Pulumi Blog: Tailscale

Deploy a Private Hermes Agent on Render Securely with Pulumi, Modal, and Tailscale

Engin Diri — Wed, 24 Jun 2026 00:00:00 +0000

Personal AI agents had their breakout this year. OpenClaw crossed 100,000 GitHub stars within months of launching, and self-hosting your own assistant went from a hobbyist trick to something a lot of developers actually do. I wrote up how to deploy that lobster to AWS or Hetzner back when it was everywhere.

The one people are switching to now is Hermes, the open-source runtime from Nous Research, and it caught on just as quickly. The reason shows up in every “I ditched OpenClaw for Hermes” thread: it actually learns, building up memory and writing its own skills as it goes instead of running off a static, human-written list.

Here is the part the launch videos skip. Hermes writes and runs its own code, with no human approving the commands. A model that can write code will eventually write a bad one, and the only thing between that command and your credentials is the sandbox it runs in. That is the box you do not want on the public internet. Researchers found 175,000 exposed Ollama servers sitting open in early 2026, and attackers hijack the ones they find for compute. The fix is not a better lock on the front door. It is to have no front door at all.

So this post deploys a private Hermes agent as one Pulumi program across Render, Modal, and Tailscale. The agent and its chat UI run as Render private services with no public URL, Tailscale puts the UI on your tailnet, and Modal runs the agent’s code in throwaway sandboxes. One pulumi up to stand it up, one pulumi destroy to tear it down, around $50 a month. No Makefile, no CLI escape hatches, and an honest look at the few places “nothing on the public internet” still leaks.

What is Hermes?

Hermes is the open-source, MIT-licensed agent runtime from Nous Research. It runs continuously on a server rather than living in a browser tab, and you talk to it through a chat UI or a messaging platform like Telegram, Discord, Slack, or Signal. A few things make it more than a chatbot:

It is model-agnostic. You point it at any provider. This deployment uses OpenRouter, one key that fronts 400-plus models across providers, with automatic failover when one is down.
It remembers across restarts. Memory persists on disk, so it builds up context over time instead of resetting every session.
It writes its own skills. When it works through a task, it can save that approach as a reusable skill and reach for it next time.
It schedules itself. A built-in cron runs automations on a schedule, driven in plain language.
It runs code in a sandbox. When the agent needs to execute code, it hands that off to an isolated, ephemeral container instead of running it next to its own process.

The difference from a cloud-hosted assistant is the usual self-hosting trade: it runs on your infrastructure with your keys, and your conversation history and memory stay on your disk.

“Hermes” here is the agent runtime from Nous Research, not the Hermes family of language models that share the name. The agent is model-agnostic, and the model it talks to is a separate choice you make through OpenRouter.

Prerequisites

Before getting started, ensure you have:

Pulumi CLI installed and configured
A Pulumi Cloud account
A Render account, an API key, and your workspace owner ID
A Modal account and a token pair (token ID and secret)
An OpenRouter API key with credit on the account
A container registry you can push to; this post uses GitHub Container Registry (a GHCR username and token)
Docker running locally (the image build rides on a local buildx engine), or a Docker-enabled CI runner
A Tailscale account with HTTPS enabled and a reusable auth key
Node.js 18+ (for TypeScript) or Python 3.9+ (for Python), depending on the language you pick

This guide routes models through OpenRouter, but Hermes works with other providers too. The model is just a routing string you pass (gpt-5.5 here), so any model OpenRouter supports works by changing that one value.

Understanding the Hermes architecture

Strip away the dashboard clicks and the architecture is four pieces. One rule governs all of them: what the public internet is allowed to touch.

flowchart LR
User([Your devices]) -->|"tailnet (WireGuard)"| TS["Tailscale<br/>private mesh"]
TS -->|"open-webui.&lt;tailnet&gt;.ts.net"| WebUI["Open WebUI<br/>(Render private service,<br/>joined to your tailnet)"]
WebUI -->|"private network<br/>&lt;hermes-slug&gt;:8642"| Hermes["Hermes gateway<br/>(Render private service)"]
Hermes -->|"Modal SDK at runtime"| Modal["Modal sandbox<br/>isolated code execution"]
Hermes -->|model calls| OR["OpenRouter"]

Component	Port	Description
Hermes gateway	8642	Holds secrets and memory, talks to the model, creates Modal sandboxes. The most dangerous box, so it has no public URL.
Open WebUI	8080	The chat front end. Joins your tailnet and reaches Hermes over Render’s private network.
Modal sandbox	-	Isolated, ephemeral container for running the agent’s code.
Tailscale	-	A private WireGuard mesh that makes the UI reachable to your devices only.

The agent that can run code and read secrets is never routable from the internet, and neither is the UI in front of it. There is no inbound ingress on any box (the outbound calls to the model, to Modal, and to the image registry still cross the internet, as they have to). Expressing “which box can reach which” in code is what makes the boundary auditable: the rule lives in the program rather than in a dashboard.

The four pieces split cleanly in two: two you declare as resources, and two you hand a credential and let run.

Layer	How you provision it	Status
Render services, disks, secrets	official `render-oss` Terraform provider, bridged	Declarative, via one `pulumi package add`.
Container images	`@pulumi/docker-build`	Built and pushed during `pulumi up`. No `docker` CLI.
Modal sandboxes	nothing	No Terraform provider exists. A runtime credential.
Tailnet access (Tailscale)	nothing	No provider needed. A runtime credential, like Modal.

Two of these four layers are credentials, not resources. That distinction often gets missed, and it is worth getting right: a provider can only manage what it can provision, and spinning up a Modal sandbox is a runtime act, not a provisioned resource. We come back to it at each layer.

Setting up ESC for secrets management

Deploying Hermes means handling a pile of credentials: a Render API key, registry credentials, the OpenRouter key, the Modal token pair, and the Tailscale auth key. You don’t want these hardcoded or scattered across environment variables. Pulumi ESC (Environments, Secrets, and Configuration) stores them securely and passes them directly to your Pulumi program.

Create a new ESC environment:

pulumi env init <your-org>/hermes-secrets

Add your secrets to the environment:

values:
 renderApiKey:
 fn::secret: "rnd_xxxxx"
 renderOwnerId: "tea-xxxxx"
 ghcrUser: "your-github-username"
 ghcrToken:
 fn::secret: "ghp_xxxxx"
 openrouterApiKey:
 fn::secret: "sk-or-xxxxx"
 modalTokenId:
 fn::secret: "ak-xxxxx"
 modalTokenSecret:
 fn::secret: "as-xxxxx"
 tailscaleAuthKey:
 fn::secret: "tskey-auth-xxxxx"
 tailnetDnsName: "tailxxxxx.ts.net"
 pulumiConfig:
 renderApiKey: ${renderApiKey}
 ownerId: ${renderOwnerId}
 ghcrUser: ${ghcrUser}
 ghcrToken: ${ghcrToken}
 openrouterApiKey: ${openrouterApiKey}
 modalTokenId: ${modalTokenId}
 modalTokenSecret: ${modalTokenSecret}
 tailscaleAuthKey: ${tailscaleAuthKey}
 tailnetDnsName: ${tailnetDnsName}

To find your tailnet DNS name, go to the Tailscale admin console, look under the DNS section, and find your tailnet name (e.g., tailxxxxx.ts.net). This is the domain suffix used for all machines in your Tailscale network.

Then create a Pulumi.dev.yaml file in your project to reference the environment:

environment:
 - <your-org>/hermes-secrets

This keeps your secrets out of your codebase and hands them to the program at deploy time. The Modal token pair and the Tailscale auth key never become resources; they ride straight through as encrypted env vars on the services that need them.

Generating the Render SDK

Render has no first-party Pulumi provider. What it has is an official, maintained Terraform provider, and Pulumi can turn any Terraform provider into a typed local SDK with Any Terraform Provider:

pulumi package add terraform-provider render-oss/render 1.8.0

That one command generates a render SDK you import like any other package, in whatever language your stack is written in. There is no published @pulumi/render package and no vendor to wait on.

This is also where the provider map shows its edges. The bridge wraps a Terraform provider that already exists, so it works for Render. But Modal has no Terraform provider anywhere, so pulumi package add terraform-provider modal-labs/modal has nothing to fetch. That is not a gap to work around. Modal is not a provisioned resource here; Hermes creates sandboxes at runtime through the Modal SDK, and Pulumi’s only job is to hold the token pair and hand it over. Tailscale lands in the same bucket: a Tailscale provider exists, but it manages your tailnet’s settings, not the act of putting a container on the network, which is a runtime job done inside the image.

Securing with Tailscale

The usual way to make a self-hosted UI reachable is to give it a public hostname and put an identity gate in front: an SSO provider, an access policy, a public DNS record, and a certificate to keep renewing. Tailscale collapses all of it into nothing you declare. There is no gate to bolt in front of a public URL, because there is no public URL. Open WebUI joins your tailnet and answers only to your own devices.

This is a stronger position than a public UI behind a login. Because there is no public URL, there is no login to harden and no certificate to renew, and Open WebUI answers only to your own devices.

Tailscale lives in the Open WebUI image rather than the Pulumi program. The image adds Tailscale and an entrypoint that brings up tailscaled in userspace mode (a container has no /dev/net/tun), joins your tailnet, and runs tailscale serve to expose Open WebUI on it. serve publishes over HTTPS to authenticated members of your tailnet only, where its sibling tailscale funnel would put the same port on the public internet, the one thing this design avoids.

FROM ghcr.io/open-webui/open-webui:main-slim
RUN apt-get update && apt-get install -y --no-install-recommends curl ca-certificates \
 && curl -fsSL https://tailscale.com/install.sh | sh
COPY entrypoint.sh /usr/local/bin/ts-entrypoint
ENTRYPOINT ["/usr/local/bin/ts-entrypoint"]

#!/usr/bin/env bash
set -e
PORT="${PORT:-8080}"
mkdir -p /app/backend/data/tailscale
# Userspace networking: a container has no /dev/net/tun. Keep node state on the disk
# so it survives restarts, and accept-dns=false so Render's DNS still resolves the
# private Hermes hostname.
tailscaled --tun=userspace-networking --statedir=/app/backend/data/tailscale &
n=0
until tailscale up --authkey="${TS_AUTHKEY}" --hostname="${TS_HOSTNAME}" --accept-dns=false; do
 n=$((n + 1)); [ "${n}" -ge 30 ] && { echo "tailnet join failed; check TS_AUTHKEY"; exit 1; }
 sleep 2
done
tailscale serve --bg "${PORT}" # serve Open WebUI on the tailnet over HTTPS
cd /app/backend && exec bash start.sh

The TS_AUTHKEY env var on the service, pulled from ESC, is the only thing Pulumi contributes; everything else is the image doing its own networking.

There is one prerequisite, the same one any Tailscale node needs for serve: enable HTTPS for your tailnet once in the admin console so it can get a certificate. Use a reusable auth key, since the service re-authenticates on every redeploy, and the join loop has a ceiling so a dead key fails the deploy in a minute instead of hanging it.

