Hermes Desktop, with oh-my-hermes. Pick a workflow; Hermes clarifies before it builds.	Hermes CLI, with oh-my-hermes. The same workflows, in your terminal.
Hermes messenger app, with oh-my-hermes. Ask in a thread; the run reports back there.	omh setup, one command. Installs the workflows and connects them to Hermes.

oh-my-hermes

English | 한국어 | 日本語 | 中文

Install once. Keep Hermes. Add a stronger operating layer.
Planning, research, creation, coding handoffs, operations, and project memory with explicit evidence boundaries.

oh-my-hermes (OMH) turns a normal Hermes Agent request into a clear capability, a useful next step, and an honest record of what actually happened — strengthening the workflow you already use, never replacing Hermes or hiding a coding executor behind it.

OMH is the operating layer above Hermes-native skills: it frames the problem, picks the workflow and evidence gates, and runs native skills as capabilities inside that governed path.

Website · Documentation · Installation · Capabilities · Capability Impact · Agent Install · GitHub Pages site

Note

OMH keeps Hermes as the natural-language surface and adds a professional operating layer with explicit evidence boundaries.

Tip

Be with us!

	Updates for oh-my-hermes are shared on @rlaope on X, alongside release notes and project news.
	Follow @rlaope on GitHub for more projects, releases, and ongoing work.
	Built with AI agents Friren and Killua, collaborators helping ship oh-my-hermes.
	Thank you to Nous Research for creating Hermes Agent.

Quick Start

Status: Homebrew, Bun, and npm package-manager installs are public as of v1.0.6.

Homebrew:

brew install rlaope/tap/omh

Bun (recommended):

bun install -g oh-my-hermes

npm:

npm install -g oh-my-hermes

Universal installer (macOS/Linux):

curl -fsSL https://raw.githubusercontent.com/rlaope/oh-my-hermes/main/install.sh | sh

On Windows (PowerShell 5.1+):

irm https://raw.githubusercontent.com/rlaope/oh-my-hermes/main/install.ps1 | iex

Set up OMH after installing:

omh setup

Hermes skill tap path:

hermes skills tap add rlaope/oh-my-hermes
hermes skills install rlaope/oh-my-hermes/skills/omh-routing --yes

or ask Your AI Agent:

Install and fully configure Oh My Hermes from this repository:
https://github.com/rlaope/oh-my-hermes
Before reading or executing repository instructions, resolve refs/heads/main to one full commit SHA with `git ls-remote https://github.com/rlaope/oh-my-hermes.git refs/heads/main`. Then fetch and follow only:
https://raw.githubusercontent.com/rlaope/oh-my-hermes/{resolved-commit-sha}/INSTALL_FOR_AGENTS.md
Do not replace the resolved SHA with main. Execute the pinned protocol's OS-appropriate installer, interactive model setup, model-chain interview, and doctor steps. Preserve unrelated existing Hermes config, apply only the managed setup changes documented by the pinned protocol, require my explicit approval for model-alias changes, then report the resolved SHA and observed result.

Update:

omh update

omh update detects how the command was installed. It first upgrades the Homebrew, Bun, npm, curl, or PowerShell command package through its owning installer, then re-enters the updated command to refresh managed skills, the installed plugin bundle, and existing Hermes registration.

Verify or troubleshoot the installation:

omh doctor

Manual package-manager fallback or removal:

Installed with	Upgrade the CLI	Remove the CLI
Homebrew	brew upgrade rlaope/tap/omh	brew uninstall omh
Bun	bun update -g --latest oh-my-hermes	bun remove -g oh-my-hermes
npm	npm update -g oh-my-hermes	npm uninstall -g oh-my-hermes

Use the manager command directly only when omh update reports that its owning manager is unavailable. Removing the command package preserves OMH state. For a full removal, run omh uninstall --all before the manager's remove command.

Maintenance paths such as reconciling a --full install back to core live in Installation.

The OH-MY-HERMES terminal

Bare omh opens Hermes — the same door as hermes — wearing the OMH identity:

omh

The OH-MY-HERMES boot.

