A monitoring tool to track real-time VRAM usage and node availability across distributed AI computing clusters.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gpu-check
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gpu-check using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is GPU Status Monitor?
The GPU Status Monitor is a dedicated utility within the Openclaw Skills ecosystem, designed to provide developers with instant visibility into their hardware resources. It specifically targets distributed AI compute nodes, such as local RTX 3090 and 4090 setups, fetching live telemetry via API endpoints. By integrating this into your workflow, you can ensure your AI agents have sufficient resources before deploying intensive workloads or fine-tuning sessions.
GPU Status Monitor Use Cases
- Checking the availability of local GPU clusters before launching LLM inference tasks.
- Monitoring the online status of distributed API services across specific local network IPs.
- Visualizing resource distribution using progress bars for better capacity planning within Openclaw Skills.
How GPU Status Monitor Works
- The skill listens for specific triggers like /gpu or status-related queries.
- It sends concurrent requests to the /gpu endpoints of configured IP addresses (e.g., 192.168.2.236 and 192.168.2.164).
- It validates node availability and retrieves current VRAM metrics via the axios library.
- The raw metrics are parsed into a human-readable format.
- A Markdown table is generated, featuring visual progress bars to indicate memory pressure and online status.
GPU Status Monitor Setup
To integrate this into your environment, navigate to the skill directory and install the necessary dependencies:
cd ~/.openclaw/workspace/skills/gpu_check
npm init -y
npm install axios
Ensure that your GPU nodes are running a compatible service that exposes health data at the /gpu path for this specific skill to function.
GPU Status Monitor Data Schema & Taxonomy
The skill processes and displays data using the following schema:
| Attribute | Description |
|---|---|
| Node Identifier | The IP address or hostname of the compute node (e.g., 192.168.2.236). |
| Memory Usage | Current VRAM consumption relative to the total capacity (MB/GB). |
| Progress Bar | A visual representation of VRAM saturation using Markdown symbols. |
| Service Status | Connectivity indicator showing if the API node is reachable. |
GPU Status Monitor Advanced Features
- Multi-node parallel polling for high-efficiency monitoring across local clusters.
- Integration-ready architecture for resource-dependent Openclaw Skills that require hardware verification.
- Real-time connectivity alerts for distributed AI services.
- Extensible node configuration to support additional IP addresses or custom hardware types.
SKILL.md
Loading
Related Openclaw Skills
WPS/Word Automation (Windows)
A robust Python-based automation tool for programmatically controlling Microsoft Word and WPS Writer on Windows via COM interfaces.
WPS PowerPoint Automation
A robust Windows-based automation utility that programmatically controls PowerPoint and WPS Presentation to manage slide content, formatting, and exports.
NotebookLM CLI Wrapper
A command-line interface wrapper for NotebookLM that enables automated AI research, source management, and artifact generation.
plsreadme
Instantly share markdown documents and text as clean, readable web links via plsreadme.com.
Workspace Manager
An automated organization assistant for ClawPad that builds structured workspaces and document templates tailored to specific professional domains.
IKEA Dirigera Smart Home Control
A comprehensive Python-based integration for controlling IKEA Dirigera smart hubs to manage lights, outlets, and automation scenes.
Featured*