To generate the reusable auth key:

Go to the Tailscale admin console.
Click Generate auth key.
Enable Reusable, since the service re-authenticates on every redeploy.
Copy the key into your ESC environment as tailscaleAuthKey.

Deploying the agent

This is the part a Makefile usually handles. Two private services, two disks, every secret an encrypted env var, and both images built and pushed during the same pulumi up that creates the services. No CLI runs anywhere, though the build still rides on a local Docker engine through buildx: the docker call is gone, the daemon it talks to is not, so pulumi up needs Docker running.

Create a new Pulumi project (pick the language you prefer; the companion repo has all three):

mkdir hermes-agent-pulumi && cd hermes-agent-pulumi
pulumi new typescript

Install the dependencies and generate the Render SDK:

npm install @pulumi/docker-build @pulumi/random
pulumi package add terraform-provider render-oss/render 1.8.0

Both services need the 2 GB Standard plan. The gateway and Open WebUI each exhaust memory on the 512 MB Starter and OOM on boot.

Two facts make this clean. Render env var values are encrypted at rest, so a secret is only an env var, with no separate resource. And @pulumi/docker-build builds and pushes an image through an embedded buildx during pulumi up, so the image pipeline is declarative too. Render then pulls the pushed image by digest.

The complete program

Hermes comes first: a private Render service with no public URL, a disk for its memory, and every secret as an encrypted env var. The shared bearer key is generated in state with random.RandomBytes, the clean replacement for openssl rand -base64 32; the Modal token pair and the OpenRouter key come from config or Pulumi ESC. Render has no port field, so Hermes binds 0.0.0.0:8642 and Open WebUI reaches it at the service’s read-only slug. Open WebUI is almost the mirror image, private too, except its image joins your tailnet (the tailscaled entrypoint from the previous section) and it carries the operational env vars that keep it lean: no local embedding models, and ENABLE_PERSISTENT_CONFIG=false so your config always wins over a stale copy in its database. One render.Provider carries your renderApiKey and ownerId into every Render resource.

Here is the whole program, copy-paste ready as your index.ts (or __main__.py, or Pulumi.yaml):

import * as pulumi from "@pulumi/pulumi";
import * as dockerbuild from "@pulumi/docker-build";
import * as random from "@pulumi/random";
// Local SDK generated by: pulumi package add terraform-provider render-oss/render 1.8.0
// (no @pulumi/render is published; the SDK is bridged from the official Render provider).
import * as render from "@pulumi/render";

const cfg = new pulumi.Config();

// ---------------------------------------------------------------------------
// Configuration. Non-secret values via `pulumi config set`, secrets via
// `pulumi config set --secret` or a Pulumi ESC environment (see README).
// The Render provider reads renderApiKey/renderOwnerId (or RENDER_API_KEY/RENDER_OWNER_ID).
// ---------------------------------------------------------------------------
const region = cfg.get("renderRegion") ?? "oregon";
const modelDefault = cfg.get("modelDefault") ?? "gpt-5.5";

// Container registry the images are pushed to and Render pulls from (GHCR here).
const ghcrUser = cfg.require("ghcrUser");
const ghcrToken = cfg.requireSecret("ghcrToken"); // GHCR PAT with write:packages

// Long-lived secrets supplied by you (dashboard-minted). Hold in config or ESC.
const modalTokenId = cfg.requireSecret("modalTokenId");
const modalTokenSecret = cfg.requireSecret("modalTokenSecret");
const openrouterApiKey = cfg.requireSecret("openrouterApiKey");

// Tailscale: the only "gateway". Open WebUI joins your tailnet and is reachable
// at https://<hostname>.<tailnet>.ts.net by your devices only — never public.
// Both values are already in your ESC. Enable HTTPS once in the Tailscale admin console.
const tailscaleAuthKey = cfg.requireSecret("tailscaleAuthKey");
const tailnetDnsName = cfg.require("tailnetDnsName"); // e.g. tailc6fb4e.ts.net
const webuiHostname = "open-webui";
const webuiTailnetUrl = `https://${webuiHostname}.${tailnetDnsName}`;

// Render provider auth (from ESC: pulumiConfig.renderApiKey / pulumiConfig.renderOwnerId).
const renderProvider = new render.Provider("render", {
 apiKey: cfg.requireSecret("renderApiKey"),
 ownerId: cfg.require("renderOwnerId"),
});

// ---------------------------------------------------------------------------
// Secrets generated in state (the in-IaC replacement for `openssl rand -base64 32`).
// The shared bearer authenticates Open WebUI -> Hermes; it lands on both services.
// ---------------------------------------------------------------------------
const sharedKey = new random.RandomBytes("hermes-shared-key", { length: 32 });
const webuiSecretKey = new random.RandomBytes("webui-secret-key", { length: 32 });

// ---------------------------------------------------------------------------
// Build and push both images during `pulumi up` (no docker CLI; the provider
// embeds buildx). Render then pulls them by their digest-pinned ref.
// ---------------------------------------------------------------------------
const registryAuth = [{ address: "ghcr.io", username: ghcrUser, password: ghcrToken }];

const hermesImage = new dockerbuild.Image("hermes-image", {
 context: { location: "./hermes" },
 dockerfile: { location: "./hermes/Dockerfile" },
 platforms: ["linux/amd64"],
 tags: [pulumi.interpolate`ghcr.io/${ghcrUser}/hermes-agent:latest`],
 push: true,
 registries: registryAuth,
});

const webuiImage = new dockerbuild.Image("webui-image", {
 context: { location: "./openwebui" },
 dockerfile: { location: "./openwebui/Dockerfile" },
 platforms: ["linux/amd64"],
 tags: [pulumi.interpolate`ghcr.io/${ghcrUser}/open-webui:latest`],
 push: true,
 registries: registryAuth,
});

// Credential Render uses to pull the private GHCR images.
const ghcrCredential = new render.RegistryCredential("ghcr", {
 name: "ghcr",
 registry: "GITHUB",
 username: ghcrUser,
 authToken: ghcrToken,
}, { provider: renderProvider });

// ---------------------------------------------------------------------------
// Hermes: a PRIVATE Render service. No public URL; reachable only over Render's
// private network. A disk holds its memory and workspace. Env values are
// encrypted at rest, which is how secrets ride on Render (no separate flag).
// ---------------------------------------------------------------------------
const hermes = new render.PrivateService("hermes-agent", {
 name: "hermes-agent",
 plan: "standard", // 2 GB; the gateway OOMs on starter's 512 MB
 region: region,
 runtimeSource: {
 // Render wants the bare repo in imageUrl; the tag/digest go in their own field.
 image: {
 imageUrl: pulumi.interpolate`ghcr.io/${ghcrUser}/hermes-agent`,
 digest: hermesImage.digest,
 registryCredentialId: ghcrCredential.id,
 },
 },
 disk: { name: "hermes-data", mountPath: "/opt/data", sizeGb: 5 },
 envVars: {
 PORT: { value: "8642" },
 API_SERVER_ENABLED: { value: "true" },
 API_SERVER_HOST: { value: "0.0.0.0" },
 API_SERVER_PORT: { value: "8642" },
 API_SERVER_MODEL_NAME: { value: modelDefault },
 // Auto-approve the agent's shell/terminal hooks (no TTY in a container),
 // so it can run code in the Modal sandbox without an interactive prompt.
 HERMES_ACCEPT_HOOKS: { value: "1" },
 // Secrets (encrypted at rest on Render):
 API_SERVER_KEY: { value: sharedKey.base64 },
 OPENROUTER_API_KEY: { value: openrouterApiKey },
 // Modal is a runtime credential, not a provisioned resource: Hermes creates
 // sandboxes at runtime with this token pair. No Modal provider, no Modal CLI.
 MODAL_TOKEN_ID: { value: modalTokenId },
 MODAL_TOKEN_SECRET: { value: modalTokenSecret },
 },
}, { provider: renderProvider });

// Open WebUI reaches Hermes at its Render-assigned internal hostname (the read-only
// slug), not the bare service name. Same region + same workspace share the network.
const hermesApiBaseUrl = pulumi.interpolate`http://${hermes.slug}:8642/v1`;

// ---------------------------------------------------------------------------
// Open WebUI: also a PRIVATE Render service, but the container joins your tailnet
// (tailscaled in userspace + `tailscale serve`), so you reach it at
// https://open-webui.<tailnet>.ts.net from your devices. Never public; the gate
// is tailnet membership. It still reaches Hermes over Render's private network.
// ---------------------------------------------------------------------------
const webui = new render.PrivateService("open-webui", {
 name: "open-webui",
 plan: "standard", // 2 GB; Open WebUI OOMs on starter's 512 MB
 region: region, // must match Hermes for private networking
 runtimeSource: {
 image: {
 imageUrl: pulumi.interpolate`ghcr.io/${ghcrUser}/open-webui`,
 digest: webuiImage.digest,
 registryCredentialId: ghcrCredential.id,
 },
 },
 disk: { name: "openwebui-data", mountPath: "/app/backend/data", sizeGb: 5 },
 envVars: {
 PORT: { value: "8080" }, // tailscale serve points at this; Open WebUI binds it
 OPENAI_API_BASE_URL: { value: hermesApiBaseUrl },
 ENABLE_OPENAI_API: { value: "true" },
 ENABLE_OLLAMA_API: { value: "false" },
 DEFAULT_MODELS: { value: modelDefault },
 WEBUI_AUTH: { value: "true" },
 WEBUI_URL: { value: webuiTailnetUrl },
 // Reached only over the tailnet, so the first sign-up is the admin.
 ENABLE_LOGIN_FORM: { value: "true" },
 ENABLE_SIGNUP: { value: "true" },
 DEFAULT_USER_ROLE: { value: "admin" },
 // Always apply env config; otherwise Open WebUI persists the first run's config
 // to its DB and ignores later changes.
 ENABLE_PERSISTENT_CONFIG: { value: "false" },
 // Don't load local embedding/RAG models (a big memory saver; the agent is the brain).
 RAG_EMBEDDING_ENGINE: { value: "openai" },
 BYPASS_EMBEDDING_AND_RETRIEVAL: { value: "true" },
 OFFLINE_MODE: { value: "true" },
 HF_HUB_OFFLINE: { value: "1" },
 // Secrets (encrypted at rest):
 OPENAI_API_KEY: { value: sharedKey.base64 }, // shared bearer to call Hermes
 WEBUI_SECRET_KEY: { value: webuiSecretKey.base64 },
 // Tailscale joins this container to your tailnet and serves Open WebUI on it.
 TS_AUTHKEY: { value: tailscaleAuthKey },
 TS_HOSTNAME: { value: webuiHostname },
 },
}, { dependsOn: hermes, provider: renderProvider });

export const hermesInternalUrl = hermesApiBaseUrl;
// Open this from any device on your tailnet:
export const openWebUiTailnetUrl = webuiTailnetUrl;

import pulumi
import pulumi_docker_build as docker_build
import pulumi_random as random

