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

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.
	Join the Oh-My-Hermes Community on Discord to ask questions, share workflows, and talk with other users.
	Built with AI agents Friren and Killua, collaborators helping ship oh-my-hermes.
	Thank you to Nous Research for creating Hermes Agent.

Quick Start

macOS / Linux:

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

Windows (PowerShell 5.1+):

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

Or paste this into 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.

⭐ Then set it up (required):

omh setup

Update:

omh update

omh update detects how the command was installed, upgrades the 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:

omh doctor

brew install rlaope/tap/omh

bun install -g oh-my-hermes

npm install -g oh-my-hermes

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

What you get

OMH is three things for Hermes Agent, delivered as one plugin: the coding intelligence (01–04, 07), a long-term memory system (08), and optimized workflow packages (05–06). One scene each, drawn from the real surfaces.

01 · Per-model tuning, task splitting, and stronger coding skills

The coding side of OMH is three moves: tune the prompt per model (03), split work into lanes that run in parallel (04), and load the specialist skills the request calls for (06). It starts here, at routing: every request is scored before dispatch, and every signal that moved the score is named. A rename scores light and goes to the quick lane. "Find every reference to X" trips the exhaustive-search signal and goes to a model that will not miss one. Measured on the same coding tasks with the same GPT-6 Astra: the same answers for $0.66 instead of $4.29, in 5 minutes instead of 23.

02 · Categories you own, per executor

ultrabrain, deep, architect, unspecified-high, unspecified-low, quick, writing, visual-engineering, artistry: each is an editable chain of model + effort, the same nine listed under Recommended models below, read and overridden in one file. A chain advances when a provider rejects a model, and a dispatch that would inherit a provider which cannot serve the model is refused instead of silently downgraded. Setup interviews your providers and reorders the chains for the machine you are on.

03 · Prompting tuned per model family, and measured

Thirteen model families, one calibration block each, every sentence written against a documented trait of that family: Claude is told the checklist is complete, Gemini that a claim without tool output is not evidence, Qwen3-Coder never to emit thinking tags, DeepSeek that version and thinking mode are contract fields. GPT-6 Astra gets its own exact-model contract and block. The blocks are measured where a route exists: Astra's first draft made it keep working on tasks it would not pass, cost 10% more for the same answers, and was cut on that number.

04 · Parallel where it is safe, typed when it comes back

ulw-work splits an accepted plan into units that never share a file, gives each one its own worktree branched from one pinned SHA, and lets a unit issue its tool calls in one turn. Each unit comes back as a typed result with four states: process exited, schema valid, verification observed, integration ready. Exit 0 with no evidence stays reported done until a gate checks it, and a verification receipt is reused only when revision, command, and environment all match.

05 · The Oh-My-Hermes interface, and Hermes Agent workflows

The interface is the Hermes terminal with an OMH dock under the prompt and a phase todo above it; the workflows are the ulw-* engines and every omh-* skill, routed from chat. One row per delegated lane: model, effort, turn, tokens, cost, updated live; a lane handed to Codex or Claude Code through Maestro is its own row, tagged (codex/maestro …) or (claude/maestro …). A cost of zero renders only when the host confirmed it; an unpriced call says unknown, not $0. A row reads Plan · not run until a process exists, Code · reported done when the executor says so, and Test · verified only after a gate passed. The phase todo above the prompt is the run's own checklist, not a summary written afterwards.

06 · Expert skills seep into the run

You never invoke an expert. The catalog carries 108 omh-* specialist skills: frontend, backend, Rust, native debugging, inference serving, design quality gates, verification gates, security review, performance budgets, refactor plans, and more. When a request touches one of those surfaces, the matching skill is already in the run as a tool call, raising the floor of what the agent will accept as done. Say it in English or Korean; the router picks the specialists.

07 · The architecture in one picture, then improved in phases

Ask for a picture of the repo and codebase-uml draws it from the code: packages, modules, and every import edge, with the cycles marked. The findings come ranked, and refactor-plan turns the top ones into phases that each land as one PR, behavior-locked by the tests, and abort the moment a lock breaks. The before and after are measured on the tree, and the dock shows each phase as it runs, and whether anything checked it.

08 · A long-term memory that a reviewer admitted

Nothing is remembered silently. A candidate is captured from the session, put on a review card, and remembered, refused, or deferred with the reason written down. An approved record carries its provenance and a review-due date; confirming it resets the clock, silence ages it from active to reference to archive. The next session gets a recall pack ranked for its task and cut to a token budget, with conflicts and duplicates resolved. Hermes' own memory is never read or patched; this store is OMH's, file-backed and reviewed.

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 numbered phases with tasks (todo init), rendered as the checklist above the prompt: one active item, tasks indented beneath every phase header, subtask nesting, and fold lines once the plan grows past eight rows.

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.

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:

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-5-1", "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". When an alias uses a provider-specific wire ID, map it once in ~/.omh/routing/model-providers.json with model_provider_routes/v1; set, status, fallback, and HUD then report the complete alias/provider/wire-model route. OMH stores only provider IDs, never provider credentials.

Every account differs, so the interactive omh setup also asks which providers the machine holds (config keys and env-key names suggest them; you can add more) and whether you have a Claude Code subscription, and records the answer in ~/.omh/routing/providers.json (provider_entitlements/v1). Each chain is then reordered so the entries a confirmed provider can serve lead; nothing is removed, nothing is invoked to check, and the Claude Code subscription only seeds the Claude Code --model preference for the Maestro lane, because Hermes itself cannot spend it.

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.

Coding delegation dispatch (omh coding run / omh coding fanout dispatch) — the Maestro lane that spawns Claude Code or Codex directly — has the same category dial as its own sibling file. Route it per work category with

$ omh coding category-maestro set codex ultrabrain gpt-5.6-sol:xhigh
$ omh coding category-maestro interview   # guided walk, Enter keeps each chain
$ omh coding run --owner codex --category ultrabrain --goal ...

which edits ~/.omh/routing/category-maestro.json (omh_category_maestro/v1); omh coding category-maestro show prints the effective table with operator overrides marked, and the interactive omh setup offers the same walk. An explicit --model on a run always wins, and ~/.omh/routing/dispatch-models.json remains the per-owner default used only when no route resolves at all (for the strongest Claude Code tier, set "claude-code": "opus" there). See docs/FANOUT.md (Category-maestro and Dispatch-model preference) for schemas and the full precedence order.

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

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

What OMH Adds

Hermes Agent already runs the loop. OMH decides what goes into it: which model and effort each lane gets, who owns the code change, which skills apply, and what counts as done. Two rules hold everywhere — model choice and coding ownership are separate decisions, and nothing prepared is ever reported as executed. The generated catalog, triggers, and evidence rules live in Workflow Reference.

Highlights

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.

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
• Model routing, fan-out contracts, and request scoring
• Per-model calibration map
• Evidence rules and capability impact
• Long-term memory model
• Live model benchmark and measured results
• 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.