Hermes Agent Swarm: Free Multi-Agent Update

The Hermes agent swarm feature is the free Hermes Workspace update that turns one AI agent into an entire team.

Single-agent workflows are slow.

Each step happens one at a time.

Long tasks take ages.

Hermes agent swarms fix that.

Multiple agents run in parallel.

One plans, one builds, one reviews — all at once, all coordinated automatically.

This post is the full walkthrough.

What Hermes Agent Swarm Is

A new feature inside Hermes Workspace.

Free.

Created by community contributor Eric.

Lets you run a team of Hermes agents simultaneously.

Each agent has:

A role.
A model.
A mission.
Memory.

The orchestrator (called Aurora) routes work between them.

You give the team a goal.

It figures out how to get there.

What's New In This Update

Three things to know:

1. Agent swarms — run multiple agents in parallel.

2. Phone access — control your swarm from mobile.

3. Auto-routing — give it a goal, it composes the routing plan.

This is one of the biggest free updates Hermes Workspace has shipped.

Setting Up Hermes Agent Swarms

Step 1 — Install the plugin

Use the free plugin (the one Eric created).

Run the install command in your terminal — it sets up Hermes Workspace.

Step 2 — Run Hermes gateway

Standard Hermes startup.

Step 3 — Start the workspace UI

Connect to Hermes Workspace on your local host.

Step 4 — Update if existing

If you already had Hermes Workspace, click Update first.

The swarms feature only works on the latest version.

Step 5 — Open the Swarms section

Left sidebar in Hermes Workspace.

Click "Swarms".

You'll see workers for planning, routing, reports, and more.

🔥 Want my full Hermes Agent Swarm setup? Inside the AI Profit Boardroom, I share my Hermes Workspace configs, swarm prompts, and the 30-day road map for using swarms in real workflows. Plus a 2-hour Hermes course and weekly live coaching. 2,800+ members. → Get the setup

Adding A Swarm Agent

In the Swarms section:

Click "Add swarm" (top right).
Pick a role from presets:
- Builder
- Reviewer
- Triage
- Lab
- Sage
- Scribeex
Each role has preset system prompts and skills.
Or click "Custom" — full control over system prompt, mission, skills.

The Main Agent (Aurora)

At the top of your swarm sits Aurora — the orchestrator.

Her job:

Receive your mission.
Decide which sub-agents handle what.
Route work between them.
Compile results.

You give Aurora a mission.

She compiles a routing plan.

The team executes.

Real Mission Example

From the demo:

"Create a new AI automation blog for SEO + plan keyword strategy + create the content. I want to rank for AI agent community related terms + send traffic to [URL]."

Aurora composed a plan:

Research agent gathered keyword data.
Strategy agent planned the content calendar.
Builder agents created the actual blog posts.
Reviewer agents checked the work.

Result: full blog with keyword research, competitor analysis, content brief, templates, and a 90-day content plan — built in 5-10 minutes.

That's the power of the swarm.

What You See In The UI

The Swarms section gives you:

Office view — round table or grid showing every agent.
Per-agent terminals — see what each agent is doing in real time.
File outputs — all generated content saved locally.
Browser preview — open generated work in your browser.
Blocked vs ready agents — instantly see what needs attention.

Compare this to managing 5 separate Hermes terminals.

This is a real upgrade.

Phone Access

Hermes Workspace's phone access works for swarms too.

You can:

Trigger a swarm from your phone.
Check progress on the go.
Approve outputs remotely.

Your agent team running 24/7 in your pocket.

This pairs naturally with OpenClaw Aion UI's phone access.

When To Use Swarms (And When Not)

Use swarms when:

The task has multiple distinct phases (research → write → review).
Output quality matters.
You want speed via parallelism.
The mission is too big for one agent.

Skip swarms when:

The task is small.
You're prototyping.
You're doing single-step work.

For one-off chats, single-agent is fine.

For production work, swarms are the upgrade.

Common Setup Issues

1. Agent showing "blocked".

Click the agent.

Check its settings — usually wrong API selected.

Switch to a model the agent can actually use.

2. Plugin install failing.

If you're not technical, ask Claude Code to install for you.

This trick works for most Hermes installs — covered in Free Claude Code.

3. Swarms feature can be a bit buggy.

If you hit issues, ask Claude Code to debug — it communicates with Hermes well.

Models For Each Swarm Role

Don't put every agent on the same model.

Match model to role:

Researcher — long-context cloud model (Kim K2.5).
Builder — creative cloud model.
Reviewer — small fast model.
Sub-agent in larger swarms — Nvidia Nemotron 3 Nano Omni (designed for sub-agents).

I cover model picks in Hermes Gemma 4 and Hermes DeepSeek.

Daily Reality

What it looks like running swarms daily:

Morning — give Aurora a content mission.
Aurora spawns the swarm.
Multiple agents work in parallel.
10-15 minutes later, full output ready.
I review and publish.

Used to be a half-day task.

Now it's a coffee.

Why Swarms Beat Single-Agent

Three reasons.

1. Parallelism.

Multiple tasks happen simultaneously.

No more waiting for one step before the next starts.

2. Specialisation.

Each agent does one thing well.

Better than a generalist trying to do everything.

3. Scale.

Adding more agents scales output without proportional time investment.

🚀 Want my full Hermes swarm playbook? The AI Profit Boardroom has my Hermes swarm configs, 2-hour Hermes course, daily training drops, and weekly live coaching. 2,800+ members building real automations. → Join here

FAQ — Hermes Agent Swarm

Is Hermes Agent Swarm free?

Yes — free plugin for Hermes Workspace.

Do I need Hermes Workspace installed first?

Yes — swarms run inside Workspace.

How many agents can I run in a swarm?

Hardware-dependent — I run 4-6 agents comfortably.

Can I run swarms from my phone?

Yes — Hermes Workspace supports phone access.

Will swarms work with cloud models?

Yes — but local Ollama models are cheaper for high-volume swarms.

What if a swarm agent gets stuck?

Check its API settings.

Most stuck agents are model misconfiguration.

Can I create custom swarm roles?

Yes — fully customisable system prompts, missions, and skills.