# Local SDK generated by: pulumi package add terraform-provider render-oss/render 1.8.0
# (no pulumi_render is published; the SDK is bridged from the official Render provider).
import pulumi_render as render

cfg = pulumi.Config()

# ---------------------------------------------------------------------------
# Configuration. Non-secret values via `pulumi config set`, secrets via
# `pulumi config set --secret` or a Pulumi ESC environment (see README).
# The Render provider reads renderApiKey/renderOwnerId (or RENDER_API_KEY/RENDER_OWNER_ID).
# ---------------------------------------------------------------------------
region = cfg.get("renderRegion") or "oregon"
model_default = cfg.get("modelDefault") or "gpt-5.5"

# Container registry the images are pushed to and Render pulls from (GHCR here).
ghcr_user = cfg.require("ghcrUser")
ghcr_token = cfg.require_secret("ghcrToken") # GHCR PAT with write:packages

# Long-lived secrets supplied by you (dashboard-minted). Hold in config or ESC.
modal_token_id = cfg.require_secret("modalTokenId")
modal_token_secret = cfg.require_secret("modalTokenSecret")
openrouter_api_key = cfg.require_secret("openrouterApiKey")

# Tailscale: the only "gateway". Open WebUI joins your tailnet and is reachable
# at https://<hostname>.<tailnet>.ts.net by your devices only -- never public.
# Enable HTTPS once in the Tailscale admin console so `tailscale serve` can get a cert.
tailscale_auth_key = cfg.require_secret("tailscaleAuthKey")
tailnet_dns_name = cfg.require("tailnetDnsName") # e.g. tailc6fb4e.ts.net
webui_hostname = "open-webui"
webui_tailnet_url = f"https://{webui_hostname}.{tailnet_dns_name}"

# Render provider auth (from ESC: pulumiConfig.renderApiKey / pulumiConfig.renderOwnerId).
render_provider = render.Provider(
 "render",
 api_key=cfg.require_secret("renderApiKey"),
 owner_id=cfg.require("renderOwnerId"),
)

# ---------------------------------------------------------------------------
# Secrets generated in state (the in-IaC replacement for `openssl rand -base64 32`).
# The shared bearer authenticates Open WebUI -> Hermes; it lands on both services.
# ---------------------------------------------------------------------------
shared_key = random.RandomBytes("hermes-shared-key", length=32)
webui_secret_key = random.RandomBytes("webui-secret-key", length=32)

# ---------------------------------------------------------------------------
# Build and push both images during `pulumi up` (no docker CLI; the provider
# embeds buildx). Render then pulls them by their digest-pinned ref.
# ---------------------------------------------------------------------------
registry_auth = [{"address": "ghcr.io", "username": ghcr_user, "password": ghcr_token}]

hermes_image = docker_build.Image(
 "hermes-image",
 context={"location": "./hermes"},
 dockerfile={"location": "./hermes/Dockerfile"},
 platforms=["linux/amd64"],
 tags=[pulumi.Output.concat("ghcr.io/", ghcr_user, "/hermes-agent:latest")],
 push=True,
 registries=registry_auth,
)

webui_image = docker_build.Image(
 "webui-image",
 context={"location": "./openwebui"},
 dockerfile={"location": "./openwebui/Dockerfile"},
 platforms=["linux/amd64"],
 tags=[pulumi.Output.concat("ghcr.io/", ghcr_user, "/open-webui:latest")],
 push=True,
 registries=registry_auth,
)

# Credential Render uses to pull the private GHCR images.
ghcr_credential = render.RegistryCredential(
 "ghcr",
 name="ghcr",
 registry="GITHUB",
 username=ghcr_user,
 auth_token=ghcr_token,
 opts=pulumi.ResourceOptions(provider=render_provider),
)

# ---------------------------------------------------------------------------
# Hermes: a PRIVATE Render service. No public URL; reachable only over Render's
# private network. A disk holds its memory and workspace. Env values are
# encrypted at rest, which is how secrets ride on Render (no separate flag).
# ---------------------------------------------------------------------------
hermes = render.PrivateService(
 "hermes-agent",
 name="hermes-agent",
 plan="standard", # 2 GB; the gateway OOMs on starter's 512 MB
 region=region,
 runtime_source={
 "image": {
 "image_url": pulumi.Output.concat("ghcr.io/", ghcr_user, "/hermes-agent"),
 "digest": hermes_image.digest,
 "registry_credential_id": ghcr_credential.id,
 },
 },
 disk={"name": "hermes-data", "mount_path": "/opt/data", "size_gb": 5},
 env_vars={
 "PORT": {"value": "8642"},
 "API_SERVER_ENABLED": {"value": "true"},
 "API_SERVER_HOST": {"value": "0.0.0.0"},
 "API_SERVER_PORT": {"value": "8642"},
 "API_SERVER_MODEL_NAME": {"value": model_default},
 # Auto-approve the agent's shell/terminal hooks (no TTY in a container).
 "HERMES_ACCEPT_HOOKS": {"value": "1"},
 # Secrets (encrypted at rest on Render):
 "API_SERVER_KEY": {"value": shared_key.base64},
 "OPENROUTER_API_KEY": {"value": openrouter_api_key},
 # Modal is a runtime credential: Hermes creates sandboxes at runtime with this pair.
 "MODAL_TOKEN_ID": {"value": modal_token_id},
 "MODAL_TOKEN_SECRET": {"value": modal_token_secret},
 },
 opts=pulumi.ResourceOptions(provider=render_provider),
)

# Open WebUI reaches Hermes at its Render-assigned internal hostname (the read-only slug).
hermes_api_base_url = pulumi.Output.concat("http://", hermes.slug, ":8642/v1")

# ---------------------------------------------------------------------------
# Open WebUI: also a PRIVATE Render service, but the container joins your tailnet
# (tailscaled in userspace + `tailscale serve`), so you reach it at
# https://open-webui.<tailnet>.ts.net from your devices. Never public.
# ---------------------------------------------------------------------------
webui = render.PrivateService(
 "open-webui",
 name="open-webui",
 plan="standard", # 2 GB; Open WebUI OOMs on starter's 512 MB
 region=region, # must match Hermes for private networking
 runtime_source={
 "image": {
 "image_url": pulumi.Output.concat("ghcr.io/", ghcr_user, "/open-webui"),
 "digest": webui_image.digest,
 "registry_credential_id": ghcr_credential.id,
 },
 },
 disk={"name": "openwebui-data", "mount_path": "/app/backend/data", "size_gb": 5},
 env_vars={
 "PORT": {"value": "8080"}, # tailscale serve points at this; Open WebUI binds it
 "OPENAI_API_BASE_URL": {"value": hermes_api_base_url},
 "ENABLE_OPENAI_API": {"value": "true"},
 "ENABLE_OLLAMA_API": {"value": "false"},
 "DEFAULT_MODELS": {"value": model_default},
 "WEBUI_AUTH": {"value": "true"},
 "WEBUI_URL": {"value": webui_tailnet_url},
 # Reached only over the tailnet, so the first sign-up is the admin.
 "ENABLE_LOGIN_FORM": {"value": "true"},
 "ENABLE_SIGNUP": {"value": "true"},
 "DEFAULT_USER_ROLE": {"value": "admin"},
 # Always apply env config; otherwise Open WebUI persists the first run's config.
 "ENABLE_PERSISTENT_CONFIG": {"value": "false"},
 # Don't load local embedding/RAG models (a big memory saver; the agent is the brain).
 "RAG_EMBEDDING_ENGINE": {"value": "openai"},
 "BYPASS_EMBEDDING_AND_RETRIEVAL": {"value": "true"},
 "OFFLINE_MODE": {"value": "true"},
 "HF_HUB_OFFLINE": {"value": "1"},
 # Secrets (encrypted at rest):
 "OPENAI_API_KEY": {"value": shared_key.base64},
 "WEBUI_SECRET_KEY": {"value": webui_secret_key.base64},
 # Tailscale joins this container to your tailnet and serves Open WebUI on it.
 "TS_AUTHKEY": {"value": tailscale_auth_key},
 "TS_HOSTNAME": {"value": webui_hostname},
 },
 opts=pulumi.ResourceOptions(depends_on=[hermes], provider=render_provider),
)

pulumi.export("hermesInternalUrl", hermes_api_base_url)
# Open this from any device on your tailnet:
pulumi.export("openWebUiTailnetUrl", webui_tailnet_url)

name: hermes-agent-pulumi
runtime: yaml
description: Deploy a Hermes agent (Render + Modal + Tailscale) as one declarative Pulumi program.

# The Render SDK is bridged from the official Terraform provider. Run once:
# pulumi package add terraform-provider render-oss/render 1.8.0
# Then `pulumi install` regenerates it on a fresh checkout.
packages:
 render:
 source: terraform-provider
 version: 1.1.4
 parameters:
 - render-oss/render
 - 1.8.0

config:
 renderRegion:
 type: string
 default: oregon
 modelDefault:
 type: string
 default: gpt-5.5
 ghcrUser:
 type: string
 ghcrToken:
 type: string
 secret: true
 modalTokenId:
 type: string
 secret: true
 modalTokenSecret:
 type: string
 secret: true
 openrouterApiKey:
 type: string
 secret: true
 tailscaleAuthKey:
 type: string
 secret: true
 tailnetDnsName:
 type: string
 renderApiKey:
 type: string
 secret: true
 renderOwnerId:
 type: string

variables:
 registryAuth:
 - address: ghcr.io
 username: ${ghcrUser}
 password: ${ghcrToken}
 # Open WebUI reaches Hermes at its private slug; you reach Open WebUI on the tailnet.
 hermesApiBaseUrl: http://${hermes-agent.slug}:8642/v1
 webuiTailnetUrl: https://open-webui.${tailnetDnsName}

resources:
 # Render provider auth (from config or ESC).
 render:
 type: pulumi:providers:render
 properties:
 apiKey: ${renderApiKey}
 ownerId: ${renderOwnerId}

 # Secrets generated in state: the replacement for `openssl rand -base64 32`.
 hermes-shared-key:
 type: random:RandomBytes
 properties:
 length: 32
 webui-secret-key:
 type: random:RandomBytes
 properties:
 length: 32

 # Build + push both images during `pulumi up` (no docker CLI).
 hermes-image:
 type: docker-build:Image
 properties:
 context:
 location: ./hermes
 dockerfile:
 location: ./hermes/Dockerfile
 platforms: [linux/amd64]
 tags:
 - ghcr.io/${ghcrUser}/hermes-agent:latest
 push: true
 registries: ${registryAuth}
 webui-image:
 type: docker-build:Image
 properties:
 context:
 location: ./openwebui
 dockerfile:
 location: ./openwebui/Dockerfile
 platforms: [linux/amd64]
 tags:
 - ghcr.io/${ghcrUser}/open-webui:latest
 push: true
 registries: ${registryAuth}

 # Credential Render uses to pull the private GHCR images.
 ghcr:
 type: render:RegistryCredential
 properties:
 name: ghcr
 registry: GITHUB
 username: ${ghcrUser}
 authToken: ${ghcrToken}
 options:
 provider: ${render}

