Run Hermes Agent on MIOSA

~15 min TypeScript Python

What you’re building: Install the open-source agent harness and run many tool-using agents.

Primitives you’ll use: Sandbox, Agent and harness

Agent prompt

Start with your coding agent

A few quick questions, then copy a prompt for any coding agent.

Who is it for?

Pick one to start. The rest adapts to it.

For my company Internal. One organization, a workspace per team, SSO. No billing. Build a product For customers. A workspace per customer, isolation, metering and billing.

What you're building

an open-source agent harness that runs many tool-using agents Modelled on Hermes Agent, by Nous Research.

Hermes Agent is an open agent harness: an orchestrating agent calls tools and delegates work to other agents running in their own environments.

Primitives you'll use: Sandbox · Agent and harness

Open-source agent harness
Tool-using agents
Delegation to sub-agents
Runs on your own infrastructure

You install and run the real Hermes Agent on MIOSA. Read the official docs first: hermes-agent.nousresearch.com/docs/getting-started/installation. Every install command below comes from them; if the docs and this guide disagree, the docs win. Hermes Agent is open source (Nous Research).

What you need on MIOSA

Each row is one thing to create before you start. The number matches the step that uses it.

Organization and API key Scopes every call; a workspace key is all a worker needs. miosa api-key create app-key --preset agent Docs
Sandbox The isolated Linux workspace the agent writes code and runs commands in. miosa create app-box --template nextjs --wait Docs
A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
Usage metering and bill-to Usage per customer, and which account pays for new machines. miosa org bill Docs
Agent and harness Turns a prompt into work: pick the harness and model a run uses. miosa agent harnesses Docs

Architecture

How it runs on MIOSA

Where it runs -> a MIOSA sandbox (an isolated Linux workspace)

State and files -> Hermes keeps its config and memory under `~/.hermes`; a persistent sandbox keeps it across pauses.

Model -> your own provider key, never a MIOSA platform key

Your customers -> one workspace each, isolated from each other

Auth and tenancy

Your organization is the platform; customers never get a MIOSA account, they sign into YOUR product. One workspace per customer, created as they onboard, isolates their machines, runs and data.

miosa workspace create hermes-agent-customer-1

Tag every machine and run with the customer id in `metadata`, and never query across customers. Meter usage per customer with GET /api/v1/usage and set who pays with PUT /api/v1/bill-to (/docs/platform/usage-and-billing).

Install Hermes Agent

Run these inside the sandbox (for example `miosa exec hermes-agent-box -- bash -lc '<command>'`), in order. The commands are from the official docs.

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

source ~/.bashrc

Check: the install finishes without errors; the next sections configure and start it.

Configure

Choose the provider and model with `hermes model` (Nous Portal, OpenRouter, OpenAI, or your own endpoint), then `hermes setup` for the full wizard.

Model: Anthropic (Claude). Calls use my own provider key (entered in the tool's own setup); MIOSA platform keys are never used.

Run it

Start it and prove it works.

hermes doctor

Check: the tool starts without errors and responds.

Persistence and access

Hermes keeps its config and memory under `~/.hermes`; a persistent sandbox keeps it across pauses.

Check: after the machine pauses and resumes, the tool starts again with its state intact.

Make it a product

MIOSA routes to Hermes as the `hermes` runtime (client.agentRuns.run with provider "hermes"): run one per customer workspace and stream its events into your UI.

Limits and costs

Pin the version you tested and update deliberately; these tools change quickly.

Give the tool only the credentials it needs, as secrets, not baked into files.

Prototype: keep it to one machine at the default size, skip replicas and custom hostnames you do not need, and delete everything when you are done.

Acceptance checks

Hermes Agent runs on a MIOSA sandbox and answers a real task.

State survives a pause and resume.

Each customer has its own workspace and its own instance; nothing is shared between them.

Everything it created can be deleted with nothing left running.