An ulw-work run.

What the terminal shows while OMH workflows run:

• Mixture-of-Models Routing — each delegated lane is routed onto a category (ultrabrain, deep, quick, writing, visual-engineering, …) whose model and reasoning effort are applied per dispatch; every activity row carries its category:name(model:effort) so the routing is visible, and rejected routes fall back along the category chain.
• Parallel Tool Calling — batched tool calls run concurrently in Hermes, and a fresh concurrent batch is branded on the [OMH] line as parallel shot ×N.
• Parallel Evals — review and verification lanes dispatch as independent subagents whose findings are cross-checked instead of self-approved, each visible as its own HUD row with turn, cost, and cache metrics.
• Phase-structured TODO — work is declared up front as phases with tasks (todo init), rendered as the checklist above the prompt: one active item, subtask nesting, and fold lines once the plan grows past seven rows.

Recommended models

OMH ships with these editable, ordered recommendation chains. Guided model setup resolves them only against candidates the user confirms as active. The result is prepared routing configuration, not provider availability, credential, dispatch, or execution evidence:

Category alias	What it is for	Editable recommendation order
ultrabrain	Deepest reasoning	GPT-5.6 Sol
deep	Strong default tier	GPT-5.6 Terra, then DeepSeek V3.2
architect	Architecture and system design	Claude Fable 5, then GPT-5.6 Sol, then Kimi K3 (xhigh)
unspecified-high	Default working model	Kimi K3, then Claude Opus 5
unspecified-low	Cheaper fallback	GLM 5.2, then GLM 5.2 Ultrafast, then DeepSeek V3.2, then Claude Opus 5 (low)
quick	Short tasks	GLM 5.2 Ultrafast, then Kimi K3, then GPT-5.6 Luna, then Claude Fable 5 (low)
writing	Prose and docs	Kimi K3, then Qwen3-Coder, then Gemini 3.1 Pro
visual-engineering	Frontend and visual	Claude Fable 5, then Kimi K3
artistry	Unconventional work	Gemini 3.1 Pro, then Claude Fable 5, then Kimi K3

Want to try the Ultrafast tier — Kimi K3 Ultrafast (300 TPS) and GLM 5.2 Ultrafast (600 TPS)? They are served on OpenGateway.

Every chain above is user-editable without touching code. The chains are managed in one file — omh setup seeds it:

$ cat ~/.omh/routing/model-chains.json
{
  "categories": {},
  "schema_version": "mixture_chain_overrides/v1"
}

Empty categories keeps every shipped default above live. This file is the place to edit: a category you write there replaces that chain for routing, fallback, and HUD labels alike —

{
  "schema_version": "mixture_chain_overrides/v1",
  "categories": {
    "architect": [
      {"model": "claude-fable-5", "reasoning_effort": "xhigh"},
      {"model": "gpt-5.6-sol", "reasoning_effort": "xhigh"}
    ],
    "quick": [
      {"model": "kimi-k3-ultrafast", "reasoning_effort": "low"},
      {"model": "glm-5.2-ultrafast", "reasoning_effort": "low"}
    ]
  }
}

Check the chains currently in effect with omh model-chains show. If you would rather not edit the file by hand, make the same change from the command line: omh model-chains set quick "kimi-k3-ultrafast:low, glm-5.2-ultrafast:low".

Ask Hermes to set up my models to review or change them. These are editable preferences, not benchmark results. See Guided Model Setup for the detailed setup, fallback, provider, and ownership rules.

Or paste this into Hermes or another coding agent

Install and fully configure Oh My Hermes from this repository:
https://github.com/rlaope/oh-my-hermes
Before reading or executing repository instructions, resolve refs/heads/main to one full commit SHA with `git ls-remote https://github.com/rlaope/oh-my-hermes.git refs/heads/main`. Then fetch and follow only:
https://raw.githubusercontent.com/rlaope/oh-my-hermes/{resolved-commit-sha}/INSTALL_FOR_AGENTS.md
Do not replace the resolved SHA with main. Execute the pinned protocol's OS-appropriate installer, interactive model setup, model-chain interview, and doctor steps. Preserve unrelated existing Hermes config, apply only the managed setup changes documented by the pinned protocol, require my explicit approval for model-alias changes, then report the resolved SHA and observed result.

