# rlaope/oh-my-hermes

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Repository: https://github.com/rlaope/oh-my-hermes
Canonical: https://ross.abutalabs.com/products/oh-my-hermes
Homepage: https://rlaope.github.io/oh-my-hermes/
Language: Python
License: MIT
License Family: permissive
Topics: agent, ai, ai-agent, ai-tools, claude-code, codex, hermes-agent, hermes-skill, skills
Last push: 2026-08-26T17:16:08+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 6
- inputs: {"age_days": 91, "days_push": 7, "days_rel": 9, "gap_med": 7.0, "n_releases_24m": 9}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1166, forks 114 (observed 2026-08-28T04:03:49.743003+00:00)

## What it is
oh-my-hermes (OMH) is an installable enhancement layer for the Hermes Agent that adds planning, research, coding handoffs, agentic memory, subagents, and model routing on top of the existing agent runtime. It ships 103 skills and 9 workflows, routes work to coding executors like Claude Code or Codex, and keeps evidence boundaries without patching Hermes itself.

## Use cases
- add structured workflows and skills to hermes agent
- route ai coding tasks to claude code or codex with prepared handoffs
- set up per-task model routing across multiple llm providers
- give my ai agent persistent project memory
- orchestrate planning research and coding handoffs in a terminal agent
- install agent skills with a single setup command
- run multi-model agent workflows locally

## When to choose
- you already use Hermes Agent and want a stronger operating layer without replacing it
- you want vendor-neutral routing across coding executors like Claude Code, Codex, or pi
- you want editable model chains per kind of work with graceful fallback
- you want local contracts and explicit evidence boundaries for agent runs

## When to avoid
- you don't use Hermes Agent and aren't willing to install it as the host runtime
- you need a standalone agent framework rather than an enhancement layer for a specific host
- you need a hosted or cloud-managed agent orchestration service

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, prompt-engineering, workflow-automation, developer-tools, cli
- domain: large-language-models, developer-tools
- platform: windows, cli, python
- tags: hermes-agent, claude-code, codex, agent-skills, agentic-memory, model-routing, subagents, ai-workflows, ai-agents, automation, macos, linux

## Member repositories
- rlaope/oh-my-hermes (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:49.743003+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:29:17.954677+00:00, confidence not recorded.
  - readme: https://github.com/rlaope/oh-my-hermes (fetched 2026-08-28T04:03:49.743003+00:00, sha 160a8f13b730)
  - homepage: https://rlaope.github.io/oh-my-hermes/ (fetched 2026-08-29T12:35:16.491077+00:00, sha c294456e9585)
- Data as of 2026-08-30T08:39:29.467469+00:00.