Codex
OpenAI just released Codex, a “Lightweight coding agent that runs in your terminal”
Codex CLI is built for developers who already live in the terminal and want ChatGPT‑level reasoning plus the power to actually run code, manipulate files, and iterate – all under version control. In short, it’s chat‑driven development that understands and executes your repo.
We can think about Codex as a competitor to Claude Code. They are both agentic coding agents.
Anthropic recently released a Best-Practices for Agentic Coding guide on April 18th, 2025 which followed the open-source release of the Codex CLI on April 16th, 2025.
OpenAI is building in public with this one, similar to what they did with Swarm and are calling it an “experimental project.”
Experimental Technology Disclaimer Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. We’re building it in the open with the community and welcome:
Bug reports
Feature requests
Pull requests
Good vibes
Help us improve by filing issues or submitting PRs (see the section below for how to contribute)!
OpenAI Codex was originally released on August 10, 2021. At that time, we learned:
Codex is the model that powers GitHub Copilot, which we built and launched in partnership with GitHub a month ago.
Subsequently, in March 2023, Codex models were deprecated. Now they have reemerged as agents; as open-source projects. As something entirely new and nearly unrelated to the original codex models.
Today, Claude helps to power the AI Code Editor Cursor, a fork of VS Code and the most popular AI Code Editor in the world. Will OpenAI’s codex CLI help to power Windsurf, another AI Code Editor? There are some rumors swirling.
We’ll discuss what we know about the state of AI Code Editors and Coding Agents of various kinds (e.g., Claude Code, Manus, Devin, etc.), and the role that we should expect CLI-based tools like Codex to play in our software engineering workflows now and moving forward.
In the age of vibe coding, coding agents appear to be gaining momentum and steam. Join us to dive into understanding how we should be using them with or without code editors in 2025 and moving forward.
📚 You’ll learn:
What a Coding Agent does, and what the best-practices are for using coding agents today
How to use Codex CLI in your workflows today, and whether it should be considered a new best-practice open-source tool
How Anthropic and OpenAI’s options compare with one another today, and how we expect this space to evolve moving forward.
🤓 Who should attend the event:
AI Engineers who want to build with the latest open-source agent tooling
AI Engineers looking to increase their personal productivity with coding agents.
AI Engineering leaders interested in increasing their team’s productivity with AI Code Editors.
Speaker Bios
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.