What Are 'Claws'? And Why You Shouldn't Run Them on Your Mac Mini

Source: Dev.to

Andrej Karpathy just posted a mini‑essay about buying a Mac Mini to tinker with what he calls “Claws” — persistent AI‑agent systems that sit on top of LLMs. He names OpenClaw, NanoClaw, zeroclaw, ironclaw, picoclaw.
Simon Willison calls “Claw” a term of art for the entire category.

When Karpathy names something, it sticks. He coined “vibe coding.” This is the same energy.

Definition – “Just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level.”

I’ve been building managed infrastructure for exactly this category. Below I break down what Claws are, why running them on a Mac Mini has real trade‑offs, and what the alternative looks like.

What Makes a Claw Different from an Agent?

Regular LLM agents run, do a thing, and stop. You prompt them, they respond, maybe they call a tool, done.

Claws are persistent. They:

• Run continuously on hardware or a server
• Have their own scheduling — they act without you asking
• Maintain context across sessions and conversations
• Communicate via messaging protocols (MCP, etc.)
• Orchestrate multiple agents with tool access

Think of it as the difference between running a script and running a service. A Claw is a service: always on, always watching, always ready to act.

The Mac Mini Angle

Karpathy bought a Mac Mini specifically to run Claws. The Apple Store told him they’re “selling like hotcakes and everyone is confused.” It makes sense — decent hardware, small form factor, runs 24/7 at home.

But here are some thoughts from someone who’s been running persistent Elixir services for a while.

The Self‑Hosting Pain List

I love self‑hosting. I really do. However, running a persistent AI‑agent system on a box under your desk means you’re now responsible for:

Uptime

Your Claw goes down when the power cuts, the ISP hiccups, or macOS decides to update at 3 am. The whole point of a Claw is that it’s always on. “Always on except when it isn’t” is a rough spec.

Networking

A Claw needs internet access — receive webhooks, call APIs, expose endpoints. That means:

• Port forwarding
• Dynamic DNS
• TLS certificates
• Hoping your router cooperates

Your ISP probably gives you a dynamic IP.

Security

You’re running an AI agent with tool access on your home network. It can execute code, make API calls, and access file systems. One mis‑configured permission and your Claw can see everything on your LAN.

Updates & Maintenance

The Claw ecosystem evolves fast. OpenClaw pushes updates regularly. You must manage versions, handle breaking changes, and keep dependencies current. On a personal Mac Mini, that’s manual work.

Process Supervision

What happens when a Claw process crashes? On a Mac Mini, it just… dies. You need to build your own restart logic, health checks, and monitoring. This is a solved problem in production infrastructure, but not on a desktop.

Scaling

Today you run one Claw. Tomorrow you want three. Next month you want one per project. A Mac Mini has finite resources and no way to scale horizontally.

Why Managed Hosting Makes Sense

I’m building OpenClawCloud because I think the pain list above will hit most people who try to run Claws seriously.

The architecture is built on Elixir and runs on Fly.io. Here’s why that matters for Claws specifically:

Supervision Trees

Elixir’s OTP supervision is designed exactly for long‑running processes that need to stay alive. If a Claw process crashes, the supervisor restarts it automatically—no cron jobs, no systemd hacks, no Docker restart policies. It’s built into the runtime.

Process Isolation

Each tenant’s Claw runs in its own isolated process. One Claw crashing doesn’t take down another. The BEAM VM was literally built for this—telecom‑grade reliability for concurrent, independent processes. Ericsson designed it in the ’80s to keep phone switches running; it’s perfect for persistent AI agents too.

Built‑in Scheduling

Claws need to act on their own schedule. Elixir provides Process.send_after, GenServer timers, and libraries like Oban for persistent job scheduling. No external cron needed; the scheduler lives in the same runtime as the agent.

Economics That Work

I run five Elixir apps on Fly.io for under €50 / month total. The infrastructure is efficient enough that hosting multiple Claws per machine is practical without burning through a credit card.

The State of the Ecosystem

Karpathy mentions several projects, each taking a different approach:

The ecosystem hasn’t consolidated yet, but the pattern is clear: people want persistent, tool‑enabled AI‑agent systems that run autonomously.

Where This Is Going

Karpathy naming this category matters. “Vibe coding” went from a tweet to a conference‑talk title in weeks. “Claws” as a term of art will follow the same trajectory. Simon Willison is already using it, and it even has an established emoji: 🦞.

The interesting question isn’t whether Claws are real—they obviously are—but whether the infrastructure catches up. Right now the default path is “buy hardware and figure it out yourself.” That works for tinkering. For production use—agents mana… (the original text cuts off here).

Managing your calendar, monitoring your infrastructure, handling customer requests — you need something more robust.

That's the gap I'm building **[OpenClawCloud](https://clawcloud.net/)** to fill. You bring your Claw config, I handle deployment, uptime, and process supervision. No Mac Mini required.

I'm a solo founder building this in Elixir from Braga, Portugal. It's early days, but the foundation is solid — and today, thanks to Karpathy, the category has a name.

* I'm [@joaosetas](https://x.com/joaosetas) on X. Building OpenClawCloud and other Elixir SaaS products in public.