#109109th of 149 in Skills, plugins and rules
oh-my-hermes
Plugin layer for Hermes Agent adding model routing, parallel coding lanes and memory
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.4k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
oh-my-hermes (OMH) installs as a plugin and CLI over Nous Research's Hermes Agent. It scores each request and routes it to one of twelve editable model-and-effort categories, splits work into parallel git worktree units, and loads 108 specialist omh-* skills. It also adds a reviewed, file-backed long-term memory and its own TUI (bare `omh`).
Who it is for: Hermes Agent users who want model routing, parallel coding and reviewed memory
Strengths
- Twelve editable model-and-effort chains with fallback when a provider rejects a model
- Parallel units get separate worktrees from one pinned SHA, with typed evidence states
- Memory entries need review and carry provenance and review-due dates
- Installs via curl script, Homebrew, Bun or npm, with `omh doctor` and `omh update`
Weaknesses
- Requires an existing Hermes Agent install; not usable standalone
- OMH TUI unavailable on Windows; falls back to Hermes' own TUI
- Cost and speed figures come from the README's own GPT-6 Astra benchmark
- Default install pipes a remote script to sh; setup needs an interactive model interview
What it needs
- Needs Hermes Agent, Node (for OMH TUI)
- Models: Claude, Gemini, Qwen3-Coder, DeepSeek, GPT-6 Astra
Also in Skills, plugins and rules
See all 149| Rank | Project | Score |
|---|---|---|
| 1 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #4 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 94 out of 100 |
| #5 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |