No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Intent-Lab · Codex Skill · ★ 2.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is VisionClaw safe to install? View the security audit →
VisionClaw A real-time AI assistant for Meta Ray-Ban smart glasses. See what you see, hear what you say, and take actions on your behalf -- all through voice. Built on Meta Wearables DAT SDK (iOS) / DAT Android SDK (Android) + Gemini Live API + OpenClaw (optional). Supported platforms: iOS (iPhone) and Android (Pixel, Samsung, etc.) What It Does Put on your glasses, tap the AI button, and talk: "What am I looking at?" -- Gemini sees through your glasses camera and describes the scene "Add milk to my shopping list" -- delegates to OpenClaw, which adds it via your connected apps "Send a message to John saying I'll be late" -- routes through OpenClaw to WhatsApp/Telegram/iMessage "Search for the best coffee shops nearby" -- web search via OpenClaw, results spoken back The glasses camera streams at 1fps to Gemini for visual context, while audio flows bidirectionally in real-time. How It Works Meta Ray-Ban Glasses (or phone camera) | | video frames + mic audio v iOS / Android App (this project) | | JPEG frames (1fps) + PCM audio (16kHz) v Gemini Live API (WebSocket) | |-- Audio response (PCM 24kHz)
| Stars | 2,556 |
| Forks | 511 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 65.5776865573431/100 |
| Open Issues | 42 |
| Last Updated | 2026-09-20 |
| Created | 2026-02-06 |
| Platforms | gemini, node |
| Est. Tokens | ~17k |
These tools work well together with VisionClaw for enhanced workflows:
Looking for a VisionClaw alternative? If you're comparing VisionClaw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex
Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark
📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Codex, Claude Co
Skills for pi coding agent (compatible with Claude Code and Codex CLI)
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,
A Claude or Codex skill for deliberate skill development during AI-assisted coding
Explore other popular codex skill tools:
VisionClaw is Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw. It is categorized as a Codex Skill with 2.6k GitHub stars.
VisionClaw is primarily written in TypeScript.
You can find installation instructions and usage details in the VisionClaw GitHub repository at github.com/Intent-Lab/VisionClaw. The project has 2.6k stars and 511 forks, indicating an active community.
The top alternatives to VisionClaw on Agent Skills Hub include refly, Claude-to-IM-skill, skillshare. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: