VergeIO Launches Verge CLI, Enabling an AI-Powered VMware Alternative
Verge CLI gives an AI platform commands to act, an MCP server connects it over the open Model Context Protocol, and agent skills supply the know-how. Claude Code, OpenAI’s Codex, or a local model can operate a customer’s VergeOS environment in plain language, with the administrator in control of what it can do.
For More Details
Verge CLI Datasheet
Get the full technical breakdown of Verge CLI, the MCP server, and the agent skills.
View the Datasheet
VergeIO, the Private Cloud Operating System company, announced Verge CLI, a complete command-line interface for VergeOS that turns a leading VMware alternative into an AI-powered platform. Alongside the CLI, VergeIO is releasing an MCP server built on the open Model Context Protocol and a set of agent skills. Together they let agentic AI platforms, including Anthropic’s Claude Code and OpenAI’s Codex, work with a customer’s VergeOS environment directly, building networks, deploying workloads, and diagnosing faults in plain language, with the administrator deciding what the assistant runs on its own and what needs their approval.
Key Takeaways
Verge CLI is a complete command-line interface that maps to the full VergeOS API, covering compute, storage, networking, and data protection from one command set.
An MCP server on the open Model Context Protocol and a set of agent skills let Claude Code, OpenAI’s Codex, or any compatible platform operate a VergeOS environment in plain language.
The administrator decides what the assistant runs on its own and what needs approval, so conversational operation runs inside the limits a person sets.
Privacy or security sensitive teams run a local open-weight model, keeping every operation and all environment data on their own infrastructure.
API-First by Design
VergeOS has always been API-first, so Verge CLI was a natural extension of the company’s development philosophy. The interface maps to the full VergeOS API, so one command set covers compute, storage, networking, and data protection. That command set is the hands an AI platform uses to act, and a set of agent skills supplies the know-how to drive it. Claude Code or Codex reads the environment, proposes the work, and runs it within the limits the administrator sets. Infrastructure that used to mean per-core VMware licensing now takes direction in plain language.
Open by Standard, Including Local AI
The MCP server is built on the Model Context Protocol, an open standard, so any compatible client works rather than a single vendor’s assistant. Teams with privacy or security requirements run a local open-weight model, such as Llama, Qwen, or DeepSeek through a runtime like Ollama, and keep every operation and all environment data on their own infrastructure.
Key Terms
Verge CLI
A complete command-line interface for VergeOS. It maps to the full platform API, so one command set drives compute, storage, networking, and data protection.
MCP Server
A server that gives an AI platform a secure, scoped window into a VergeOS environment and its documentation, built on the open Model Context Protocol.
Model Context Protocol (MCP)
An open standard supported by today’s major AI platforms. It lets any compatible client connect to the VergeOS environment rather than a single vendor’s assistant.
Agent Skills
A library that encodes how VergeOS engineers design networks, deploy workloads, and run diagnostics, giving an AI platform the know-how to drive the command set.
Local Open-Weight Model
A model such as Llama, Qwen, or DeepSeek run inside the customer’s own environment through a runtime like Ollama, so no environment data leaves their infrastructure.
One API, Diagnoses Grounded in How the Platform Works
Live Webinar
See Verge CLI in action
Watch Claude Code and Codex operate a live VergeOS environment in plain language. Register for the live session.
Save Your Seat
Because one API spans the whole platform, an AI agent traces a fault end to end rather than guessing from a single layer. The agent reasons against VergeOS documentation through the MCP server, so its conclusions come from how the platform actually behaves.
How Verge CLI Compares
Traditional VMware Stack VergeOS with Verge CLI
Management surface Separate consoles for hypervisor, storage, and network One command set across compute, storage, networking, and data protection
AI operation Chatbots that answer documentation questions Claude Code, Codex, or a local model that acts on the environment
Control model Scripts and manual change windows Administrator sets what the assistant runs on its own and what needs approval
Data privacy Cloud-bound AI services Local model option keeps all environment data on-premises
Frequently Asked Questions What is Verge CLI?
Verge CLI is a complete command-line interface for VergeOS. It maps to the full platform API, so one command set covers compute, storage, networking, and data protection, whether an administrator types the commands or an AI platform proposes them.
How do Claude Code and OpenAI’s Codex work with VergeOS?
An MCP server built on the open Model Context Protocol connects the AI platform to the environment, and a set of agent skills supplies the know-how. Claude Code or Codex reads the environment, proposes the work, and runs it within the limits the administrator sets.
Does the AI act on its own?
The administrator decides what the assistant runs on its own and what needs their approval. Conversational operation runs inside the limits a person sets, not outside them.
Can we use a local AI model for privacy or security?
Yes. Teams with privacy or security requirements run a local open-weight model, such as Llama, Qwen, or DeepSeek through a runtime like Ollama. Every operation and all environment data stay on their own infrastructure.
When is Verge CLI available?
Verge CLI is available on June 23rd to VergeOS customers, along with the MCP server and agent skills.
Jason Yaeger, SVP of Product and Engineering, VergeIO
Customers leaving VMware want lower cost and infrastructure ready for AI. Verge CLI gives them both. Claude Code, Codex, or a local model they run themselves can all operate the platform directly, and the administrator stays in control of what it’s allowed to do.
Larry Ludlow, Chief Architect of Verge CLI, VergeIO
The agent reasons against VergeOS documentation through the MCP server, so its diagnoses come from how the platform actually works, not a model’s guess. Because one API spans compute, storage, and networking, it traces a fault across the whole stack that tooling stitched across separate products would miss.
