OmO
Oh My OpenAgentv3.17.13

Core Concepts

How OmO connects intent, planning, models, agents, categories, skills, tools, and continuation.

System Shape

Intent Before Action

OmO does not treat every prompt as literal text. It first asks what the user really needs: explanation, investigation, implementation, planning, review, or delegation. That matters because the same sentence can imply different work depending on context.

Surface requestHarness interpretation
“Why is this broken?”Reproduce, diagnose root cause, fix if feasible.
“Can you look into this?”Investigate and resolve, not just summarize.
“What's the best way?”Choose the route and implement when the codebase implies action.
“Review this”Find bugs, risks, missing tests, and verification gaps first.

Planning vs Execution

Prometheus, Metis, Momus, and Atlas exist to separate decisions from implementation.

AgentBoundary
PrometheusInterviews, researches, and writes plans. It should not edit production code.
MetisFinds hidden intent, ambiguity, missing constraints, and AI failure points before a plan hardens.
MomusRejects vague plans until file references, acceptance criteria, and verification are concrete.
AtlasExecutes an approved plan through focused tasks, accumulates learnings, and verifies each step.
Sisyphus-JuniorCategory-spawned executor. It focuses on one assigned unit and cannot re-delegate.

The important rule is “Decision Complete”: a plan should leave no hidden product or architecture decisions to the implementer.

Model Families

OmO routes by agent and category because models behave differently.

FamilyTypical use
Claude-like modelsStructured orchestration and disciplined instruction following. Claude Opus, Sonnet, Kimi K2.5, GLM 5 fit many Sisyphus-style flows.
GPT modelsExplicit reasoning and architecture. GPT-5.4 is used for Hephaestus, Oracle, Momus, and hard logic categories.
Gemini modelsVisual/frontend and creative work where a different reasoning style helps.
Fast utility modelsExplore, Librarian, quick fixes, grep-style work, and cheap background research.

Do not “upgrade” every task to the most expensive model. Explore and Librarian are intentionally fast and cheap because retrieval should not burn orchestration tokens.

Category + Skill

Categories describe the work; skills inject domain expertise and sometimes MCP servers.

CategoryUse
visual-engineeringFrontend, UI/UX, design, styling, animation.
ultrabrainHard logic, architecture, deep reasoning.
deepAutonomous research and implementation.
artistryCreative or unconventional problem solving.
quickTrivial single-file changes, typo fixes, simple modifications.
unspecified-lowLow-effort work that does not fit another category.
unspecified-highHigh-effort work that does not fit another category.
writingDocumentation, prose, technical writing.

A good delegation names both:

task({
  category: "visual-engineering",
  load_skills: ["frontend-ui-ux", "playwright"],
  run_in_background: false,
  prompt: "Implement and browser-verify the responsive sidebar.",
});

Continuation as a Harness Feature

The Sisyphus metaphor is literal: the system pushes unfinished work back into motion.

MechanismWhat it protects against
Todo continuationAgent stops while todos remain.
Ralph loop / ulw loopLong tasks that need repeated self-continuation.
Boulder state/start-work can resume a Prometheus plan across sessions.
Session recoveryMissing tool results, unavailable tools, empty content, context-limit failures.
Runtime fallbackModel/provider failures that should move to a configured fallback.

On this page