Back to directory

LazyCodex

An agent harness for OpenAI Codex that adds project memory, planning, execution and verified completion on top of Codex sessions, installed through the OmO agent-harness project.

LazyCodex

LazyCodex is an agent harness that brings project memory, planning, execution and verified task completion to OpenAI Codex sessions, built on the OmO agent harness project. It installs with a single npx command that runs the OmO installer targeting the Codex platform, or, experimentally, as a Codex plugin marketplace entry that can be added and installed from inside Codex itself or from its CLI.

After installation, a background worker finishes setting up configuration blocks, agent roles, binary links and a pinned binary for its bundled ast_grep MCP tool, printing a message to restart the session once that finishes; Codex requires approving the harness's hooks in its startup review before they run. A doctor command checks and explains the installation's health, and the harness can be upgraded through the Codex plugin marketplace.

It is written in TypeScript and installs as an npm package.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.