 # Hermes: a PRIVATE Render service. No public URL; encrypted env vars are the secret mechanism.
 hermes-agent:
 type: render:PrivateService
 properties:
 name: hermes-agent
 plan: standard  # 2 GB; the gateway OOMs on starter's 512 MB
 region: ${renderRegion}
 runtimeSource:
 image:
 imageUrl: ghcr.io/${ghcrUser}/hermes-agent
 digest: ${hermes-image.digest}
 registryCredentialId: ${ghcr.id}
 disk:
 name: hermes-data
 mountPath: /opt/data
 sizeGb: 5
 envVars:
 PORT: { value: "8642" }
 API_SERVER_ENABLED: { value: "true" }
 API_SERVER_HOST: { value: "0.0.0.0" }
 API_SERVER_PORT: { value: "8642" }
 API_SERVER_MODEL_NAME: { value: "${modelDefault}" }
 HERMES_ACCEPT_HOOKS: { value: "1" }
 API_SERVER_KEY: { value: "${hermes-shared-key.base64}" }
 OPENROUTER_API_KEY: { value: "${openrouterApiKey}" }
 MODAL_TOKEN_ID: { value: "${modalTokenId}" }
 MODAL_TOKEN_SECRET: { value: "${modalTokenSecret}" }
 options:
 provider: ${render}

 # Open WebUI: also a PRIVATE Render service, joined to your tailnet by its image.
 open-webui:
 type: render:PrivateService
 properties:
 name: open-webui
 plan: standard  # 2 GB; Open WebUI OOMs on starter's 512 MB
 region: ${renderRegion}  # must match Hermes for private networking
 runtimeSource:
 image:
 imageUrl: ghcr.io/${ghcrUser}/open-webui
 digest: ${webui-image.digest}
 registryCredentialId: ${ghcr.id}
 disk:
 name: openwebui-data
 mountPath: /app/backend/data
 sizeGb: 5
 envVars:
 PORT: { value: "8080" }
 OPENAI_API_BASE_URL: { value: "${hermesApiBaseUrl}" }
 ENABLE_OPENAI_API: { value: "true" }
 ENABLE_OLLAMA_API: { value: "false" }
 DEFAULT_MODELS: { value: "${modelDefault}" }
 WEBUI_AUTH: { value: "true" }
 WEBUI_URL: { value: "${webuiTailnetUrl}" }
 ENABLE_LOGIN_FORM: { value: "true" }
 ENABLE_SIGNUP: { value: "true" }
 DEFAULT_USER_ROLE: { value: "admin" }
 ENABLE_PERSISTENT_CONFIG: { value: "false" }
 RAG_EMBEDDING_ENGINE: { value: "openai" }
 BYPASS_EMBEDDING_AND_RETRIEVAL: { value: "true" }
 OFFLINE_MODE: { value: "true" }
 HF_HUB_OFFLINE: { value: "1" }
 OPENAI_API_KEY: { value: "${hermes-shared-key.base64}" }
 WEBUI_SECRET_KEY: { value: "${webui-secret-key.base64}" }
 TS_AUTHKEY: { value: "${tailscaleAuthKey}" }
 TS_HOSTNAME: { value: "open-webui" }
 options:
 provider: ${render}
 dependsOn:
 - ${hermes-agent}

outputs:
 hermesInternalUrl: ${hermesApiBaseUrl}
 # Open this from any device on your tailnet:
 openWebUiTailnetUrl: ${webuiTailnetUrl}

Neither box is published to the internet. The same code, plus the Dockerfiles and the Tailscale entrypoint, is in the companion repo:

github.com/dirien/hermes-agent-pulumi

Cost

Two details shape the bill. The host starts on Render’s free Hobby workspace, but a private service with a persistent disk runs on paid compute, so you need a card on file the moment you add them. There is no free-tier version of this architecture. Both services also need the 2 GB Standard plan, since the gateway and Open WebUI each OOM on the 512 MB Starter.

	Hermes gateway	Open WebUI
Plan	Standard (2 GB)	Standard (2 GB)
Compute	~$25/mo	~$25/mo
Disk	5 GB	5 GB
Public URL	none	none (tailnet only)

That lands the host around $50/month, in line with what a comparable managed setup runs. Modal and OpenRouter bill by usage on top, so the total tracks how hard the agent works rather than a flat number. Tailscale is free for a personal tailnet, so the private gateway adds nothing to that.

The persistent disk pins each service to a single instance, so there is no autoscaling, and a redeploy drops a few seconds of connectivity while the old instance lets go of the disk. For a single-user agent that is a fine trade, and it is why “stand it up in a second region” is a copy-the-config move and not a live failover.

The OpenRouter Activity dashboard: 56 requests and 738K tokens of gpt-5.5 usage, all routed through one key.

Running the deployment

With your ESC environment referenced in Pulumi.dev.yaml, deploy with:

pulumi up

This generates the Render SDK’s resources, builds and pushes both images through buildx, and creates the two private services with their disks and encrypted env vars, all in one run, with no docker CLI and no secret import hiding in a script. When it finishes, both services show up in the Render dashboard with no public URL.

The hermes-agent and open-webui private services in the Render dashboard, both deployed with no public URL.

Access the agent

Give it a few minutes after pulumi up finishes. The images still have to be pulled and the containers booted, and Open WebUI has to join your tailnet before the URL resolves. Refresh until it loads.

Open WebUI is reachable only from a device on your tailnet, at https://open-webui.<your-tailnet>.ts.net, with no domain to buy, no DNS to point, and no certificate to manage. Open it, sign up so the first account becomes the admin, and ask the agent to run a Python command. It should fire up a Modal sandbox and return the result, with nothing exposed to the public internet at any point.

Open WebUI on the tailnet URL: the gpt-5.5 agent runs sum(i*i for i in range(1, 1001)) in a Modal sandbox and returns 333833500.

When the agent runs that code, Modal builds a throwaway sandbox specifically for it. There is no Modal resource to declare, no Modal CLI to call, and no Modal provider to bridge. The Hermes service carries MODAL_TOKEN_ID and MODAL_TOKEN_SECRET as two encrypted env vars, and that is the whole footprint.

The Modal dashboard: the per-task sandboxes the Hermes agent spun up at runtime to execute code.

Verify the deployment (optional)

If the chat UI does not load, give the services a few minutes to finish their first boot, then check two things:

Render dashboard logs for the hermes-agent and open-webui services, to confirm both started and pulled their images.
Tailscale admin console (Machines), to confirm the open-webui node joined your tailnet. If it did not, the TS_AUTHKEY is likely expired or not reusable.

Keep your AI agent private

Deploy your Hermes agent across Render, Modal, and Tailscale as one Pulumi program, with secrets held in Pulumi ESC and nothing exposed to the public internet.

Get started

Security considerations

Self-hosted AI servers get found fast: scanners like Shodan and Censys enumerate a freshly exposed one within hours to days, and the code-capable ones are already under active attack. Running an always-on agent on a machine you also use for everything else invites prompt injection on top of that. The answer here is to keep the agent unroutable from the internet and to isolate the code it runs. That defeats the scanner: nobody finds an open port to attack. It does less against the agent being turned against you from the inside, which is the harder problem.

One detail makes that isolation essential. In a headless container there is no one at the terminal to approve anything, and the same is true of its cron and CI runs, so the deployment runs Hermes with HERMES_ACCEPT_HOOKS=1 to auto-accept the shell hooks it would otherwise pause on. The practical result is that the agent’s code runs with no human in the loop, which is exactly why the Modal sandbox has to carry the weight: when the model writes a bad command, the throwaway container it runs in is what stands between that command and the gateway’s credentials, not a confirmation prompt.

Concern	Typical self-host	This deployment
Gateway reachability	Public port, or behind a login	Private service, no public URL
Chat UI reachability	Public hostname + auth	Tailnet only (`tailscale serve`)
Code execution	Runs next to the gateway	Isolated Modal sandbox, torn down after
Command approval	Human approves dangerous commands	Headless: isolation replaces the prompt
Secrets in transit	Exposed if accessed over HTTP	Encrypted env vars; tailnet-encrypted access

This is private, which is not the same as fully trusted. A few places the boundary still leaks:

The shared bearer never rotates. Hermes is unroutable from the internet, but it is wide open to Open WebUI, and the two share one static bearer key. Whoever owns the front end owns the gateway behind it. Rotate it periodically.
The tailnet policy is click-ops. The ACLs, the node’s tags, and the one-time HTTPS toggle live in the Tailscale admin console, not in pulumi up, and the reusable key has no tag scoping its blast radius. The Tailscale provider can manage that policy declaratively if you want it in code.
Signup defaults to admin. Fine on a single-user tailnet, the first thing to lock down (ENABLE_SIGNUP, DEFAULT_USER_ROLE) once more than one person can reach the URL.
Every messaging client is another entry point. Each platform you wire up adds another way in, which is why the tailnet is the baseline for securing this, not the full extent of it.
A compromised agent can still reach out. The private core stops external discovery, but it does not contain the agent itself. The gateway holds the Modal and OpenRouter tokens as env vars and can call out freely, so a prompt-injected agent could read its own environment and send them somewhere; the Modal sandbox isolates the code the agent runs, not the credentials it holds. Cap and rotate the OpenRouter key, keep the Modal token off the gateway, and allowlist outbound traffic, which on Render means a forward-proxy sidecar (Render gives you dedicated outbound IPs and inbound rules, but no destination egress filter).

My recommendations:

Keep both services private; never give Hermes a public URL
Run code in Modal sandboxes, since HERMES_ACCEPT_HOOKS=1 means no human approves commands
Rotate the shared bearer key and the Tailscale auth key periodically
Cap and rotate the OpenRouter key; a leaked credential is the likelier failure mode than an open port
Use Pulumi ESC for secrets instead of hardcoding
Lock down Open WebUI signup once more than one person can reach it
Manage Tailscale ACLs and tags deliberately, in the admin console or with the Tailscale provider

What’s next?

The deployment is the foundation the agent builds on. A private agent becomes useful when it remembers earlier context, runs code without a human at the terminal, and initiates contact on its own. The disk is what makes this persist: its memory and its schedule live on that disk, so they survive every restart.

It schedules itself. Hermes ships a first-class cron you drive in plain language, either by asking the agent in the chat window or through its CLI. The schedule takes intervals, five-field cron, or one-shots:

hermes cron create "every 1h" \
 "Scrape <listing-url> for the price, compare it with seen.json in the sandbox, message me on Telegram only if it dropped, and otherwise reply exactly [SILENT]." \
 --deliver telegram

The [SILENT] reply suppresses delivery when nothing changed, so the watcher only speaks up when there is something to say. Scheduled runs skip memory by default, so polling does not pollute what the agent has learned.

