Back to directory

Everything OpenAI Codex

An open-source workflow system that turns a raw OpenAI Codex agent harness into a repeatable engineering environment, with reusable skills, quality gates, session memory and cross-harness adapters.

Everything OpenAI Codex

EOC organizes work around a repeatable loop of intake, route, plan, execute, verify, capture and resume, backed by concrete files in the repository: AGENTS.md, agent.yaml and install profiles define what the agent owns before work starts, skills, agents, rules and commands route a task to the right specialist workflow, hook profiles and MCP configs keep runs reproducible across harnesses, and quality-gate and verification-loop scripts turn a finished task into evidence.

It ships a validated catalog of 60 agents, 232 skills, 110 rules, 28 hook matchers, 29 install modules and 75 legacy command shims, and works across OpenAI Codex, Cursor, OpenCode, Gemini, Zed, GitHub Copilot and Trae. It is licensed MIT and written in JavaScript.

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.