VisionClaw

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

View on GitHub↗Upstream Intent-Lab/VisionClaw↗

Builder

Intent-Lab

Intent-Lab • individual

Stars

1,959

Using upstream star count

Forks

350

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Feb 6, 2026

Project creation date

README Summary

VisionClaw is a real-time AI assistant designed for Meta Ray-Ban smart glasses that combines voice interaction, computer vision, and autonomous actions. The system leverages Gemini Live for natural language processing and OpenClaw for agentic capabilities, enabling users to interact with their environment through multimodal AI assistance. It provides hands-free operation by processing visual input from the smart glasses and responding with intelligent actions.

AI Dev Skills

Unmapped

Tags

Multimodal AI IntegrationReal-time Computer VisionVoice Interface DevelopmentAgentic AI SystemsWearable Computing IntegrationAPI Integration and OrchestrationEdge AI OptimizationStreaming Audio ProcessingLive Video AnalysisAudioEdge AIPersonal Productivity ToolsAugmented Reality Information OverlayWearable DeviceReal-time Visual Question AnsweringWearable TechnologyCross-platform DevelopmentTextCloud APIAugmented RealityImageEdge/MobileMultimodal ReasoningMultimodalConsumer ElectronicsContext-aware Personal AssistantVoice-controlled Task AutomationWearable AIVoice User Interface DesignReal-time AI ProcessingReal-time Streaming ProcessingAgentic AIWearable ComputingHands-free AI Assistant

Recent Activity

Updated 27 days ago

7 Days

30 Days

90 Days

Quality

prototype

Quality: medium
Maturity: prototype

PM Skills

Developer Platform

Languages

No language breakdown recorded.

Timeline

Project created: Feb 6, 2026
Forked: Mar 12, 2026
Your last push: 27 days ago
Upstream last push: 10 days ago
Tracked since: Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…