It connects where you work, with the same secret pattern. Messaging clients attach to the same gateway, and their tokens ride as encrypted env vars on the Hermes service, the exact shape you used for the Modal pair:

// alongside MODAL_TOKEN_ID on the hermes service:
TELEGRAM_BOT_TOKEN: { value: cfg.requireSecret("telegramBotToken") },

plus a platform block you add to config.yaml (the image ships only the model and terminal blocks; Hermes supports the messaging platforms on top, per its docs):

gateway:
 platforms:
 telegram:
 require_mention: true

With those two pieces, a few things are genuinely doable today:

A price or uptime watcher that only speaks up when something changed, using the [SILENT] and persistent-sandbox dedup pattern above.
A daily briefing that ranks and dedups your feeds and delivers the top items each morning, the documented daily-briefing bot. If you want it to adapt to your taste over time, that is the optional Honcho memory provider’s job; it reads your preferences out of the conversation itself. The built-in file memory has no version of that.
A PR-review teammate that reviews open pull requests against your repo’s AGENTS.md conventions and saves recurring patterns as a skill, so the fifth review needs less hand-holding than the first.

A few limits are worth stating plainly, since demos tend to overstate the capabilities. Hermes does not ship Gmail, Calendar, or market integrations out of the box; those are wired up as MCP servers or skills, which is more work than a launch video implies. It curates its own memory and improves its own skills, but it does not retrain the underlying model or autonomously change its high-level strategy, so “self-learning” here means whatever it writes into memory and skills each run.

Conclusion

Deploying a Hermes agent with infrastructure as code means you can reproduce the setup anytime, version control it, and tear it down with a single pulumi destroy. Keeping both services private, with no public URL and no exposed ports, means the code-executing core never sits on the internet for someone to find.

The part worth carrying to the next service you deploy: not every layer has a provider, and that is fine. The task is to tell a real resource apart from a runtime dependency wearing a costume. Render and the images are resources you declare; Modal and Tailscale are credentials you hand over. Draw that map first, and the program follows from it.

To generate that map instead of writing it by hand, Pulumi Neo can take a target architecture like this one and produce a first draft of the program. The agent side of this shift is covered in How Building AI Agents Has Changed in 2026 and the platform side in Agent Sprawl Is Here. Your IaC Platform Is the Answer..

If you run into issues or have questions, drop by the Pulumi Community Slack or GitHub Discussions. New to Pulumi? Get started here.

Use Your Mac for AI Agents: Self-Host Gemma 4 12 B with Pulumi and Tailscale

Pablo Seibelt — Thu, 04 Jun 2026 00:00:00 +0000

If you run AI tools and agents, you’ve probably accepted three tradeoffs: your data leaves your network, you can’t work offline, and your bill scales with usage.

Open-weight models now run well on consumer hardware. Once the model is on your machine, your data stays local, inference works offline, and tokens cost nothing. If you own a modern Mac, you can run a high-quality model yourself.

Gemma 4 is an open-weights model family from Google. This post focuses on Gemma 4 12 B, released in June 2026, using Unsloth’s Q8_0 GGUF. The 12 B model fits comfortably on a modern Mac while leaving enough headroom for local llama.cpp and a chat UI.

We’ll use llama.cpp for host-native inference, k3d for a local Kubernetes cluster, Pulumi for infrastructure as code, and Tailscale for secure access.

Prerequisites

This setup was validated on the following hardware:

macOS 26 Tahoe, version 26.5
MacBook Pro with Apple M3 Max
36 GB RAM

On this machine, llama.cpp reported about 20 output tokens per second for a 160-token validation response with unsloth/gemma-4-12b-it-GGUF, gemma-4-12b-it-Q8_0.gguf, and a 131,072-token context. Sustained throughput varies by prompt length, thermal state, and llama.cpp settings.

You’ll need brew, docker, pulumi, and tailscale installed. We’ll also install k3d during the process.

Run Gemma 4 with host-native llama.cpp

We use llama.cpp directly on macOS to leverage Apple Metal acceleration. Running the LLM on the host is more efficient than trying to pass GPU access into a local Kubernetes VM.

Install the build tools:

brew install cmake git

Then build llama.cpp from source and download the multimodal projector. In validation, Homebrew llama.cpp 9430 could run text inference, but it could not load the new Gemma 4 12 B projector and failed with unknown projector type: gemma4uv. Building current llama.cpp from source fixed that.

llm_home="$HOME/pulumi-gemma4-llm"
mkdir -p "$llm_home/models" "$llm_home/logs"

if [ ! -d "$llm_home/llama.cpp/.git" ]; then
 git clone --depth 1 https://github.com/ggml-org/llama.cpp.git "$llm_home/llama.cpp"
fi

cmake -S "$llm_home/llama.cpp" \
 -B "$llm_home/llama.cpp/build" \
 -DGGML_METAL=ON \
 -DGGML_BLAS=ON \
 -DCMAKE_BUILD_TYPE=Release

cmake --build "$llm_home/llama.cpp/build" --target llama-server -j 10

curl -L --fail \
 --output "$llm_home/models/mmproj-F16.gguf" \
 https://huggingface.co/unsloth/gemma-4-12b-it-GGUF/resolve/main/mmproj-F16.gguf

Then download and run the model with this command:

"$HOME/pulumi-gemma4-llm/llama.cpp/build/bin/llama-server" \
 --hf-repo unsloth/gemma-4-12b-it-GGUF \
 --hf-file gemma-4-12b-it-Q8_0.gguf \
 --mmproj "$HOME/pulumi-gemma4-llm/models/mmproj-F16.gguf" \
 --host 127.0.0.1 \
 --port 18080 \
 --ctx-size 131072 \
 --parallel 1 \
 --jinja \
 --reasoning off

We use port 18080 because 8080 is commonly used and is likely to conflict with another service you may already have running locally. If your port 8080 is free, you can use it and adjust the Pulumi config later.

The model file is about 12.65 GB, and the projector is about 116 MB. Gemma 4 12 B advertises a 131,072-token context, and this Mac loaded that full context with --parallel 1. llama.cpp projected about 15.1 GiB of Apple Metal device memory for the text model and about 258 MiB worst-case memory for the projector, leaving enough headroom for Open WebUI and the rest of the local stack. The --reasoning off flag keeps OpenAI-compatible chat responses visible in clients that do not read separate reasoning fields.

With --mmproj, /v1/models advertised capabilities: ["completion","multimodal"]. In local validation, Open WebUI accepted an uploaded Pulumi logo image and Gemma 4 described it correctly. A small WAV file also worked through the OpenAI-compatible input_audio request shape, though llama.cpp logs still mark audio input as experimental.

Verify the LLM API

Open a new terminal and check if llama.cpp is responding:

curl http://127.0.0.1:18080/v1/models

The /v1/models endpoint should return the model ID unsloth/gemma-4-12b-it-GGUF. Now try a chat completion:

curl http://127.0.0.1:18080/v1/chat/completions \
 -H "Content-Type: application/json" \
 -d '{
 "model": "unsloth/gemma-4-12b-it-GGUF",
 "messages": [{"role": "user", "content": "Reply with exactly: OK"}],
 "temperature": 0,
 "max_tokens": 32
 }'

The chat prompt Reply with exactly: OK should return content OK. In validation, llama.cpp reported an output token velocity of about 20 tokens per second for a longer 160-token response.

Keep llama.cpp running after reboot

For a permanent setup, put the llama.cpp startup script and logs under a folder in your home directory and let launchd restart it when you sign in:

llm_home="$HOME/pulumi-gemma4-llm"
mkdir -p "$llm_home/logs" "$HOME/Library/LaunchAgents"

cat > "$llm_home/start-llama-server.sh" <<'EOF'
#!/bin/zsh
set -euo pipefail

export PATH="/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin"

exec "$HOME/pulumi-gemma4-llm/llama.cpp/build/bin/llama-server" \
 --hf-repo unsloth/gemma-4-12b-it-GGUF \
 --hf-file gemma-4-12b-it-Q8_0.gguf \
 --mmproj "$HOME/pulumi-gemma4-llm/models/mmproj-F16.gguf" \
 --host 127.0.0.1 \
 --port 18080 \
 --ctx-size 131072 \
 --parallel 1 \
 --jinja \
 --reasoning off
EOF

chmod +x "$llm_home/start-llama-server.sh"

cat > "$HOME/Library/LaunchAgents/com.pulumi.gemma4.llama-server.plist" <<EOF
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
 <key>Label</key>
 <string>com.pulumi.gemma4.llama-server</string>
 <key>ProgramArguments</key>
 <array>
 <string>$llm_home/start-llama-server.sh</string>
 </array>
 <key>WorkingDirectory</key>
 <string>$llm_home</string>
 <key>RunAtLoad</key>
 <true/>
 <key>KeepAlive</key>
 <true/>
 <key>StandardOutPath</key>
 <string>$llm_home/logs/llama-server.out.log</string>
 <key>StandardErrorPath</key>
 <string>$llm_home/logs/llama-server.err.log</string>
</dict>
</plist>
EOF

launchctl bootout gui/$(id -u)/com.pulumi.gemma4.llama-server 2>/dev/null || true
launchctl bootstrap gui/$(id -u) "$HOME/Library/LaunchAgents/com.pulumi.gemma4.llama-server.plist"
launchctl kickstart -k gui/$(id -u)/com.pulumi.gemma4.llama-server

Check the launchd service and llama.cpp logs:

launchctl print gui/$(id -u)/com.pulumi.gemma4.llama-server
tail -f "$HOME/pulumi-gemma4-llm/logs/llama-server.err.log"

If you want to stop llama.cpp later, unload the launchd service:

launchctl bootout gui/$(id -u)/com.pulumi.gemma4.llama-server

Deploy Open WebUI with Pulumi and k3d

Now we’ll deploy Open WebUI into a local Kubernetes cluster. This provides a polished chat interface that connects to our host-native LLM.

First, install k3d if you haven’t already:

brew install k3d

Create a new cluster for this project:

k3d cluster create pulumi-gemma4-blog-qa

We’ll use the Pulumi program in pulumi/examples. This program defaults to runtimeMode=host, which creates a Kubernetes ExternalName service pointing to your host machine.

Why not run the LLM inside Kubernetes on this Mac? Pulumi can do that, and the example supports it with runtimeMode=cluster, but that path is meant for Linux hosts with NVIDIA or AMD GPU device plugins.

On macOS, llama.cpp enables Metal by default, and Metal acceleration is available to native macOS processes. k3d runs Linux containers through Docker Desktop, so those pods do not get direct access to the Mac’s Metal device. Docker’s own vLLM Metal announcement calls out the same boundary: Metal-backed inference runs natively on the host because there is no Metal GPU passthrough for containers. That is why this setup keeps inference host-native and lets Pulumi manage the Kubernetes UI, service wiring, and optional Tailscale access around it.

Clone the examples repo, navigate to the program directory, and initialize a new stack:

git clone https://github.com/pulumi/examples.git
cd examples/kubernetes-py-self-host-gemma4-llm
pulumi stack init gemma4-local

Configure the program to match your local setup:

pulumi config set hostLlmPort 18080
pulumi config set llmBaseUrl http://llm-server:18080/v1

The Kubernetes service named llm-server maps to host.k3d.internal. In our validation, we confirmed that a disposable k3d pod could reach the Mac’s llama.cpp API at http://llm-server:18080/v1/models after a CoreDNS restart.

kubectl rollout restart deployment coredns -n kube-system

Run pulumi up to deploy Open WebUI and connect it to host-native llama.cpp:

pulumi up

In our validation environment, this command successfully reached the resource synthesis phase without requiring Tailscale credentials because Tailscale exposure is opt-in.

