Self-Hosted AI Agent

Which computer should run your agent?

OpenClaw's hardware requirements are small: 1 GB of memory, or 4 GB for Claude Code and Codex, with the model in the cloud. Start on a computer you have. Buy a Mac for iMessage, and 32 GB for big local models.

Every pick, by price

The maker's list price, checked 18 October 2026. The Amazon buttons open the live listing.

Free: use what you have

A small black Dell OptiPlex Micro mounted on the back of a monitor standThe computer you already haveFreeFine for any of the four agents with a cloud model, if you set it never to sleep. Any 64-bit computer with 4 GB of memory, 8 GB to be comfortable.
Illustrative image: a Dell OptiPlex Micro mounted behind a monitor.

Under $400: a small box for a cloud model

A small black Dell OptiPlex Micro desktopDell OptiPlex 7070 Micro, refurbishedabout $237Cloud-model agent, always on, cheapest box with 16 GB that doesn't feel slow. Intel Core i5-9500T (6-core), 16 GB memory, 256 GB NVMe SSD.
Illustrative image: a Dell OptiPlex Micro, an office-surplus mini PC.
A palm-sized Intel NUC mini PC held in a handGMKtec G3S$249.99Cloud-model agent on a new, tiny, low-power box at the lowest price; 8 GB meets Codex's recommended RAM. Intel N95 (4-core), 8 GB memory, 256 GB SSD.
Illustrative image: an Intel NUC mini PC held in one hand.

$600 to $1,300: room for small local models

A small square mini PC with USB and network ports on its sideGMKtec M6 Ultra, 32 GB$679.99Cheapest new 32 GB mini PC for a busy Linux agent host. AMD Ryzen 5 7640HS (6-core), 32 GB memory, 1 TB SSD.
Illustrative image: a mini PC (an older Zotac ZBOX) showing its ports.
A silver Mac mini on a wooden tableMac mini M6, 16 GB$899Always-on cloud-model agent on macOS (needed for OpenClaw's iMessage), silent and 4 W at idle. Apple M6, 12-core CPU, 12-core GPU, 153 GB/s, 16 GB memory, 256 GB SSD.
Illustrative image: a Mac mini (2024 design).
A Mac mini on a wooden table in a shopMac mini M6, 24 GB$1,299macOS agent host with headroom for browser automation and mid-size local models. Apple M6, 12-core CPU, 12-core GPU, 170 GB/s, 24 GB memory, 512 GB SSD.
Illustrative image: a Mac mini (M4, 2024) on a store table.

$1,500 and up: big local models

A silver Mac mini on a wooden tableMac mini M6, 32 GB$1,799Cheapest Apple box that runs 27-35B local models alongside the agent. Apple M6, 12-core CPU, 12-core GPU, 170 GB/s, 32 GB memory, 1 TB SSD.
Illustrative image: a Mac mini (2024 design).
A Mac Studio, a taller silver box than the Mac miniMac Studio M5 Max, 36 GB$2,499Faster local 27-35B models than a Mac mini (about 2.7x the memory bandwidth), still near-silent. Apple M5 Max, 18-core CPU, 32-core GPU, 460 GB/s, 36 GB memory, 512 GB SSD.
Illustrative image: a Mac Studio (2022 design).
The back of a Mac mini: power, Ethernet, HDMI and three Thunderbolt portsMac mini M5 Pro, 64 GB$3,199Apple box that runs 70B-class local models at 4-bit. Apple M5 Pro, 18-core CPU, 20-core GPU, 64 GB memory, 1 TB SSD.
Illustrative image: the back of a Mac mini (M4, 2024).
A drawing of a small cube-shaped computer with its power light onFramework Desktop, 128 GB$3,449128 GB local-model box from a maker with strong Linux support and repairable parts, if you can wait for stock. AMD Ryzen AI Max+ 395 (16-core), 40 graphics cores, 128 GB memory, none included (add M.2 SSD, +$135 for 500 GB to +$2,269 for 8 TB).
Illustrative image: a drawing of a cube-shaped mini PC.
A drawing of a small cube-shaped computer with its power light onGMKtec EVO-X2, 128 GB$3,649.99Most RAM for local models under $4,000, shipping now; runs Linux or Windows. AMD Ryzen AI Max+ 395 (16-core), Radeon 8060S, 128 GB memory, 2 TB SSD (1 TB variant $3,499.99).
Illustrative image: a drawing of a cube-shaped mini PC.

Amazon links on this site are affiliate links: if you buy, I may earn a commission, at no cost to you. As an Amazon Associate I earn from qualifying purchases. Nobody pays to be picked. Prices are the maker's list price, or a typical price, on 18 October 2026.

Self-hosted means the agent runs on a computer you control: its memory, its files and the accounts it signs in to live there. It doesn't usually mean the AI is there too. Most people connect the agent to a model in the cloud, which still sees what the agent sends it. Only a local model keeps that at home, and it takes far more memory.

A small black Lenovo ThinkCentre Tiny standing next to a coffee mug

I run my own agents on five computers: two old mini PCs, two office-surplus Dell OptiPlex desktops and a newer mini PC. Pictured: a Lenovo ThinkCentre Tiny beside a coffee mug, for scale.

Running costs

Leaving a Mac mini on all month costs about $0.53 in electricity, an old laptop about $0.86. Claude Code needs 4 GB of memory. A 30B local model needs 32 GB.

Idle power from published measurements, at the US average of 18.31¢ a kWh (EIA, July 2026). Memory from the Claude Code and Ollama docs. All the figures.

Longer answers

  1. Do you need a Mac mini for OpenClaw?

    When a Mac mini is worth it, which one, and when the computer you have is enough.