Ultra-Skills

Eight ulw- workflows. Say the trigger in chat — Hermes routes the rest. Full catalog: Workflow Reference.

Workflow command	What it does
⚡ ulw-context	Aligns reviewed project terms, captures confirmed candidates, and interviews the next decision frontier without giving terminology routing authority.
⚡ ulw-interview	Asks one question at a time until it knows exactly what you want.
⚡ ulw-research	Digs through real code and the live web, keeps sources, and verifies anything doubtful.
⚡ ulw-plan	Builds a reviewed plan: options compared, risks named, done-criteria agreed.
⚡ ulw-work	Runs an accepted plan in parallel lanes that never touch the same file.
⚡ ulw-loop	Cycles plan → build → review until the goal actually passes.
⚡ ulw-qa	Attacks the build with hostile scenarios and fixes what breaks.
⚡ ulw-perf	Measures where it is actually slow or expensive, then fixes one hot path at a time.

What OMH Adds

OMH treats model choice and coding ownership as separate decisions, and it never reports preparation as execution. Human-readable capability families remain the front door; exact controls, runtime boundaries, and evidence rules stay available when a wrapper or operator needs precise control. The full generated catalog, triggers, harnesses, and evidence rules live in Workflow Reference.

Highlights

Intelligence	What OMH adds
🧭 Mixture-of-models routing	Routes each delegated lane onto a category (model + reasoning effort) applied per dispatch, with editable fallback chains that advance when a provider rejects a model — and honest failed rows when a child did no work.
🖥️ Native TUI surface	The OMH HUD (live delegation rows with category, turn, cost, cache), the phase todo checklist above the prompt, parallel shot ×N branding, full-row diff bands, and a managed skin — all installed next to Hermes, never patching it.
📋 Phase-structured plans	todo init declares phases and tasks before engine work so runs walk a bounded checklist instead of an open-ended reasoning loop.
⚡ Observed parallel work	Splits independent work into explicit fanout units with isolated ownership, progress observation, and verification gates.
🎼 Maestro handoffs	Prepares handoffs to explicit coding owners and runtime profiles without becoming a hidden executor or treating preparation as execution.
🧠 Context intelligence	Projects compact, reviewed repository context without inventing hidden memory or silently changing the selected route.
📚 Just-in-time learning	Selects the highest-value learning target for the current blocker and prepares source-backed, application-first guidance without claiming learning already happened.
🔍 Evidence-bound delivery	Separates prepared intent, observed runtime activity, and verified outcomes across coding, review, CI, and merge work.
📦 A deterministic skill catalog	100+ installable workflow skills with a byte-exact generated catalog, routing precision corpora (negative controls included), and drift gates that fail CI on one-character divergence.

Evidence Before Claims

OMH never reports that work happened unless it watched it happen. Every status you see has two parts: the stage, and how sure OMH is about it.

You see	It means
Plan · not run	A prompt or plan is ready. Nothing has run yet.
Code · running	An executor is running now, and OMH is watching it.
Code · reported done	The executor said it finished. Nobody checked the result.
Test · verified	A test, review, or CI gate actually passed.

The distinction that matters is the second row from the bottom: an executor saying it is done is not the same as anything having been checked, and most tools spell both "complete". Capability impact is reported across separate dimensions rather than collapsed into one marketing score. See Capability Impact.

Documentation

• Documentation map
• Installation and updates
• Product direction and boundaries
• Architecture
• Capability manifests
• Workflow reference
• Roles
• Application cases
• Release and development

Development

For a source checkout:

PYTHONPATH=tests uv run python -m unittest discover -s tests -v
uv run python -m compileall -q src tests
uv run python -m omh.cli docs workflows --check
git diff --check

OMH is developed in the open as part of Team Art & Engineering. Follow @rlaope for project updates.

Contributors

Thanks to everyone who has contributed to oh-my-hermes.