OpenClaw System Requirements

At a Glance

RAM — What We Actually Measured

We sampled resident memory across OpenClaw agent containers serving live traffic on three separate hosts. Every container was running the same 2026.7.1 image with a mix of chat channels and skills enabled.

Sample of 19 production containers, measured 17 August 2026. The important shape here is the gap between the median and the 90th percentile: a typical agent sits under 400 MB, but the tail is more than 3× that. Sizing a box at exactly the median is how people end up with an agent the kernel kills mid-conversation.

Practical reading: 1 GB works for a single chat-only agent. 2 GB is the number to pick if you want headroom for the p90 case without thinking about it again.

Node.js Version — Read This Carefully

OpenClaw 2026.7.1 declares a deliberately gapped engine range:

"engines": { "node": ">=22.22.3 <23 || >=24.15.0 <25 || >=25.9.0" }

That is three separate supported windows, and the gaps are intentional:

• Node 22.22.3 up to (not including) 23 — supported
• Node 23.x — not supported at all
• Node 24.15.0 up to (not including) 25 — supported
• Node 25.0 through 25.8 — not supported
• Node 25.9.0 and newer — supported

Node 23 was an odd-numbered non-LTS release, and an install on it fails at the engine check rather than at runtime — which is why the error people hit usually looks like an npm EBADENGINE complaint rather than an OpenClaw error. If your distro ships Node 23, install 24 LTS with nvm instead of forcing the install.

# Check what you have
node -v

# Install a supported LTS
nvm install 24
nvm use 24

CPU

OpenClaw is I/O bound. It spends nearly all of its time waiting on model responses, channel webhooks, and disk. 1 vCPU is genuinely enough for a personal agent. A second core helps when a browser sidecar renders pages or a skill does CPU-heavy parsing (PDF extraction, video, OCR).

Sustained high CPU on an idle agent almost always means a runaway skill or a crash loop, not an undersized box — check logs before upgrading the plan.

Disk

The install itself is modest; the growth comes from state. ~/.openclaw holds config, chat history, embeddings, and workspace files.

• 5 GB — minimum, chat-only, modest history
• 10 GB — comfortable with a browser sidecar and skill data
• 20 GB+ — long chat history, media handling, or a coding workspace

A browser sidecar pulls in Chromium (roughly 400 MB) plus per-session profile data, which is the single largest jump most people hit.

Do You Need a GPU? No.

OpenClaw does not run model inference locally. Model calls go out over HTTPS to whichever provider you configure, so the GPU question simply does not apply. If you want local inference, run Ollama or LM Studio on a separate machine and point OpenClaw at it — the GPU belongs on the inference host, not the agent host.

Operating System Support

• Linux — first-class, x86_64 and arm64. The official container image is Debian 12 based.
• macOS — Intel and Apple Silicon
• Windows — see the Windows 11 install guide; WSL2 is the smoother path
• Docker — works anywhere Docker does; see docker compose
• Raspberry Pi — works on arm64 with 2 GB+; expect slower skill installs

Network

• Outbound 443 to your model provider — required
• Inbound to the gateway port (18789 by default) if you access the web gateway remotely
• Inbound 80/443 if you terminate TLS for channel webhooks

Sizing Cheat Sheet

Skip the Sizing Question

OpenClaw Launch runs OpenClaw on right-sized containers with the supported Node version, browser sidecar, and channel wiring already in place. Compare self-hosting costs in the cheapest OpenClaw hosting guide or see the OpenClaw VPS guide if you would rather run it yourself.