I built a team of AI agents at my company using Hermes — here's what actually happened
Summary
A firsthand account of building a team of AI agents at a company using the Hermes framework, detailing practical outcomes and lessons learned.
Similar Articles
I Stopped Building an AI-first company. What is the right Hermes setup should look like
The author shares their experience pivoting from a binary AI-can-or-cannot approach to a three-tier system (manual, autonomous with review, fully autonomous) for building AI agents, using Hermes with DeepSeek V4 Flash as orchestrator and Claude Code as executor, with a Kanban board and deterministic scripts to ensure reliability.
@coreyganim: I spent the entire week building 3 Hermes agents from scratch. The full architecture: 4 separates Gbrains as the founda…
A developer detailed the architecture of three Hermes AI agents built from scratch, using shared and private brains for role-specific tasks, with automated data syncs from various sources.
@kjut4q: I setup Hermes this week. A lot of you said you want to try it out, I'm documenting the whole journey, week by week, wh…
The author sets up the Hermes AI agent and plans to document its weekly progress, sharing what it learns and builds over a month of real use.
Thoughts after building with Hermes Agent
The author reflects on building with Hermes Agent, highlighting its modular architecture with separate identity, memory, and skills, and poses questions about its production use and comparisons to other agent frameworks.
A technical guide to building a persistent personal AI agent with Hermes, Obsidian, Git, memory, skills, and verification
A technical guide that explains how to build a persistent personal AI agent using Hermes, Obsidian, Git, and features like memory, skills, and verification.