A web-based VPS management panel that enables users to deploy websites, manage Docker containers, and run AI agents through a graphical interface. It targets operations teams and general users who prefer visual server management over command-line administration.
Project overview
It combines traditional server orchestration with native AI agent capabilities, allowing users to deploy containerized applications, provision websites, and run LLMs from a single web dashboard.
Project type
Model Runtime
Deployment
Refer to project documentation
License
GPL-3.0
Best for
Operations teams and general users who manage Linux VPS environments and prefer web GUI interaction over command-line administration.
Users looking to consolidate application deployment, website hosting, and local AI agent management into a single control panel.
Key capabilities
Deploy Ollama LLMs, spin up OpenClaw personal agents, and monitor GPU utilization from the dashboard.
Launch production-ready websites with automatic domain binding, SSL provisioning, and Nginx configuration.
Install and update 165+ trusted open-source apps, such as Nextcloud, Bitwarden, Umami, and NocoBase, with a single click.
Create, start, stop, and inspect containers, images, networks, and volumes through a visual UI.
Configure firewall rules, fail2ban, container isolation, WAF, and audit logs from day one.
Schedule automated backups to AWS S3, Cloudflare R2, or local storage and restore snapshots in one click.
Limitations and risks
Requires a Linux VPS; documented compatible distributions include Debian, Ubuntu, CentOS, and Rocky.
Internet access is required during the installation process.
There is no end-to-end documentation confirming a local-only data boundary. Remote APIs or cloud round-trips may occur during integrations or operation.
Telemetry practices are not documented.
Getting started
Run the bash quick start script on a compatible Linux server with at least 1 GB of RAM, which takes approximately 60 seconds. Internet access is required for installation. Access the panel by navigating to the designated HTTP port and security path in a browser.
Alternatives and comparisons
An open-source AI backend control plane providing multi-model routing and an agentic tool harness for application development.
An AI-native proxy server and data plane that centralizes orchestration, safety, observability, and LLM routing.
An asynchronous reinforcement learning training paradigm for building AI agents.