# Intent-Lab/VisionClaw

Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw

Repository: https://github.com/Intent-Lab/VisionClaw
Canonical: https://ross.abutalabs.com/products/visionclaw
Language: TypeScript
License: NOASSERTION
License Family: other
Last push: 2026-08-19T02:31:30+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 35, longevity 14
- inputs: {"age_days": 208, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2529, forks 497 (observed 2026-08-28T04:06:58.787886+00:00)

## What it is
VisionClaw is a real-time AI assistant app for Meta Ray-Ban smart glasses that streams camera frames and microphone audio to the Gemini Live API for voice-and-vision interaction. It can delegate agentic actions like messaging, web search, and smart home control to an optional OpenClaw gateway, and runs on iOS and Android.

## Use cases
- ask ai what i'm looking at through my smart glasses
- voice assistant for meta ray-ban glasses
- control apps hands-free with voice via glasses camera
- stream glasses point-of-view video to a browser
- add reminders and send messages by talking to my glasses
- build a multimodal ai assistant on wearable hardware

## When to choose
- you own Meta Ray-Ban smart glasses and want a hands-free AI assistant
- you want real-time voice + vision interaction using Gemini Live
- you want agentic actions (messaging, search, smart home) delegated to OpenClaw
- you want to experiment with wearable multimodal AI on iOS or Android

## When to avoid
- you need a fully supported, production-grade commercial product
- you don't have Meta Ray-Ban glasses or a compatible phone camera setup
- you want a local/offline assistant without cloud LLM dependency
- you need a non-Gemini model backend without modification

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, computer-vision, agent-framework, chatbot, llm-inference, websocket
- domain: artificial-intelligence, mobile-development, computer-vision, speech-processing
- platform: -
- tags: smart-glasses, gemini-live, meta-ray-ban, voice-assistant, multimodal-ai, wearable-ai, openclaw, real-time, ai-agents, wearables, ios, android, mobile, swift, typescript

## Member repositories
- Intent-Lab/VisionClaw (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.787886+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:25:21.921981+00:00, confidence not recorded.
  - readme: https://github.com/Intent-Lab/VisionClaw (fetched 2026-08-28T04:06:58.787886+00:00, sha 85d8c5f931db)
- Data as of 2026-08-30T08:39:29.467469+00:00.