Yeachan-Heo/oh-my-codex

OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

What it solves

OMX (oh-my-codex) acts as a workflow and orchestration layer for the OpenAI Codex CLI. It addresses the need for a more structured, persistent, and repeatable development environment when using Codex, helping users manage complex tasks through standardized planning, multi-goal execution, and state tracking.

How it works

OMX wraps the existing Codex CLI, providing a set of specialized commands and a directory structure (.omx/) to maintain context. It introduces a canonical workflow—moving from Socratic clarification ($deep-interview) to architectural planning ($ralplan) and finally to durable, multi-goal execution ($ultragoal). It uses Git worktrees to isolate concurrent tasks and provides tools for managing project-specific guidance via AGENTS.md files.

Who it’s for

This tool is designed for developers who already use the OpenAI Codex CLI and want to improve their day-to-day productivity with better task routing, workflow automation, and session management. It is primarily optimized for macOS and Linux environments.

Highlights

  • Structured Workflow: Provides a clear path from requirement gathering to execution using specialized commands like $deep-interview, $ralplan, and $ultragoal.
  • State Persistence: Automatically stores plans, logs, and memory in a local .omx/ directory, allowing for resumable sessions.
  • Git Integration: Uses Git worktrees to safely isolate different tasks, preventing context contamination between concurrent sessions.
  • Team Coordination: Includes a $team command to handle parallel execution lanes for complex stories.
  • Configurable Guidance: Supports project-scoped AGENTS.md files to provide durable instructions and safety rules for specific repositories.

Related

  • Project
    onyx-dot-app/onyx

    Onyx is a self-hosted knowledge and context layer that connects to over 50 applications to provide AI agents with secure, relevant access to internal company data. It enables advanced features like deep research, custom agents, and external actions while maintaining strict data sovereignty.

  • Dispatch
    OpenAI Codex Research Preview

    OpenAI has launched Codex, a cloud-based software engineering agent powered by the codex-1 model that can independently write features, fix bugs, and propose pull requests in isolated sandbox environments.

  • Dispatch
    Running Codex safely at OpenAI

    OpenAI has implemented a security framework for Codex that combines sandboxing, managed network policies, and agent-native telemetry to balance developer productivity with enterprise-grade control.

  • Project
    onyx-dot-app/onyx-foss

    Onyx is a self-hosted knowledge and context layer that connects to over 50 applications to provide AI agents with secure, relevant access to your organization's internal data.

  • Project
    ogx-ai/ogx

    OGX is an open‑source, model‑agnostic API server that mimics OpenAI’s REST endpoints. It lets you run any LLM (Llama, GPT, Gemini, etc.) locally or in the cloud, while keeping the same client code. In addition to standard chat/completion/embedding calls, OGX offers a “Responses” API for tool‑calling and RAG, versioned skill bundles, and native routes for Anthropic and Google GenAI SDKs. Install with a one‑line script, start the server, and point any OpenAI‑compatible client at it.