Field guide

Build your own agent team with Hermes

Hermes is an open-source agent runtime. It runs on your machine, holds memory across sessions, uses tools on your behalf, and can operate on a schedule without you watching.

This guide walks through what Hermes is, how it works, and how to design an agent team for a real workflow — from a single agent doing keyword research to a full team that researches, writes, and reviews content on a weekly cadence.

No coding experience required. Each chapter builds on the last.

Start from Chapter 1

14 chapters · Read in order or jump to what you need

01

What Problem Hermes Solves

Chat tools lose context between sessions and can't act on their own. A persistent agent runtime changes what your AI can do — and when it's overkill.

02

Hermes vs Normal AI Tools

A chat app responds to prompts. An agent runtime runs tools, holds memory, and operates on a schedule. A better runtime does not fix a bad workflow.

03

The Hermes Mental Model

An agent is not just a model — it's a role with identity, tools, memory, and skills. The hiring metaphor: you hire a specialist, not someone smart.

04

Underlying Tech Stack

What runs underneath: Python, the ~/.hermes directory, model providers, and the tool registry. You don't need to understand most of this — but knowing it exists helps when something breaks.

05

Frontend, Backend, and Interfaces

The CLI is the primary interface. The gateway connects your agent to 20+ messaging platforms. Some services run continuously, others only when you ask.

06

Installation and Hosting

Installing a runtime is different from signing up for a SaaS — your data stays on your machine. The install command, the setup wizard, and choosing between local, VPS, or Docker.

07

Agentic Behavior

The agent loop: observe, think, act, repeat. How tool calls happen, when approvals kick in, and what this means for how you design your agents.

08

Skills, Instructions, and Sharp Agents

What makes one agent better than another: narrow roles, the instruction hierarchy, skill documents with output contracts, and feedback loops that compound over time.

09

Multiple Agents and Subagents

Profiles for durable roles that compound over time, subagents for one-off tasks, and kanban coordination to keep agents from stepping on each other.

10

Memory and Auto-Learning

What agents store, when they retrieve it, and why memory is not intelligence. Auto-learning means persisting your feedback — not independent improvement.

11

Cron, Webhooks, and Unattended Work

Scheduled tasks, no-agent scripts, webhook triggers, and the boundary between what to automate and what to keep manual.

12

Designing a Practical Agent Team

The capstone: start small with two agents, add complexity only when you see the gaps. PR-only publishing, the minimum viable setup, and the mature team design.

13

Security, Reliability, and Operations

Security is a practice, not a feature. Secrets handling, approval workflows, provider fallback, backup strategies, and the six habits that prevent most problems.

Start here

Ready to see what a persistent agent can do?

Chapter 1 starts with the problem — why your current AI chat sessions lose context and can't carry work forward — and shows what changes when your agent runs in a persistent environment.

Book a Call