mturac

mturac / everything-openai-codex

Public

EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.

github.commturaceverything-openai-codex agent-harness agent-skills ai-agents automation cli-tools
10
0
94% credibility
Found May 22, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

Everything OpenAI Codex (EOC) is an open-source workflow system that enhances AI coding assistants like OpenAI Codex, Cursor, and OpenCode. It provides 60 specialized agents, 232 reusable skills, and 110 coding rules that work across 12 programming languages. The system adds quality gates, session memory, and automation hooks to make AI coding more consistent and productive. It installs as a plugin or manually, works on Windows/macOS/Linux, and is MIT-licensed.

How It Works

1
💡 You discover a smarter way to code

You hear about a system that makes AI coding assistants remember your patterns, enforce best practices, and work across multiple tools.

2
⚡ You install it in seconds

With one simple command, everything is set up. The system automatically detects your preferred coding tool and configures itself.

3
🧠 Your AI assistant gains 60 specialized helpers

Instead of one general AI, you now have experts for security reviews, Python code, Go projects, testing, and much more—all ready to help.

4
You choose how to work
🔍
Quick task path

Run a single command like '/code-review' and get instant feedback on your work

📋
Guided workflow path

Start a skill that walks you through test-driven development or security auditing step by step

5
🛡️ Quality happens automatically

The system checks your work as you go—catching console.log statements, enforcing coding standards, and reminding you about tests.

6
💾 Your work is remembered

Sessions save your progress and learned patterns. When context gets full, the system saves your place so nothing is lost.

🚀 You ship better code, faster

Your AI assistant now works like an experienced team member who knows your project, follows best practices, and never forgets what you've built together.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is everything-openai-codex?

EOC is a workflow operating system for OpenAI Codex and similar AI coding tools. It wraps raw agent sessions with structured guidance: reusable skills for different domains, always-on coding rules, automated quality gates, and session memory that survives across work sessions. The system ships 60 specialized agents (code reviewers, security scanners, build fixers), 232 workflow skills covering everything from TDD to ML pipelines, and hooks that fire automatically during development. It also includes a Rust-powered alpha dashboard for visualizing session state. The project targets JavaScript/TypeScript tooling but supports 12 language ecosystems including Python, Go, Rust, Java, and Kotlin.

Why is it gaining traction?

The hook is completeness. Most Codex setups are bare prompts; EOC packages the operational patterns developers actually need into something installable. The cross-harness support is unusual—you get similar behavior whether you use OpenAI Codex, Cursor, OpenCode, or GitHub Copilot. Token optimization settings are built in, which matters for anyone watching API costs. The skill catalog covers real engineering work, not just toy examples.

Who should use this?

Teams using OpenAI Codex for production work who want consistent quality enforcement across sessions. Backend developers working with Go, Python, or Java who want language-specific review agents and build resolvers. Anyone running long Codex sessions who has hit context management problems—the memory persistence and strategic compaction features address this directly. Not for casual users or one-off experiments; the install complexity assumes you already know what you want from an AI coding tool.

Verdict

The feature surface is impressive for a 10-star project, but the credibility score of 0.949999988079071% signals you are early. Documentation exists and the catalog is substantial, but test coverage and community validation are minimal. Worth evaluating if you have serious Codex workflows, but treat it as a craft project with potential rather than a mature product.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.