framework
- OpenAI - GPT-4o text + vision
- Tavily - Live web search built for AI assistants
- DuckDuckGo - Keyless web-search fallback
Built with Swift and ❤️