Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
A web-based HUD interface that displays your OpenClaw agent as a JARVIS-style dashboard. Shows a reactive Three.js orb, live chat, audio visualizer, token usage, and system stats. Connects to the OpenClaw Gateway via WebSocket and supports text-to-speech on both macOS and cross-platform.
Gives a visual and audio interface to OpenClaw agents without building a custom frontend from scratch.
When to use it
- Monitoring an agent's thinking and speaking states visually
- Chatting with an OpenClaw agent through a browser interface
- Displaying live token usage and model info during a session
- Running a persistent agent dashboard on a home or office machine
- Using TTS to hear agent responses spoken aloud while working
Example Workflow
Here's how your AI assistant might use this skill in practice.
User wants to interact with their OpenClaw agent through a visual dashboard
- 1Run setup.sh to install dependencies and auto-detect the Gateway token
- 2Copy config.json to config.local.json and set agent name and session key
- 3Start the server with node --env-file=.env server/index.js
- 4Open http://localhost:9999 in a browser
- 5Send messages via the chat panel and watch the orb react to agent state
Live HUD showing agent responses in chat, orb animation reflecting agent state, and TTS reading responses aloud
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.