Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

oh-my-hermes

oh-my-hermes• Pinned

oh-my-hermes: Your Hermes bots and coding agents, in one window.

What problem it solves

Software work often needs several agents to handle independent tasks while preserving clear model routing, file ownership, and verification. It is also important to distinguish work that was planned or reported complete from work supported by observed test, review, or CI results.

Key features

  • Model routing by work category — Each lane receives a work category, model chain, and reasoning effort. When a provider rejects a model, the chain advances to the next configured option.

    Source: README

  • Parallel graph runs — A goal becomes a graph of small nodes whose ready work runs in parallel. A separate verification node checks the goal, and failed nodes are repaired before reporting.

    Source: README

  • Expert skills selected automatically — A catalog of frontend, backend, Rust, security review, and verification specialists is available to runs. Users do not invoke these specialists directly because the router loads the relevant skills as tool calls.

    Source: README

  • Reviewable long-term memory — Memory candidates are kept, refused, or deferred with a written reason instead of being remembered silently. The next session receives a task-ranked recall pack constrained to a token budget.

    Source: README

  • Evidence-based completion status — Status reports distinguish planning, execution, reported completion, and verification. A run is treated as verified only after a test, review, or CI gate passes.

    Source: README

Quick start

Copied verbatim from the project's README.

curl -fsSL https://omher.app/install | sh
omh setup

Who it may suit

This project may suit Hermes Agent users who want parallel coding workflows, configurable model routing, specialist skills, and explicit completion evidence.

Topics to discuss

  • Which work categories and model-chain fallbacks are most useful in daily workflows?

  • How should parallel lanes define and enforce coding ownership?

  • What evidence should be required before a graph run is considered verified?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/rlaope/oh-my-hermes#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/rlaope/oh-my-hermes

Comments

…