AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
oh-my-hermes
oh-my-hermes logo

oh-my-hermes

Active·★ 3.6k·MIT·Updated 2026-10-22

oh-my-hermes (OMH) is an add-on for Nous Research's Hermes Agent. Hermes stays the natural-language surface; OMH sits above its native skills, frames each request as a capability, picks a workflow and evidence gates, and runs the native skills inside that path. Workflows cover planning, research, creation, coding handoffs, operations and project memory.

A recurring theme is honesty about what happened: OMH records explicit evidence boundaries and says it never hides a coding executor behind Hermes. The omh CLI handles setup, update and doctor checks, and omh model sets the head model and effort per work category, with a skill for onboarding new model families.

Installation is via a shell script, Homebrew, Bun, npm or a Hermes skill tap, followed by a required omh setup. It is only relevant if you already use Hermes Agent, and the README is long, with many concepts to absorb.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#hermes-agent#agent-skills#long-term-memory#subagents#claude-code#codex#cli
$ Install
$ brew install rlaope/tap/omh && omh setup
↗ Visit site★ GitHub
01

Features

01Workflows for planning, research, creation, coding handoffs, operations and project memory
02Explicit evidence boundaries that record what actually happened
03omh model picker to set the head model and effort per work category
04omh doctor and omh update to verify and refresh skills and Hermes registration
05Installs via shell script, Homebrew, Bun, npm or a Hermes skill tap
02

Why choose it

+Adds structured workflows to Hermes while keeping Hermes and its native skills in place.
+Per-category model and effort routing from a single picker.
+Many install paths plus omh doctor and omh update for upkeep.
03

Trade-offs

!Only useful for Hermes Agent users.
!Another layer of concepts and configuration on top of Hermes.
!Setup is required after install, and it modifies Hermes configuration.
04

Maintenance check

ActiveChecked: 2026-10-23
Last commit
2026-10-22
Commits, last 90 days
100+
Releases, last 90 days
17
Latest release
v4.0.1 (2026-10-22)
Open issues
13
Recent issues with at least one comment
3/4

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1056 Run the paid-live benchmark for the four new family calibrations (mistral, llama, codestral, solar)3 comments · 2026-08-21
  • #1836 Measurement path for the Claude composer calibration2 comments · 2026-09-23
  • #1333 [Benchmark]: Hermes alone vs Hermes + OMH on this repository's own merged PRs, four quotable numbers2 comments · 2026-09-05
  • #2193 Native-speaker review of the vi.json trigger pack (follow-up to #2187)1 comments · 2026-10-21
  • #1817 [Feature]: Shadow, decline, refuse and replay — turning an OMH decision surface on from the owner's own traffic1 comments · 2026-09-22

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Hermes Agent
Operating layer
Verified via docs
macOS / Linux / Windows
omh CLI
Verified via docs
06

Quick start

1
$ brew install rlaope/tap/omh
2
$ omh setup
07

Use cases

↳Hermes Agent users who want structured workflows on top of native skills
↳Handing coding tasks from Hermes to an executor with a clear record
↳Routing different kinds of work to different models
08

Alternatives

⚡Top VS:
VSkungfu★4.5k→VSagent-bridge★404→VSagentpack★18→VSOpenPass★32→
kungfu logo
kungfu★ 4.5k
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
VSCompare→
agent-bridge logo
agent-bridge★ 404
A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。
VSCompare→
agentpack logo
agentpack★ 18
Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.
VSCompare→
OpenPass logo
OpenPass★ 32
🔐 The password manager for terminal users and AI agents. Age-encrypted, keyring-cached, MCP-ready. Zero telemetry.
VSCompare→
symaira-vault logo
symaira-vault★ 32
🔐 The password manager for terminal users and AI agents. Age-encrypted, keyring-cached, MCP-ready. Zero telemetry.
VSCompare→
skillhub logo
skillhub★ 5.3k
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
VSCompare→
fast-agent logo
fast-agent★ 3.9k
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
VSCompare→
bub logo
bub★ 1.7k
Bub it. Build it. A tiny agent runtime, composable with plugins.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
rlaope /
oh-my-hermes
↗

An operating layer for Hermes Agent that adds workflows, model routing and honest evidence records without replacing it

3.6kMIT
Last commit1d ago
StatusActive
CategoryDev Tooling
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.