How to use Oh My Hermes: what you can do with it

3 use cases

• Add parallel graph runs to Hermes Agent with /dag-ulw

  Install OMH and type /dag-ulw so a goal becomes a graph of small nodes that run in parallel.

  • REPO rlaope/oh-my-hermes
  • Software and DevOps
  • Intermediate
  View prompt

  Install rlaope/oh-my-hermes for my Hermes Agent, run omh setup, then use /dag-ulw for <goal> and tell me which nodes were verified by a test, review or CI gate.

  Share Email me this

• Choose which model handles each kind of work

  Use omh model to set the model chain and reasoning effort for categories like ultrabrain, deep and quick.

  • REPO rlaope/oh-my-hermes
  • Software and DevOps
  • Beginner
  View prompt

  Open omh model in rlaope/oh-my-hermes and set <cheap model> for quick lanes and <strong model> for ultrabrain and deep lanes, then run a small /dag-ulw goal to confirm the routing.

  Share Email me this

• Rename Python symbols correctly with language server tools

  Enable OMH's opt-in lsp_tools so renames use the language server instead of text search.

  • REPO rlaope/oh-my-hermes
  • Software and DevOps
  • Intermediate
  View prompt

  Enable lsp_tools in rlaope/oh-my-hermes, then rename <symbol> to <new name> across this Python project with lsp_rename and run the test suite.

  Share Email me this

Quick start with Oh My Hermes

1. Check you have what it needs: Hermes Agent installed; macOS or Linux (install script) or Windows PowerShell 5.1+; Accounts or keys for the model providers you want in each lane.
2. Open rlaope/oh-my-hermes on GitHub and read the README and license.
3. Install with curl -fsSL https://raw.githubusercontent.com/rlaope/oh-my-hermes/main/install.sh | sh
4. Run omh setup
5. In Hermes type /dag-ulw followed by your goal
6. Read the report's stage labels: Plan not run, Code reported done, Test verified

These steps come from our top use case, Add parallel graph runs to Hermes Agent with /dag-ulw, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for rlaope/oh-my-hermes

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Software and DevOps

About this repo

• Who it is forHermes Agent users who want parallel, model-routed runs and a clear record of what was really verified.
• Why it is hot4.7k stars, talked about in 3 AI sources we track
• LanguagePython
• Sourcegithub.com/rlaope/oh-my-hermes · Back to Hot repos

Requirements

• Hermes Agent installed
• macOS or Linux (install script) or Windows PowerShell 5.1+
• Accounts or keys for the model providers you want in each lane

Related repos

• Trended earlier REPO NousResearch/hermes-agent Hermes Agent Hermes Agent is a self-improving AI agent from Nous Research. It creates skills from experience, improves them while using them, keeps agent-curated memory, searches its own past conversations, and can run on a small VPS, a GPU box or serverless infrastructure. You talk to it from a full terminal UI or from Telegram, Discord, Slack, WhatsApp and Signal through one gateway, and it can run scheduled jobs in plain language. It works with Nous Portal, OpenRouter, OpenAI or your own endpoint.
• Trended earlier REPO Yeachan-Heo/oh-my-claudecode Oh My Claudecode oh-my-claudecode (OMC) is multi-agent orchestration for Claude Code. It installs as a Claude Code plugin or an npm CLI and adds in-session skills such as /autopilot, /deep-interview and /team, plus `omc team` to spawn tmux workers running Claude, Codex, Gemini or Cursor in parallel, and `omc ask` to get a second opinion from another provider.
• Trended earlier REPO diegosouzapw/OmniRoute Omni Route OmniRoute is a free, MIT-licensed AI gateway that gives you one endpoint for many AI providers and models, with quota-aware fallback between them.