Access Open WebUI through Tailscale

Tailscale allows you to access your private Open WebUI instance from any device on your tailnet. Note that we only expose the web interface, not the raw LLM API, to keep the system secure.

The base Open WebUI deployment works without Tailscale credentials. To expose the web UI on your tailnet, enable Tailscale resources and provide an explicit api_key or OAuth/identity token:

pulumi config set enableTailscale true
pulumi config set tailscale:apiKey YOUR_API_KEY --secret

Once configured, Pulumi will create a Tailscale device or proxy that routes traffic to your Open WebUI service.

Use the model with Pi

Open WebUI gives you a browser-based chat interface, but local models are also useful from coding agents. Pi is the local coding agent used for this validation; if you do not use Pi, treat this section as an example of how any OpenAI-compatible client can point at the same local endpoint. Pi can point at the same OpenAI-compatible llama.cpp endpoint and use the model running on your Mac.

For a fresh Pi config, create ~/.pi/agent/models.json with a local provider that points at the llama.cpp API:

{
 "providers": {
 "local-llama": {
 "baseUrl": "http://127.0.0.1:18080/v1",
 "api": "openai-completions",
 "apiKey": "local",
 "compat": {
 "supportsDeveloperRole": false,
 "supportsReasoningEffort": false
 },
 "models": [
 {
 "id": "unsloth/gemma-4-12b-it-GGUF",
 "name": "Gemma 4 12B Q8 (local llama.cpp)",
 "reasoning": false,
 "input": ["text"],
 "contextWindow": 131072,
 "maxTokens": 1024,
 "cost": {
 "input": 0,
 "output": 0,
 "cacheRead": 0,
 "cacheWrite": 0
 }
 }
 ]
 }
 }
}

Then set Pi to use that provider and model by default in ~/.pi/agent/settings.json:

{
 "defaultProvider": "local-llama",
 "defaultModel": "unsloth/gemma-4-12b-it-GGUF",
 "defaultThinkingLevel": "off",
 "hideThinkingBlock": true
}

If you already have Pi configuration files, merge the local-llama provider and defaults into your existing JSON instead of replacing the files.

Manage your local AI stack as code

Let Pulumi provision the Kubernetes cluster, service wiring, and Tailscale access around your self-hosted model, so you can rebuild the whole setup with pulumi up.

Get started

Advanced: Linux GPU in-cluster serving

If you’re running on a Linux host with an NVIDIA or AMD GPU, you can run the LLM directly inside the Kubernetes cluster. This requires the NVIDIA or ROCm device plugins.

The Pulumi program supports this through runtimeMode=cluster. In this mode, it deploys a LlmServer pod that manages the llama.cpp process within the cluster, using GPU resource requests to ensure hardware acceleration.

Cleanup

When you’re done, you can tear down the resources:

pulumi destroy
k3d cluster delete pulumi-gemma4-blog-qa
# Stop llama.cpp using the PID from your terminal
kill <PID>

Deploy OpenClaw on AWS or Hetzner Securely with Pulumi and Tailscale

Engin Diri — Mon, 26 Jan 2026 00:00:00 +0000

Update (January 2026): The lobster has molted into its final form! From Clawdbot to Moltbot to OpenClaw. With 100k+ GitHub stars and 2M visitors in a week, the project finally has a name that’ll stick. The CLI command is now openclaw and the new handle is @openclaw. Same mission: AI that actually does things. Your assistant. Your machine. Your rules. See the official getting started guide for updated installation instructions.

Update (April 2026): Refreshed for OpenClaw 2026.4.27. Upstream now recommends Node 24, but the cloud-init script in this post still installs Node 22 — both work. If you’d like Node 24, change the nvm install 22 lines to nvm install 24.

The short version: Deploy OpenClaw to AWS or Hetzner with a Pulumi TypeScript program that provisions the VM, installs Docker, Node, and OpenClaw, then joins the instance to your Tailscale network so the gateway and browser ports stay private. One pulumi up to deploy, one pulumi destroy to tear down. Total cost: about $33/month on AWS or $7/month on Hetzner.

OpenClaw is everywhere right now. The open-source AI assistant gained 9,000 GitHub stars in a single day, received public praise from former Tesla AI head Andrej Karpathy, and has sparked a global run on Mac Minis as developers scramble to give this “lobster assistant” a home. Users are calling it “Jarvis living in a hard drive” and “Claude with hands”—the personal AI assistant that Siri promised but never delivered.

The Mac Mini craze is real: people are buying dedicated hardware just to run OpenClaw, with some enthusiasts purchasing 40 Mac Minis at once. Even Logan Kilpatrick from Google DeepMind couldn’t resist ordering one. But here’s the thing: you don’t actually need a Mac Mini. OpenClaw runs anywhere: on a VPS, in the cloud, or on that old laptop gathering dust.

With all this hype, I had to try it myself. But instead of clicking through the AWS console or running manual commands on a VPS, I wanted to do it right from the start: infrastructure as code with Pulumi. Why? Because when I inevitably want to tear it down, spin up a new instance, or deploy to a different region, I don’t want to remember which buttons I clicked three weeks ago. I want a single pulumi up command.

Dan got the assignment right:

In this post, I’ll show you how to deploy OpenClaw to AWS or Hetzner Cloud (if you want European data residency or just want to spend less). We’ll use Pulumi to define the infrastructure and Tailscale to keep your AI assistant off the public internet.

What is OpenClaw?

OpenClaw is an open-source AI assistant created by Peter Steinberger that runs on your own infrastructure. It connects to WhatsApp, Slack, Discord, Google Chat, Signal, and iMessage. It can control browsers, generate videos and images, clone your voice for voice notes, and run scheduled tasks via cron. There’s a skills system for extending functionality, and you can run it on pretty much anything: Mac Mini, Raspberry Pi, VPS, laptop, or gaming PC.

The difference from cloud-hosted AI? OpenClaw runs on your server, not Anthropic’s. It’s available 24/7 across all your devices, can schedule automated tasks, and keeps your entire conversation history locally. Check the official OpenClaw documentation for the full feature list.

Prerequisites

Before getting started, ensure you have:

Pulumi CLI installed and configured
A Pulumi Cloud account
AWS account (for AWS deployment)
Hetzner Cloud account (for European deployment)
Anthropic API key
Node.js 22+ installed (Node 24 recommended; the cloud-init script in this post installs Node 22 inside the VM)
Tailscale account with HTTPS enabled (one-time setup in admin console)

This guide uses Anthropic’s API, but OpenClaw works with other providers too. Check the providers documentation if you’d rather use OpenAI, Google Gemini, or a local model via Ollama.

Understanding OpenClaw architecture

OpenClaw uses a gateway-centric architecture where a single daemon acts as the control plane for all messaging, tool execution, and client connections:

Component	Port	Description
Gateway	18789	WebSocket server handling channels, nodes, sessions, and hooks
Browser control	18791	Headless Chrome instance for web automation
Docker sandbox	-	Isolated container environment for running tools safely

The Gateway connects to messaging platforms (WhatsApp, Slack, Discord, etc.), the CLI, the web UI, and mobile apps. The Browser component lets OpenClaw open web pages, fill forms, scrape data, and download files. Docker sandboxing runs bash commands in isolated containers so your bot can execute code without risking your host system.

Setting up ESC for secrets management

Deploying OpenClaw means handling sensitive credentials: API keys, auth tokens, cloud provider secrets. You don’t want these hardcoded or scattered across environment variables. Pulumi ESC (Environments, Secrets, and Configuration) stores them securely and passes them directly to your Pulumi program — the same pattern Pulumi uses to eliminate long-lived CI secrets across 70+ repos.

Create a new ESC environment:

pulumi env init <your-org>/openclaw-secrets

Add your secrets to the environment:

values:
 anthropicApiKey:
 fn::secret: "sk-ant-xxxxx"
 tailscaleAuthKey:
 fn::secret: "tskey-auth-xxxxx"
 tailnetDnsName: "tailxxxxx.ts.net"
 hcloudToken:
 fn::secret: "your-hetzner-api-token"
 pulumiConfig:
 anthropicApiKey: ${anthropicApiKey}
 tailscaleAuthKey: ${tailscaleAuthKey}
 tailnetDnsName: ${tailnetDnsName}
 hcloud:token: ${hcloudToken}

Then create a Pulumi.dev.yaml file in your project to reference the environment:

environment:
 - <your-org>/openclaw-secrets

This approach keeps your secrets out of your codebase and passes them directly to OpenClaw during automated onboarding. To prevent stack-level overrides of these values, see locking down ESC values with fn::final.

Securing with Tailscale

By default, deploying OpenClaw exposes SSH (port 22), the gateway (port 18789), and browser control (port 18791) to the public internet. This is convenient for testing but not ideal for production use.

Tailscale creates a secure mesh VPN that lets you access your OpenClaw instance without exposing unnecessary ports publicly. When you provide a Tailscale auth key, the Pulumi program:

Removes gateway and browser ports from public access
Keeps SSH as fallback for debugging if Tailscale setup fails
Installs Tailscale on the instance during provisioning (after other dependencies)
Enables Tailscale SSH so you can SSH via Tailscale without managing keys
Joins your tailnet automatically using the auth key

The Pulumi program installs Docker, Node.js, and OpenClaw first, then configures Tailscale last. This ensures that even if the Tailscale auth key is invalid or expired, you can still SSH in via the public IP to troubleshoot.

To generate a Tailscale auth key:

Go to Tailscale Admin Console
Click “Generate auth key”
Enable “Reusable” if you plan to redeploy
Copy the key and add it to your ESC environment

Deploying to AWS

Let’s walk through the complete AWS deployment. Create a new Pulumi project:

mkdir openclaw-aws && cd openclaw-aws
pulumi new typescript

Install the required dependencies:

npm install @pulumi/aws @pulumi/tls

Do not use t3.micro instances for OpenClaw. The 1 GB memory is insufficient for installation. Use t3.medium (4 GB) or t3.large (8 GB) instead.

The Pulumi program

Running OpenClaw on AWS means setting up a VPC, subnets, security groups, an EC2 instance, SSH keys, and a cloud-init script that installs everything. That’s a lot of clicking in the AWS console. The Pulumi program below defines all of it in code.

