Hermes Agent Architecture

Sat, 13 Jun 2026 00:00:00 +0000

Hermes Agent is easiest to understand as a runtime made of layers. The model is important, but it is only one layer. The useful behavior comes from the way the model is wrapped with tools, skills, memory, profiles, and gateway adapters.

graph TD
 User[User] --> CLI[CLI]
 User --> Desktop[Desktop App]
 User --> Gateway[Discord / Telegram / Slack Gateway]
 CLI --> Agent[Hermes Agent Loop]
 Desktop --> Agent
 Gateway --> Agent
 Agent --> Model[LLM Provider]
 Agent --> Tools[Toolsets]
 Agent --> Skills[Skills]
 Agent --> Memory[Memory]
 Agent --> MCP[MCP Servers]
 Agent --> Sessions[Session Store]
 Tools --> System[Filesystem / Terminal / Browser / APIs]
 MCP --> Services[External and Local Services]

Agent Loop

At the center is the agent loop:

Skills, Memory, and Context in Hermes

Sat, 13 Jun 2026 00:00:00 +0000

Hermes has several ways to remember things. They are not interchangeable. Putting the right information in the right layer is what keeps an agent useful instead of turning it into a haunted clipboard.

The Layers

Layer	Use it for	Do not use it for
Current context	The active task and immediate conversation	Durable knowledge
Session search	Finding what happened in prior chats	Source-of-truth documentation
Memory	Stable preferences and environment facts	Task logs, secrets, temporary state
Skills	Repeatable procedures and workflows	One-off project status
Obsidian	Plans, runbooks, incidents, architecture notes	Code or manifests
Git	Code, manifests, config, published docs	Private scratch notes

The mistake is treating all of these as “memory.” They are different systems with different jobs.

Memory on Derek's Guides

Hermes Agent Architecture

Agent Loop

Skills, Memory, and Context in Hermes

The Layers