Run your first agent

Install a Companion agent on your Hub, connect it to a model, and give it something to do.

Time: ~20 minutes · You’ll need: Hub running, and either Ollama with a model or a cloud API key

Already run an agent elsewhere? If you use Claude Code, or your own OpenClaw or Hermes install, you don’t need to install anything here — point it at your Hub instead. See Connect an Existing Agent.

Which agent

Two first-party agents ship in the App Store. Both declare hub_integration.mcp_client, so Hub hands them its MCP endpoints at install time.

App	Store ID	Port	What it is
OpenClaw WebCLI	`ci-openclaw`	18789	Self-hosted assistant with browser automation and tool use
Hermes	`ci-hermes`	18790	Messaging assistant with a web terminal and dashboard

This tutorial uses OpenClaw, the wizard’s default. Hermes follows the same shape.

The store also carries a plain openclaw entry (port 30189). That is the upstream project without Hub’s integration — it does not receive Hub’s MCP or memory variables. For this tutorial you want ci-openclaw, listed as OpenClaw WebCLI.

Check whether you already have it

The Onboarding Wizard pre-selects OpenClaw, so it may already be installed. Look for OpenClaw WebCLI on your dashboard before installing a second copy.

Install it

From the App Store, find OpenClaw WebCLI and install it. Hub pulls the image, generates the environment, and starts the container.

Because the app declares hub_integration.mcp_client: true, Hub injects its MCP endpoint variables (HUB_URL, HUB_MCP_URL, HUB_MCP_API_KEY, and related) into the app’s environment. You do not configure those by hand — see AI & Inference.

Open it

Click Open on the app card, or go to its port directly:


http://localhost:18789

You get OpenClaw’s setup interface on first run.

Hostname not resolving? The direct port always works — see Finding Your App’s URL.

Give it a model

On first run, OpenClaw asks for a model provider and key. Two routes:

Local — point it at Ollama on your host. Nothing leaves your machine. Requires a pulled model; see Install Ollama.
Cloud — paste an API key for a hosted provider. Better results on hard tasks; your prompts leave your machine.

You can change this later; it is not a one-way door.

Give it a task

Ask for something small and checkable, so you can tell whether it actually worked:


List the files in your working directory and tell me what this project is.

A real answer means the agent is installed, has a model, and can use its tools. That’s the whole loop working.

What the Hub integration adds

Installed this way, the agent gets things a standalone install doesn’t:

Hub MCP endpoints, injected at install, so it can act on your Hub
Companion Memory wiring, when Memory is installed — via CI_SERVER_URL and CI_SERVER_TOKEN
A wake endpoint (/hooks/wake) Hub can call to nudge the agent

Enable Hub’s MCP server if it isn’t on yet:


cihub mcp setup

Then cihub mcp config to see the resolved endpoints. See AI & Inference.

Open questions

Two details I could not confirm from the source, so they’re deliberately absent above rather than guessed:

The exact first-run screens for OpenClaw WebCLI when installed through Hub. The upstream project documents a setup UI on port 18789 that asks for a model provider and key, and Hub’s app entry uses that same port — but whether Hub pre-fills the provider from your Settings → AI preferences, or asks from scratch, isn’t something I could verify. If it pre-fills, step 4 should say so and get shorter.
Whether a restart is needed after Hub injects memory variables. Upstream notes that OpenClaw needs one restart if the memory environment arrives after onboarding. Whether Hub’s install ordering avoids that is unclear — if it doesn’t, this page needs a restart step.

Both are quick to settle for anyone with a Hub in front of them.

Connect an Existing Agent — for agents you already run
Companion Agent — the agent ecosystem
OpenClaw — the app reference