How do I get started with Huddle01 VMs?

Install the MCP server via npx (npx -y @huddle01/mcp --install antigravity) and then chat with your AI assistant to create and manage VMs. Alternatively, use the web console at get.huddle01.com.

What operating systems are supported?

Currently, Huddle01 VMs provides Ubuntu 24.04 LTS with Kernel 6.8, pre-installed with tools like ffmpeg, Go, make, and fio. More OS options may be added in the future.

How is pricing structured?

Pricing is per-second billing with no egress markup—only compute costs. This typically results in ~70% savings compared to hyperscalers like AWS. Specific pricing tiers are available on the website.

Can I use my own SSH key and get a public IP?

Yes, every VM comes with an SSH key, a public IP, and a URL on huddle01.app for easy access.

Is Huddle01 VMs suitable for production workloads?

Yes, it uses dedicated AMD EPYC vCPUs and unthrottled NVMe storage, with performance benchmarks showing superior throughput over comparable AWS instances at lower cost.

Huddle01 VMs

Virtual Machines for Your Agents

Visit

What is Huddle01 VMs

Huddle01 VMs is a cloud-based virtual machine service that lets you spin up and manage VMs directly through chat with AI assistants like Claude, Cursor, or any MCP-compatible tool. It offers high-performance AMD EPYC CPUs, unthrottled NVMe storage, unlimited ingress, and per-second billing, making infrastructure management as simple as typing a command.

Key Features

Chat-based VM provisioning via MCP server

Dedicated AMD EPYC vCPUs with no throttling

Unlimited ingress and per-second billing

Unthrottled NVMe storage for high I/O performance

Works with Claude, Cursor, Antigravity, and other MCP clients

Use Cases

Non-developers deploying web applications or scripts by chatting with an AI assistant
Developers integrating multi-agent systems that self-deploy infrastructure
AI researchers provisioning isolated environments for model training and experimentation
Teams running CI/CD builds, video transcoding, or database workloads with consistent performance

Why do startups need this tool?

Startups can leverage chat-based infrastructure management to reduce the learning curve and automate deployment, saving engineering time. With per-second billing and no egress markup, costs are significantly lower than hyperscalers, making it ideal for lean teams. The high-performance NVMe storage and dedicated vCPUs ensure fast execution for data-intensive and AI workloads.