Oh My Hermes Oh My Hermes
Oh My Hermes (OMH) is an operating layer that installs on top of Nous Research's Hermes Agent and keeps Hermes as the natural-language surface while adding governed workflows. `omh setup` registers 116 installable skills organized into seven capability families and nine `ulw-*` workflows for planning, research, creation, coding handoffs, operations, and project memory, each with explicit evidence boundaries so the run reports what actually happened. `omh model` (or `/omh-model` inside the Hermes TUI) sets a head model and effort per work category with editable model chains in `~/.omh/routing/model-chains.json`, and the Maestro lane dispatches coding units to Claude Code or Codex rather than hiding a coding executor behind Hermes. It works in the Hermes CLI, Hermes Desktop, and messenger integrations, ships `omh doctor` and `omh update` for maintenance, and offers an agent-installable protocol pinned to a commit SHA.
v2.0.2 with ~2.5k GitHub stars and 3,500+ commits as of September 2026; trending on GitHub (daily) in mid-September 2026 with package-manager installs (Homebrew, Bun, npm) public since v1.0.6.
As of
- 116 skills in seven capability families plus nine ulw-* workflows for Hermes Agent
- Per-category model chains and effort dials configurable from CLI or inside the Hermes TUI
- Maestro lane that hands coding work to Claude Code or Codex with explicit evidence gates
- Project memory and honest run records with evidence boundaries
- Homebrew, Bun, npm, shell, PowerShell, and Hermes skill-tap install paths with `omh doctor`
- Runs across Hermes CLI, Desktop, and Discord/Slack-style messenger surfaces; READMEs in English, Korean, Japanese, and Chinese
Hermes Agent users who want a structured, professional workflow layer (planning, research, ops, coding handoffs) instead of building their own skill stack.
Anyone not running Hermes Agent; users of Claude Code or Codex alone should look at Agent Skills, Superpowers, or ECC instead.
Free and open-source under MIT; install via `brew install rlaope/tap/omh`, `bun install -g oh-my-hermes`, `npm install -g oh-my-hermes`, the shell/PowerShell installer, or the Hermes skill tap. Requires Hermes Agent and whatever model providers you route to.
The most complete community operating layer for Hermes Agent so far; its explicit routing and evidence gates make Hermes more predictable for real work, though it is only useful inside that ecosystem.
Is Oh My Hermes free?
Yes - Oh My Hermes is Open Source. Free and open-source under MIT; install via `brew install rlaope/tap/omh`, `bun install -g oh-my-hermes`, `npm install -g oh-my-hermes`, the shell/PowerShell installer, or the Hermes skill tap. Requires Hermes Agent and whatever model providers you route to.
Is Oh My Hermes open source?
Yes - Oh My Hermes is open source. Free and open-source under MIT; install via `brew install rlaope/tap/omh`, `bun install -g oh-my-hermes`, `npm install -g oh-my-hermes`, the shell/PowerShell installer, or the Hermes skill tap. Requires Hermes Agent and whatever model providers you route to.
Who is Oh My Hermes best for?
Hermes Agent users who want a structured, professional workflow layer (planning, research, ops, coding handoffs) instead of building their own skill stack.
Who is Oh My Hermes not ideal for?
Anyone not running Hermes Agent; users of Claude Code or Codex alone should look at Agent Skills, Superpowers, or ECC instead.
What are the best Oh My Hermes alternatives?
The closest Oh My Hermes alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.
Who makes Oh My Hermes?
Oh My Hermes is developed by rlaope. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.
Content on this page is AI-generated. Please verify details with the vendor's website for accuracy.