  2. How much OpenClaw costs

    The model, the computer and the electricity, worked out for light, daily and heavy use.

  3. Hermes Agent vs OpenClaw

    The two most popular self-hosted agents, compared on setup, memory, channels and cost.

  4. OpenClaw alternatives

    Hermes, NanoClaw, ZeroClaw, PicoClaw, nanobot and the coding agents, and the computer each one needs.

  5. Is OpenClaw safe?

    What can go wrong when an agent has your accounts, and the precautions that limit it.

  6. Which computer can run your agent?

    Each agent on an old laptop, office PC, mini PC, Mac mini, Raspberry Pi or VPS, from its own documentation.

The figures

Computers you may already have

Any of these can run an agent whose model is in the cloud. They differ in what they cost to leave on.

ComputerPower when idleRunning costGood to know
An old laptop6.4 W$0.86 a month in electricityCosts nothing extra if you already own it, but you must set it never to sleep, including with the lid closed, and it stops when it loses power or Wi-Fi.
An office-surplus desktop (e.g. Dell OptiPlex)13 W$1.74 a month in electricityUses about three times the idle power of a Mac mini or N100 mini PC, though that is still under $2.50 a month at the US average electricity price.
A mini PC (e.g. Intel N100)4.8 W$0.64 a month in electricitySmall and cheap to leave on, but with no dedicated graphics card a local model would run on the CPU, which Hermes' docs say works but responds more slowly.
A Mac mini (Apple silicon)4 W$0.53 a month in electricityVery low idle power, and it runs macOS, which OpenClaw's docs say you need for iMessage.
A Raspberry Pi 52.7 W$0.36 a month in electricityThe lowest power draw here, but it is ARM-based, so some optional tools may lack builds, and it is too slow for local models.
A rented server (VPS)–$15–24 a monthAlways on and reachable without touching your home network, but you pay every month and your agent and its files live on someone else's computer.
The computer I use every day–None extraNo extra cost, but the agent only works while that computer is on and awake, and it shares your files, accounts and screen.

Which agents you can self-host

Each still needs an AI model: a paid plan or API account in the cloud, or a local model.

AgentRuns onMemory
OpenClawmacOS, Linux, Windows (native or WSL2)1 GB minimum, 2 GB recommended
Hermes AgentmacOS (Apple silicon), Windows 10/11, Linux, WSL2No published minimum
Claude CodemacOS 13.0+, Windows 10 1809+ or Windows Server 2019+, Ubuntu 20.04+, Debian 10+, Alpine Linux 3.19+4 GB minimum
CodexmacOS, Linux, Windows4 GB minimum, 8 GB recommended

Memory for a local model

The minimums the Ollama and Hermes Agent docs give for common model sizes, in billions of parameters (B). On an Apple silicon Mac the processor and graphics share one pool of memory, so the Mac's total memory limits the model size. On a PC, a model runs fast only if it fits in the graphics card's own memory.

Model sizeMemory neededDownload
3–4B8 GBabout 2.5 GB
7–8B8 GBabout 5.2 GB
14B16 GBabout 9.3 GB
30B+32 GBabout 19 GB

Sources

Sources for the machines and prices (37)

Questions

  • Prices checked 18 October 2026.
  • Nobody pays to be picked.
  • Setup is booked and paid through Fiverr.
What is a self-hosted AI agent?

An AI agent that runs on a computer you control, such as your own PC, a Mac mini or a rented server, rather than in the agent maker's cloud. OpenClaw, Hermes Agent, Claude Code and Codex can all run this way. The AI model can still be in the cloud.

How much RAM does a self-hosted AI agent need?

With the model in the cloud, 4 GB is the minimum Claude Code and Codex publish, and Codex recommends 8 GB. OpenClaw's gateway alone runs in 1 GB. A local model needs more: about 8 GB for a 7–8B model and 32 GB for a 30B one.

Do I need a Mac mini to run OpenClaw?

No. OpenClaw runs on Linux, Windows and macOS. A Mac mini is worth it for iMessage, which needs macOS, or for running local models in its shared memory. Mac mini for OpenClaw goes through the choice.

Is a rented server (VPS) or a computer at home better?

A server is always on and doesn't touch your home network, but costs about $15–24 a month for 2 processors and 4–8 GB of memory, and your agent and its files live on someone else's computer. A spare computer at home costs under $2 a month in electricity to leave on.

Is it safe to run an AI agent on my own computer?

A separate computer and limited accounts reduce what a mistake or attack can reach; they do not make an agent safe. Anything it reads can try to steer it, and connected accounts still need protection. See Is OpenClaw safe? for risks and precautions.

Do you get paid for these picks?

Links to Amazon can earn me a commission if you buy; it doesn't change your price. Nobody pays to be listed, and Apple and Framework links go straight to the maker and earn nothing. I also sell setup, on Fiverr, which is labelled where it appears.

Why is there no Amazon price next to the button?

Amazon's prices change by the hour, so the button opens the live listing. The price beside each machine is the maker's list price on the date above, or a typical price where there is no list price.

A small black Dell OptiPlex Micro mounted on the back of a monitor standA silver Mac mini on a wooden table
Pictured: a Dell OptiPlex Micro mounted behind a monitor. Inset: a Mac mini (2024 design).
  • Tulsa, Oklahoma
  • Runs agents on five computers
  • About Tyler

Tyler MayberryI'm Tyler Mayberry. I build AI agents and the computers they run on. I run agents on five computers and write about choosing, setting up and maintaining them.

This site answers what people ask before they buy: which machine, what it costs to leave on, and how to keep an agent from doing damage. How it's made, and how it earns money.