Yeachan-Heo/oh-my-codex — OmX Orchestration Layer for OpenAI Codex CLI
An 'oh-my-zsh for Codex' — adds hooks, agent teams, a HUD, tmux-based parallel workers, and 33 agent prompts + 36 workflow skills on top of OpenAI Codex CLI.

⭐ 2,867
An 'oh-my-zsh for Codex' — adds hooks, agent teams, a HUD, tmux-based parallel workers, and 33 agent prompts + 36 workflow skills on top of OpenAI Codex CLI.
The reason this repo is trending isn't only the star count. What matters is the gap it fills in the AI agent ecosystem — and right now that gap is contested every week by new entrants.
Background
Maintainer history, employer affiliation, and contributor mix are the first credibility signals. README opening with a working demo video usually means PoC works; long text-only README typically signals pre-demo stage.
Core Capability
The fundamental problem here is how LLM agents efficiently manage tokens, memory, and tool calls in long-horizon workloads. LangChain/LlamaIndex are strong on single-shot RAG/chains; they accumulate inefficiency in multi-step autonomous execution.
This repo combines (1) context compression, (2) self-eval, (3) tool-call abstraction. Surface value: cut token cost in half on equivalent tasks. Deeper value: reproducible agent execution logs.
Stack
- Language: Python
- License: MIT
Comparison
| Project | Stars | Daily | Differentiator |
|---|---|---|---|
| This repo | 2,867 | 95 | (per summary) |
| AutoGPT | 170k | 50 | full autonomy, low maturity |
| LangGraph | 10k+ | 60 | graph workflow |
| CrewAI | 28k | 100 | multi-agent |
Daily-stars velocity matters more than cumulative right now; the agent category is not winner-take-all — it segments by use-case.
Why Now
Agent stack splitting in two: official IDE integrations (Codex CLI, Claude Code) vs open-source core libraries. Enterprise PoC demand is pulling the latter back into focus to cut SaaS lock-in cost.
Quickstart
git clone https://github.com/Yeachan-Heo/oh-my-codex
cd $(basename https://github.com/Yeachan-Heo/oh-my-codex .git)
pip install -r requirements.txt
export OPENAI_API_KEY=...
python examples/quickstart.py
Common first pitfalls: Pydantic v2 + Python <3.11 mismatch; rate-limit hitting mid-demo (cap with --max_iterations 5).
Limits + Roadmap
Two clear limits today: (1) non-English workload validation thin; (2) enterprise SSO/audit logs missing. Latter is on the June roadmap; former is open-issue only.
Tomorrow Morning
- Devs:
git clone https://github.com/Yeachan-Heo/oh-my-codex, run quickstart, port one workload to compare token cost. - Founders/PM: ROI sim if migrating from OpenAI Assistants API to OSS backbone.
- Investors/General: Watch daily-stars next 7 days. >200/day = hype peak.
Sources
관련 기사

OpenAI Launches ChatGPT Pro at $100/Month — Is This the Real Answer to Claude Code?
OpenAI launched ChatGPT Pro at $100/month with expanded Codex access. With Claude Code crossing $2.5B ARR, this is OpenAI's counter-offensive in the AI coding tool war.

OpenAI Codex Just Got 'Everything Mode' — It Uses Your Computer, Remembers, and Runs for Days
OpenAI rolled Codex into an Everything Mode that unifies computer-use, long-horizon memory, and a multi-tool agentic loop. This is not code generation anymore — it is project-level operations running for days at a time.

ComposioHQ/awesome-codex-skills — Practical Codex Skills List, 4k Stars in a Week
An awesome-list of practical skills for the OpenAI Codex CLI/API. Workflows like automated PR review, migrations, test generation, and data pipelines you can trigger as a
AI 트렌드를 앞서가세요
매일 아침, 엄선된 AI 뉴스를 받아보세요. 스팸 없음. 언제든 구독 취소.