Replace the contents of index.ts with the following:

import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
import * as tls from "@pulumi/tls";

const config = new pulumi.Config();

const instanceType = config.get("instanceType") ?? "t3.medium";
const anthropicApiKey = config.requireSecret("anthropicApiKey");
const model = config.get("model") ?? "anthropic/claude-sonnet-4";
const enableSandbox = config.getBoolean("enableSandbox") ?? true;
const gatewayPort = config.getNumber("gatewayPort") ?? 18789;
const browserPort = config.getNumber("browserPort") ?? 18791;

const tailscaleAuthKey = config.requireSecret("tailscaleAuthKey");
const tailnetDnsName = config.require("tailnetDnsName");

// Generate a random token for gateway authentication
const gatewayToken = new tls.PrivateKey("openclaw-gateway-token", {
 algorithm: "ED25519",
}).publicKeyOpenssh.apply(key => {
 // Create a deterministic token from the public key (take first 48 hex chars)
 const hash = require("crypto").createHash("sha256").update(key).digest("hex");
 return hash.substring(0, 48);
});

const sshKey = new tls.PrivateKey("openclaw-ssh-key", {
 algorithm: "ED25519",
});

const vpc = new aws.ec2.Vpc("openclaw-vpc", {
 cidrBlock: "10.0.0.0/16",
 enableDnsHostnames: true,
 enableDnsSupport: true,
 tags: { Name: "openclaw-vpc" },
});

const gateway = new aws.ec2.InternetGateway("openclaw-igw", {
 vpcId: vpc.id,
 tags: { Name: "openclaw-igw" },
});

const subnet = new aws.ec2.Subnet("openclaw-subnet", {
 vpcId: vpc.id,
 cidrBlock: "10.0.1.0/24",
 mapPublicIpOnLaunch: true,
 tags: { Name: "openclaw-subnet" },
});

const routeTable = new aws.ec2.RouteTable("openclaw-rt", {
 vpcId: vpc.id,
 routes: [
 {
 cidrBlock: "0.0.0.0/0",
 gatewayId: gateway.id,
 },
 ],
 tags: { Name: "openclaw-rt" },
});

new aws.ec2.RouteTableAssociation("openclaw-rta", {
 subnetId: subnet.id,
 routeTableId: routeTable.id,
});

const securityGroup = new aws.ec2.SecurityGroup("openclaw-sg", {
 vpcId: vpc.id,
 description: "Security group for OpenClaw instance",
 ingress: [
 {
 description: "SSH access (fallback)",
 fromPort: 22,
 toPort: 22,
 protocol: "tcp",
 cidrBlocks: ["0.0.0.0/0"],
 },
 ],
 egress: [
 {
 fromPort: 0,
 toPort: 0,
 protocol: "-1",
 cidrBlocks: ["0.0.0.0/0"],
 },
 ],
 tags: { Name: "openclaw-sg" },
});

const keyPair = new aws.ec2.KeyPair("openclaw-keypair", {
 publicKey: sshKey.publicKeyOpenssh,
});

const ami = aws.ec2.getAmiOutput({
 owners: ["099720109477"],
 mostRecent: true,
 filters: [
 { name: "name", values: ["ubuntu/images/hvm-ssd-gp3/ubuntu-noble-24.04-amd64-server-*"] },
 { name: "virtualization-type", values: ["hvm"] },
 ],
});

const userData = pulumi
 .all([tailscaleAuthKey, anthropicApiKey, gatewayToken])
 .apply(([tsAuthKey, apiKey, gwToken]) => {
 return `#!/bin/bash
set -e

export DEBIAN_FRONTEND=noninteractive

# System updates
apt-get update
apt-get upgrade -y

# Install Docker
curl -fsSL https://get.docker.com | sh
systemctl enable docker
systemctl start docker
usermod -aG docker ubuntu

# Install NVM and Node.js for ubuntu user
sudo -u ubuntu bash << 'UBUNTU_SCRIPT'
set -e
cd ~

# Install NVM
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash

# Load NVM
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"

# Install Node.js 22
nvm install 22
nvm use 22
nvm alias default 22

# Install OpenClaw
npm install -g openclaw@latest

# Add NVM to bashrc if not already there
if ! grep -q 'NVM_DIR' ~/.bashrc; then
 echo 'export NVM_DIR="$HOME/.nvm"' >> ~/.bashrc
 echo '[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"' >> ~/.bashrc
fi
UBUNTU_SCRIPT

# Set environment variables for ubuntu user
echo 'export ANTHROPIC_API_KEY="${apiKey}"' >> /home/ubuntu/.bashrc

# Install and configure Tailscale
echo "Installing Tailscale..."
curl -fsSL https://tailscale.com/install.sh | sh
tailscale up --authkey="${tsAuthKey}" --ssh || echo "WARNING: Tailscale setup failed. Run 'sudo tailscale up' manually."

# Enable systemd linger for ubuntu user (required for user services to run at boot)
loginctl enable-linger ubuntu

# Start user's systemd instance (required for user services during cloud-init)
systemctl start user@1000.service

# Run OpenClaw onboarding as ubuntu user (skip daemon install, do it separately)
echo "Running OpenClaw onboarding..."
sudo -H -u ubuntu ANTHROPIC_API_KEY="${apiKey}" GATEWAY_PORT="${gatewayPort}" bash -c '
export HOME=/home/ubuntu
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"

openclaw onboard --non-interactive --accept-risk \
 --mode local \
 --auth-choice apiKey \
 --gateway-port $GATEWAY_PORT \
 --gateway-bind loopback \
 --skip-daemon \
 --skip-skills || echo "WARNING: OpenClaw onboarding failed. Run openclaw onboard manually."
'

# Install daemon service with XDG_RUNTIME_DIR set
echo "Installing OpenClaw daemon..."
sudo -H -u ubuntu XDG_RUNTIME_DIR=/run/user/1000 bash -c '
export HOME=/home/ubuntu
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"

openclaw daemon install || echo "WARNING: Daemon install failed. Run openclaw daemon install manually."
'

# Configure gateway for Tailscale Serve (trustedProxies + skip device pairing + set token)
echo "Configuring gateway for Tailscale Serve..."
sudo -H -u ubuntu GATEWAY_TOKEN="${gwToken}" python3 << 'PYTHON_SCRIPT'
import json
import os
config_path = "/home/ubuntu/.openclaw/openclaw.json"
with open(config_path) as f:
 config = json.load(f)
config["gateway"]["trustedProxies"] = ["127.0.0.1"]
config["gateway"]["controlUi"] = {
 "enabled": True,
 "allowInsecureAuth": True
}
config["gateway"]["auth"] = {
 "mode": "token",
 "token": os.environ["GATEWAY_TOKEN"]
}
with open(config_path, "w") as f:
 json.dump(config, f, indent=2)
print("Configured gateway with trustedProxies, controlUi, and token")
PYTHON_SCRIPT

# Enable Tailscale HTTPS proxy (requires HTTPS to be enabled in Tailscale admin console)
echo "Enabling Tailscale HTTPS proxy..."
tailscale serve --bg ${gatewayPort} || echo "WARNING: tailscale serve failed. Enable HTTPS in your Tailscale admin console first."

echo "OpenClaw setup complete!"
`;
 });

const instance = new aws.ec2.Instance("openclaw-instance", {
 ami: ami.id,
 instanceType: instanceType,
 subnetId: subnet.id,
 vpcSecurityGroupIds: [securityGroup.id],
 keyName: keyPair.keyName,
 userData: userData,
 userDataReplaceOnChange: true,
 rootBlockDevice: {
 volumeSize: 30,
 volumeType: "gp3",
 },
 tags: { Name: "openclaw" },
});

export const publicIp = instance.publicIp;
export const publicDns = instance.publicDns;
export const privateKey = sshKey.privateKeyOpenssh;

// Construct the Tailscale MagicDNS hostname from the private IP
// AWS private IPs like 10.0.1.15 become hostnames like ip-10-0-1-15
const tailscaleHostname = instance.privateIp.apply(ip =>
 `ip-${ip.replace(/\./g, "-")}`
);

export const tailscaleUrlWithToken = pulumi.interpolate`https://${tailscaleHostname}.${tailnetDnsName}/?token=${gatewayToken}`;
export const gatewayTokenOutput = gatewayToken;

Deploying to Hetzner

Hetzner Cloud is a solid choice if you need European data residency or want to spend less money. Spoiler: it’s a lot less money.

Hetzner has similar concepts to AWS but different names. EC2 instances become Servers. Security groups become Firewalls. Same idea, different provider. The resource types come from @pulumi/hcloud.

Create a new project for Hetzner:

mkdir openclaw-hetzner && cd openclaw-hetzner
pulumi new typescript

Install the Hetzner provider:

npm install @pulumi/hcloud @pulumi/tls

The default server type cax21 is an ARM-based (Ampere) instance with 4 vCPUs and 8 GB RAM. ARM instances cost less for the same compute. If you need x86 architecture, use ccx13 or similar CCX series instead.

The Hetzner Pulumi program

Replace index.ts with the following:

import * as pulumi from "@pulumi/pulumi";
import * as hcloud from "@pulumi/hcloud";
import * as tls from "@pulumi/tls";

const config = new pulumi.Config();

const serverType = config.get("serverType") ?? "cax21";
const location = config.get("location") ?? "fsn1";
const anthropicApiKey = config.requireSecret("anthropicApiKey");
const model = config.get("model") ?? "anthropic/claude-sonnet-4";
const enableSandbox = config.getBoolean("enableSandbox") ?? true;
const gatewayPort = config.getNumber("gatewayPort") ?? 18789;
const browserPort = config.getNumber("browserPort") ?? 18791;

const tailscaleAuthKey = config.requireSecret("tailscaleAuthKey");
const tailnetDnsName = config.require("tailnetDnsName");

// Generate a random token for gateway authentication
const gatewayToken = new tls.PrivateKey("openclaw-gateway-token", {
 algorithm: "ED25519",
}).publicKeyOpenssh.apply(key => {
 const hash = require("crypto").createHash("sha256").update(key).digest("hex");
 return hash.substring(0, 48);
});

const sshKey = new tls.PrivateKey("openclaw-ssh-key", {
 algorithm: "ED25519",
});

const hcloudSshKey = new hcloud.SshKey("openclaw-sshkey", {
 publicKey: sshKey.publicKeyOpenssh,
});

const firewallRules: hcloud.types.input.FirewallRule[] = [
 {
 direction: "out",
 protocol: "tcp",
 port: "any",
 destinationIps: ["0.0.0.0/0", "::/0"],
 description: "Allow all outbound TCP",
 },
 {
 direction: "out",
 protocol: "udp",
 port: "any",
 destinationIps: ["0.0.0.0/0", "::/0"],
 description: "Allow all outbound UDP",
 },
 {
 direction: "out",
 protocol: "icmp",
 destinationIps: ["0.0.0.0/0", "::/0"],
 description: "Allow all outbound ICMP",
 },
 {
 direction: "in",
 protocol: "tcp",
 port: "22",
 sourceIps: ["0.0.0.0/0", "::/0"],
 description: "SSH access (fallback)",
 },
];

const firewall = new hcloud.Firewall("openclaw-firewall", {
 rules: firewallRules,
});

const userData = pulumi
 .all([tailscaleAuthKey, anthropicApiKey, gatewayToken])
 .apply(([tsAuthKey, apiKey, gwToken]) => {
 return `#!/bin/bash
set -e

export DEBIAN_FRONTEND=noninteractive

# System updates
apt-get update
apt-get upgrade -y

# Install Docker
curl -fsSL https://get.docker.com | sh
systemctl enable docker
systemctl start docker

# Create ubuntu user (Hetzner uses root by default)
useradd -m -s /bin/bash -G docker ubuntu || true

# Install NVM and Node.js for ubuntu user
sudo -u ubuntu bash << 'UBUNTU_SCRIPT'
set -e
cd ~

# Install NVM
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash

# Load NVM
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"

# Install Node.js 22
nvm install 22
nvm use 22
nvm alias default 22

# Install OpenClaw
npm install -g openclaw@latest

# Add NVM to bashrc if not already there
if ! grep -q 'NVM_DIR' ~/.bashrc; then
 echo 'export NVM_DIR="$HOME/.nvm"' >> ~/.bashrc
 echo '[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"' >> ~/.bashrc
fi
UBUNTU_SCRIPT

# Set environment variables for ubuntu user
echo 'export ANTHROPIC_API_KEY="${apiKey}"' >> /home/ubuntu/.bashrc

# Install and configure Tailscale
echo "Installing Tailscale..."
curl -fsSL https://tailscale.com/install.sh | sh
tailscale up --authkey="${tsAuthKey}" --ssh || echo "WARNING: Tailscale setup failed. Run 'sudo tailscale up' manually."

