# Self-Host OpenClaw on a Real microVM (BYOK) > Run OpenClaw 24/7 on a real Firecracker microVM and bridge WhatsApp, Telegram, Discord, and Signal to your own LLM key. Auto-provisioned at checkout, 124ms boot, no shared kernel, 30-day money-back. - Published: 2026-06-02 · Updated: 2026-06-02 · jurniti - Canonical: https://www.jurniti.com/blog/openclaw-hosting OpenClaw holds your paired WhatsApp session, your model key, and a license to act on your accounts — and the docs themselves tell you not to run it open to the world on your laptop. So put it on a server. But not a shared container, where one host kernel sits between your bot and every other tenant. Here's how to self-host OpenClaw in its own Firecracker microVM: bridging WhatsApp, Telegram, Discord, and Signal to your own LLM key, running 24/7, provisioned automatically the moment you pay — the microVM boots in 124ms. This guide covers what OpenClaw is, why a dedicated microVM beats your Mac or a shared container, and how to get yours running. ## What OpenClaw is [OpenClaw](/openclaw) is an open-source gateway that connects your messaging apps to an AI agent. You run one gateway process and it becomes the bridge — message it from WhatsApp, Telegram, Discord, or Signal, and it answers in the same thread. It runs tools, browses, automates tasks, and carries the plugin ecosystem the community already builds for. It is **bring-your-own-key**: you connect your own Anthropic, OpenAI, or OpenRouter key. The OpenClaw Foundation stewards the project, and NVIDIA ships a reference deployment of it. The problem with the obvious setup — running it on your laptop — is that laptops sleep. An assistant that triages your messages at 3am can't. So you put it on a server. The question is what kind. ## Why a dedicated microVM, not your Mac or a container The OpenClaw docs themselves warn you: never run it open-to-the-world on your personal machine, and lock down who can message it. That advice exists because you are handing an agent your accounts and credentials. **A shared container means a shared kernel** — over 200 known weaknesses in the container stack, between your paired accounts and every other tenant. That's the wrong trade for a process this privileged. jurniti gives every gateway its **own Firecracker microVM with its own kernel and a KVM hardware boundary** — the isolation primitive that runs serverless platforms at scale, one per tenant, booting in about 124ms. **Bundled "AI credits" — and even most "BYOK" — put a middleman on your keys.** Managed OpenClaw offers pre-load credits so you "don't need an OpenAI or Anthropic account," and charge their margin on every token. Even the common BYOK gateway stores your key and proxies your traffic through it. jurniti's [BYOK](/pricing) is architectural: the key lives only in your VM, model traffic leaves that VM straight to the provider, and jurniti is never in the path. No proxy, no markup. And it stays a reversible decision — a **30-day money-back guarantee**, with your persistent workspace retained for 7 days after cancellation. ## Self-host OpenClaw in 3 steps Doing this by hand means a VPS, Node 22+, a gateway config, a reverse proxy for TLS, and pairing flows you debug over SSH — then patching and restarting it forever. jurniti runs the box ops; you keep the keys to the agent. Here it is in three steps. ### 1. Pick a plan and pay Choose [Starter, Pro, or Max](/pricing) and check out. Payment kicks off the provision chain automatically — no manual setup, no support ticket. ### 2. Your microVM boots and the gateway comes up A fresh Ubuntu microVM boots, the OpenClaw runtime installs, and the gateway comes up. You get an in-browser terminal, so there is nothing to SSH into. On Pro and up, the gateway also gets its own TLS subdomain at `https://.jurniti.com`. Run the guided onboarding to connect your channels and your model key: ```bash openclaw onboard ``` It walks you through pairing WhatsApp (scan a QR), Telegram (bot token), Discord, or Signal, and connecting your BYOK provider. Config lives on your persistent volume. ### 3. Message your assistant Confirm the gateway is up: ```bash openclaw gateway status ``` You should see it listening on port 18789. Now message your paired number (WhatsApp, Telegram, etc.) like any contact — OpenClaw answers in the same thread. Conversations, plugin state, and skills persist across restarts. ## What people run OpenClaw for - **A personal chief of staff.** Connect calendar + messaging; it reschedules meetings and briefs you each morning. - **A sales responder.** It qualifies leads in Telegram, logs contacts, and drafts follow-ups. - **A community moderator.** Route Discord support through it; it handles the routine tickets before a human sees them. - **A cross-platform automator.** One agent reachable from every app you already use, instead of five disconnected bots. You can snapshot a configured gateway into a [template](/templates) and fork it into a second VM for a different number or use case. It's also your safety net before a risky upstream update — OpenClaw has a reputation for breaking on upgrades: snapshot a known-good config first, upgrade, and if it breaks, fork the template back into a clean VM. ## jurniti vs your laptop vs a managed-credits host | | jurniti | Your laptop / Mac | Managed-credits host | |---|---|---|---| | Always on | Yes, 24/7 | No — it sleeps | Yes | | Isolation | Firecracker microVM (KVM) | Your whole machine | Shared container | | Model keys | Yours, never leave the VM | Yours | Bundled + marked up | | Setup | Automatic · 124ms boot | Manual, fiddly | One click | | Persistent workspace | Yes | Yes (on your disk) | Varies | | Refund | 30-day money-back | n/a | Varies | ## Pricing Starter is **$25/mo** ($250/year), Pro **$49/mo** ($490/year), Max **$99/mo** ($990/year) — annual billing is two months free. Every plan has the 30-day money-back guarantee. You bring your own model key, so token spend is separate and never marked up. Running something else? See the guides for [Hermes Agent](/blog/hermes-agent-hosting), [Pi](/blog/pi-coding-agent-hosting), and [Paperclip](/blog/paperclip-hosting), or compare plans on the [pricing page](/pricing). ## Frequently asked questions ### What is OpenClaw? OpenClaw is an open-source, self-hosted gateway that bridges WhatsApp, Telegram, Discord, Signal, and other channels to an AI agent. You run one gateway process and message your assistant from any of those apps. It is bring-your-own-key and stewarded by the OpenClaw Foundation. ### Can I run OpenClaw on a server instead of my laptop? Yes, and you probably should. A laptop sleeps; an assistant that answers your messages around the clock cannot. jurniti runs your OpenClaw gateway on an always-on Firecracker microVM, so it stays online without leaving your machine running. You reach it through the in-browser terminal on every plan, and on Pro and up it gets its own public TLS subdomain. ### Do I need my own API key for OpenClaw? Yes. jurniti is bring-your-own-key — you connect your own Anthropic, OpenAI, or OpenRouter key during onboarding, inside your VM. We never see it and never mark up your token spend. That is different from hosts that bundle AI credits and bill you their margin on every message. ### Is it safe to connect WhatsApp to a hosted agent? Safer on a dedicated microVM than on a shared container. Your gateway, conversations, and paired accounts live on your own isolated instance with a KVM hardware boundary — not in a container sharing a kernel with other tenants. Use a dedicated number for the assistant and restrict who can message it during onboarding. ### How much does OpenClaw hosting cost? Plans start at $25/mo, or $250/year (two months free). Every plan includes a 30-day money-back guarantee. Model spend is separate and unmarked-up because you bring your own key. ### Is this the official OpenClaw product? No. jurniti is independent managed hosting for the open-source OpenClaw runtime. We run the upstream installer at first boot — no fork — so you get the real gateway and the plugin ecosystem you already know.