A powerful skill for AI coding agents to manage Proxmox VE nodes, virtual machines, LXC containers, backups, and storage via the PVE REST API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install proxmox-manager
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 proxmox-manager 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 Proxmox VE Cluster Management?
The Proxmox VE Management skill empowers AI coding agents to interact directly with Proxmox VE clusters via the REST API. This integration allows automated provisioning, status monitoring, and lifecycle management of virtual machines (QEMU) and LXC containers directly through natural language requests.
By incorporating this workspace capability into Openclaw Skills, developers and sysadmins can seamlessly automate cluster management. The skill supports authenticating via secure API tokens or a credentials file, facilitating operations from simple VM restarts to robust snapshot restorations and backup creations, making it an indispensable asset for DevOps and homelab automation.
Proxmox VE Cluster Management Use Cases
- Automatically start, stop, shutdown, or reboot specific virtual machines (QEMU) or LXC containers through chat interactions.
- Monitor cluster health, resource allocation, and individual node metrics such as CPU and memory utilization.
- Create, list, and roll back virtual machine snapshots before performing risky software upgrades or configuration changes.
- Manage local and remote storage arrays, audit backup archives, and trigger immediate vzdump backups.
- Streamline infrastructure automation workflows inside Openclaw Skills by running task audits and viewing real-time logs for ongoing container operations.
How Proxmox VE Cluster Management Works
- Authentication: The skill initializes using a configured Proxmox API Token or a standard credentials file to securely access the PVE cluster API without needing interactive logins.
- API Interaction: The AI agent translates user intent (e.g., 'start VM 101') into structured REST API requests targeted at specific endpoints (
/api2/json/...). - Command Execution: Secure cluster communications are executed via HTTP operations (GET, POST, DELETE), bypassing SSL constraints where self-signed certificates are active.
- Response Processing: Output payloads are processed and filtered (often using
jqcommands or native JSON parsing) to present human-readable cluster metrics, task progress status, and VM specifications back to the user.
Proxmox VE Cluster Management Setup
Authentication Configuration
To configure the Proxmox skill, set your environment variables or store them in a secure credentials file.
Option 1: API Token (Recommended)
Export the following environment variables directly in your terminal configuration:
export PROXMOX_HOST="https://192.168.1.100:8006"
export PROXMOX_TOKEN_ID="user@pam!tokenname"
export PROXMOX_TOKEN_SECRET="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
Option 2: Credentials File
Alternatively, write your credentials directly to ~/.proxmox-credentials:
cat > ~/.proxmox-credentials << 'EOF'
PROXMOX_HOST=https://192.168.1.100:8006
PROXMOX_TOKEN_ID=user@pam!monitoring
PROXMOX_TOKEN_SECRET=your-token-secret
EOF
chmod 600 ~/.proxmox-credentials
Create your API token directly within the Proxmox VE UI by navigating to: Datacenter -> Permissions -> API Tokens -> Add.
Proxmox VE Cluster Management Data Schema & Taxonomy
The Proxmox VE Management skill interacts with the Proxmox API structure, mapping out data points into clean JSON outputs. It categorizes PVE entities using distinct identifiers:
| Entity Type | Endpoint Pattern | Key Properties Returned |
|---|---|---|
| Cluster | /api2/json/cluster/status |
Cluster name, node membership, quorum, health status |
| Nodes | /api2/json/nodes |
Node name, online status, CPU cores, active memory load |
| Virtual Machines (QEMU) | /api2/json/nodes/{node}/qemu |
VMID, name, VM status (running/stopped), memory limit |
| Containers (LXC) | /api2/json/nodes/{node}/lxc |
VMID, container name, running state, storage allocations |
| Snapshots | /api2/json/nodes/{node}/qemu/{vmid}/snapshot |
Snapshot name, descriptive notes, parent structure, timestamp |
| Storage | /api2/json/nodes/{node}/storage |
Storage pool name, storage type (LVM, Directory, NFS), active state, utilization percentage |
All non-blocking state updates (like VM starts and stops) produce an asynchronous task unique identifier (UPID) that can be used to track the task execution logs in real-time.
Proxmox VE Cluster Management Advanced Features
- Unified PVE CLI Wrapper: Employs a specialized helper script (
scripts/pve.sh) allowing rapid control of clusters, VMs, and container power states with streamlined syntax. - Asynchronous Task Auditing: Utilizes
UPIDtracking to monitor long-running background processes like vzdump backups or container cloning, ensuring full visibility into asynchronous execution queues. - Zero CSRF Overhead: Employs stateless API token authorization (using the
PVEAPITokenauthorization header) which eliminates the need to acquire and refresh temporary CSRF tokens during state-modifying requests. - Self-Signed Certificate Compatibility: Easily handles local private testing environments with automated secure flags to bypass SSL strict verification (
-k), which is highly typical of default Proxmox home lab installations. - Comprehensive Snapshot Management: Provides seamless automated API workflows to perform state checks, capture pre-update snapshots, and safely execute rollbacks in case of script failures within Openclaw Skills integrations.
SKILL.md
Loading
Related Openclaw Skills
MCPorter
MCPorter is a versatile command-line interface designed to configure, authenticate, inspect, and call Model Context Protocol (MCP) servers and tools directly via HTTP or stdio.
Model Configuration and Routing
A technical capability designed to configure, switch, and troubleshoot model providers, routing sessions, and cron executions in OpenClaw.
Agent Browser Shield
A Chromium extension that sanitizes web pages by masking PII, blocking dark patterns, and neutralizing prompt injections before an AI agent parses them.
Expense Tracker Agent Skill
A scheduled, AI-driven daily expense tracker that processes Telegram check-ins, deduplicates entries, and syncs local Markdown ledgers with Google Sheets.
Portainer
Control your Docker infrastructure and Portainer stacks directly through API-driven automation utilizing Openclaw Skills.
Coding Agent
A background-first, multi-engine autonomous programming skill that runs Codex, Claude Code, OpenCode, and Pi Coding Agent safely inside isolated working directories.
Featured*