# Enable systemd linger for ubuntu user (required for user services to run at boot)
loginctl enable-linger ubuntu

# Start user's systemd instance (required for user services during cloud-init)
systemctl start user@1000.service

# Run OpenClaw onboarding as ubuntu user (skip daemon install, do it separately)
echo "Running OpenClaw onboarding..."
sudo -H -u ubuntu ANTHROPIC_API_KEY="${apiKey}" GATEWAY_PORT="${gatewayPort}" bash -c '
export HOME=/home/ubuntu
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"

openclaw onboard --non-interactive --accept-risk \
 --mode local \
 --auth-choice apiKey \
 --gateway-port $GATEWAY_PORT \
 --gateway-bind loopback \
 --skip-daemon \
 --skip-skills || echo "WARNING: OpenClaw onboarding failed. Run openclaw onboard manually."
'

# Install daemon service with XDG_RUNTIME_DIR set
echo "Installing OpenClaw daemon..."
sudo -H -u ubuntu XDG_RUNTIME_DIR=/run/user/1000 bash -c '
export HOME=/home/ubuntu
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DIR/nvm.sh"

openclaw daemon install || echo "WARNING: Daemon install failed. Run openclaw daemon install manually."
'

# Configure gateway for Tailscale Serve (trustedProxies + skip device pairing + set token)
echo "Configuring gateway for Tailscale Serve..."
sudo -H -u ubuntu GATEWAY_TOKEN="${gwToken}" python3 << 'PYTHON_SCRIPT'
import json
import os
config_path = "/home/ubuntu/.openclaw/openclaw.json"
with open(config_path) as f:
 config = json.load(f)
config["gateway"]["trustedProxies"] = ["127.0.0.1"]
config["gateway"]["controlUi"] = {
 "enabled": True,
 "allowInsecureAuth": True
}
config["gateway"]["auth"] = {
 "mode": "token",
 "token": os.environ["GATEWAY_TOKEN"]
}
with open(config_path, "w") as f:
 json.dump(config, f, indent=2)
print("Configured gateway with trustedProxies, controlUi, and token")
PYTHON_SCRIPT

# Enable Tailscale HTTPS proxy (requires HTTPS to be enabled in Tailscale admin console)
echo "Enabling Tailscale HTTPS proxy..."
tailscale serve --bg ${gatewayPort} || echo "WARNING: tailscale serve failed. Enable HTTPS in your Tailscale admin console first."

echo "OpenClaw setup complete!"
`;
 });

const server = new hcloud.Server("openclaw-server", {
 serverType: serverType,
 location: location,
 image: "ubuntu-24.04",
 sshKeys: [hcloudSshKey.id],
 firewallIds: [firewall.id.apply(id => Number(id))],
 userData: userData,
 labels: {
 purpose: "openclaw",
 },
});

export const ipv4Address = server.ipv4Address;
export const privateKey = sshKey.privateKeyOpenssh;

// Construct the Tailscale MagicDNS hostname from the server name
// Hetzner servers use their name as the hostname
const tailscaleHostname = server.name;

export const tailscaleUrlWithToken = pulumi.interpolate`https://${tailscaleHostname}.${tailnetDnsName}/?token=${gatewayToken}`;
export const gatewayTokenOutput = gatewayToken;

You can find both programs in the Pulumi examples repo under openclaw/:

github.com/pulumi/examples

Cost comparison

Before deploying, let’s compare the costs between AWS and Hetzner for running OpenClaw 24/7:

	AWS (t3.medium)	Hetzner (cax21)
vCPUs	2	4
Memory	4 GB	8 GB
Storage	30 GB gp3 (+$2.40/mo)	80 GB NVMe (included)
Traffic	Pay per GB	20 TB included
Architecture	x86 (Intel/AMD)	ARM (Ampere)
Hourly price	$0.0416	€0.0104 (~$0.011)
Monthly price	~$33 (with storage)	€6.49 (~$7)
Annual cost	~$396	~$84

Hetzner gives you double the vCPUs, double the RAM, at less than a quarter of the price. The trade-off? ARM architecture instead of x86. But OpenClaw doesn’t care - it’s just Node.js and Docker.

Prices are for on-demand instances as of January 2026. AWS prices are for us-east-1; Hetzner prices exclude VAT. Both include standard networking and storage. Check AWS EC2 pricing and Hetzner Cloud pricing for current rates.

Running the deployment

With your ESC environment configured in Pulumi.dev.yaml, deploy with:

pulumi up

After deployment completes, you’ll see outputs similar to:

Outputs:
 gatewayTokenOutput : "786c099cc8f8bf20dbebf40b8b51b75cf5cdab25..."
 privateKey : [secret]
 publicDns : "ec2-x-x-x-x.compute-1.amazonaws.com"
 publicIp : "x.x.x.x"
 tailscaleUrlWithToken: "https://ip-10-0-1-x.tailxxxxx.ts.net/?token=786c099..."

The tailscaleUrlWithToken output provides the complete URL with authentication token. Copy and paste it into your browser to access the OpenClaw web UI.

Output names vary slightly between providers: AWS uses publicIp and publicDns, while Hetzner uses ipv4Address. The Tailscale hostname is derived from the instance’s private IP (AWS) or server name (Hetzner).

Automated onboarding

The Pulumi program runs OpenClaw’s non-interactive onboarding during instance provisioning. It uses your Anthropic API key from ESC, binds the gateway to loopback with Tailscale Serve as the HTTPS proxy, generates a secure gateway token (exported in Pulumi outputs), installs the daemon as a systemd user service, and configures trustedProxies and controlUi.allowInsecureAuth to skip device pairing when accessed via Tailscale.

The cloud-init script runs openclaw onboard --non-interactive with all necessary flags, then configures the gateway for secure Tailscale access. Your instance is ready as soon as provisioning finishes.

Access the web UI

Please wait 3-5 minutes after pulumi up completes. The cloud-init script runs after the instance launches and needs time to install Docker, Node.js, OpenClaw, and Tailscale, then run the onboarding process and start the daemon. Periodically refresh the page until it loads. If the page still doesn’t load after 5 minutes, see Verify the deployment to troubleshoot.

The easiest way to access the OpenClaw web UI is to use the tailscaleUrlWithToken output from Pulumi:

# Get the full URL with token
pulumi stack output tailscaleUrlWithToken

Copy and paste this URL into your browser. The URL includes both the Tailscale MagicDNS hostname and the authentication token, so you can access the web UI directly.

Finding your tailnet DNS name: Go to the Tailscale admin console and look under the DNS section for your tailnet name (e.g., tailxxxxx.ts.net). You can also find your machines and their MagicDNS hostnames in the Machines tab.

Token-based authentication provides an additional layer of security on top of Tailscale’s network-level authentication. Only devices on your tailnet can reach the URL, and the token prevents unauthorized access if someone gains access to your tailnet.

From the web UI, you can connect messaging channels (WhatsApp, Discord, Slack), configure skills and integrations, and manage settings.

Verify the deployment (optional)

If you encounter issues accessing the web UI, you can SSH into your instance to troubleshoot:

# Check your Tailscale admin console for the new machine
ssh ubuntu@<tailscale-ip>

# Check OpenClaw gateway status
systemctl --user status openclaw-gateway

Test your assistant

Open the gateway dashboard using the tailscaleUrlWithToken output and use the built-in chat to test your assistant:

Your personal AI assistant is now running 24/7 on your own infrastructure, accessible securely through Tailscale.

Redeploy OpenClaw with one command

With your infrastructure defined in Pulumi, you can move OpenClaw to a new region, rebuild it, or tear it down with pulumi destroy, without remembering which console buttons you clicked.

Get started

Security considerations

When self-hosting an AI assistant, security matters. OpenClaw’s rapid adoption meant thousands of instances spun up in days, and not everyone locked them down. The community noticed:

The tweet isn’t exaggerating. A quick Shodan search shows exposed gateways on port 18789 with shell access, browser automation, and API keys up for grabs:

Don’t let your instance be one of them.

Concern	Without Tailscale	With Tailscale
SSH access	Public (port 22 open)	Public fallback + Tailscale SSH
Gateway access	Public (port 18789 open)	Private (Tailscale only)
Browser control	Public (port 18791 open)	Private (Tailscale only)
API keys in transit	Exposed if gateway accessed over HTTP	Protected by Tailscale encryption
Attack surface	3 open ports	1 open port (SSH fallback)

SSH remains accessible as a fallback even with Tailscale enabled. This allows you to troubleshoot if Tailscale fails to connect. Once you’ve confirmed Tailscale is working, you can manually remove the SSH ingress rule from your security group for maximum security.

My recommendations:

Always use Tailscale for production
Rotate your auth keys periodically
Use Pulumi ESC for secrets instead of hardcoding
Enable Tailscale SSH to avoid managing keys manually
Monitor your Tailscale admin console for unauthorized devices
Remove the SSH fallback after confirming Tailscale works if you want zero public ports

What’s next?

Now that OpenClaw is running, you can install skills (voice generation, video creation, browser automation), set up scheduled tasks with cron, invite colleagues to your tailnet for shared access, or connect additional channels like WhatsApp and Discord.

For a deeper case study of running an AI assistant on Pulumi-managed infrastructure, see how we built Platybot, or read our KubeCon EU 2026 recap on the year AI moved into production on Kubernetes.

Conclusion

Deploying OpenClaw with infrastructure as code means you can reproduce your setup anytime, version control it, and tear it down with a single command. Adding Tailscale keeps it private - no exposed ports, no hoping you configured your firewall correctly at 2am.

If you run into issues or have questions, drop by the Pulumi Community Slack or GitHub Discussions.

New to Pulumi? Get started here.