code-yeongyu/lazycodex

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

What it solves

LazyCodex provides a structured agent harness for managing complex codebases within Codex. It eliminates the "setup ceremony" required for advanced agentic workflows by packaging the OmO (oh-my-openagent) engine, which brings professional-grade planning, execution, and verification to the development environment.

How it works

It acts as a distribution layer for the OmO engine, installing a suite of specialized tools and agent roles directly into Codex. It uses a multi-model routing system to assign tasks to the most efficient model (e.g., using high-reasoning models for logic and mini models for small edits) to optimize quota usage.

Who it’s for

Developers using Codex who need a high-discipline AI agent team to handle large-scale repository mapping, strategic planning, and autonomous execution of complex coding tasks.

Highlights

  • Command Pillars: Includes $ulw-plan for decision-complete planning, $start-work for durable execution, and $ulw-loop for verified completion.
  • Project Memory: The $init-deep command creates hierarchical AGENTS.md context to help agents navigate large repositories.
  • Specialized Skills: A library of skills for tasks like AST-grep structural search, LSP diagnostics, and AI-slop removal.
  • Multi-Agent Orchestration: Installs specific roles (explorer, librarian, plan, etc.) that can be spawned as sub-agents.
  • Model Routing: Automatically selects the best GPT model based on task category to balance performance and cost.

Related

  • Project
    code-yeongyu/oh-my-openagent

    A genuine AI‑agent toolkit that runs as an OpenCode plugin, a Codex‑CLI component set, or a standalone beta command. It ships 11 pre‑configured agents, a one‑word `ultrawork` launch command, Team Mode for parallel agents, LSP/AST‑grep integration, and optional hash‑line editing. Install via `bunx oh-my-openagent install`, `npx lazycodex-ai install`, or `npm i -g omo-ai@beta`.

  • Project
    AMAP-ML/LongHorizon-Harness

    A loop engineering framework that turns existing AI agents into long-running computer-use systems by wrapping them in a structured plan-act-verify cycle across GUI and CLI environments.

  • Project
    omnigent-ai/omnigent

    Omnigent is an open‑source meta‑harness that unifies many LLM coding agents (Claude Code, Codex, Cursor, etc.) under one CLI and web UI, letting you run, combine, and govern them across devices and cloud sandboxes, with built‑in collaboration and policy features.

  • Project
    truffle-ai/dexto

    An open agent harness and orchestration layer that turns LLMs into stateful agents with persistent memory, tool integration via MCP, and a built-in production-ready coding agent.