#601 · Primary category: AI Agents & Automation

oh-my-hermes

agent ai ai-agent ai-tools claude-code codex hermes-agent hermes-skill skills

The coding harness, optimized tools, a long-term memory system, subagents, and automatic model-routing packages for Hermes ⚚

Project last updated:08/30/26

GitHub Stars

1.3K

Forks

123

Contributors

15

License

MIT

Why we included this project

Most Hermes Agent users hit a familiar wall: the agent does a lot, but trusting its output takes effort. oh-my-hermes adds a control layer on top of the existing setup rather than replacing it. A single install wires up route files that push every request through problem framing, workflow selection, and explicit evidence gates before Hermes's own skills run inside that constrained path. It also brings a project-memory system, subagent orchestration with live cost and turn metrics, and model-routing chains you can edit per task type. The payoff is auditability: each run ends with a record of what actually happened, so agent output stops feeling like a black box. That fits solo developers and small teams that have outgrown ad-hoc CLI work and want structured planning, research, and coding handoffs without switching to another tool. Setup is one command through Homebrew, npm, Bun, or a curl installer, and routing, memory, and model preferences stay editable afterwards.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category