Source URL: https://simonwillison.net/2025/May/16/openai-codex/#atom-everything
Source: Simon Willison’s Weblog
Title: OpenAI Codex
Feedly Summary: OpenAI Codex
Announced today, here’s the documentation for OpenAI’s “cloud-based software engineering agent". It’s not yet available for us $20/month Plus customers ("coming soon") but if you’re a $200/month Pro user you can try it out today.
At a high level, you specify a prompt, and the agent goes to work in its own environment. After about 8–10 minutes, the agent gives you back a diff.
You can execute prompts in either ask mode or code mode. When you select ask, Codex clones a read-only version of your repo, booting faster and giving you follow-up tasks. Code mode, however, creates a full-fledged environment that the agent can run and test against.
It sounds similar to GitHub’s own Copilot Workspace project, which can compose PRs against your code based on a prompt. The big difference is that Codex incorporates a full Code Interpeter style environment, allowing it to build and run the code it’s creating and execute tests in a loop.
Copilot Workspaces has a level of integration with Codespaces but still requires manual intervention to help exercise the code.
Also similar to Copilot Workspaces is a confusing name. OpenAI now have four products called Codex:
OpenAI Codex, announced today.
Codex CLI, a completely different coding assistant tool they released a few weeks ago that is the same kind of shape as Claude Code. This one owns the openai/codex namespace on GitHub.
codex-mini, a brand new model released today that is used by their Codex product. It’s a fine-tuned o4-mini variant. I released llm-openai-plugin 0.4 adding support for that model.
OpenAI Codex (2021) – Internet Archive link, OpenAI’s first specialist coding model from the GPT-3 era. This was used by the original GitHub Copilot and is still the current topic of Wikipedia’s OpenAI Codex page.
My favorite thing about this most recent Codex product is that OpenAI shared the full Dockerfile for the environment that the system uses to run code – in openai/codex-universal on GitHub because openai/codex was taken already.
This is extremely useful documentation for figuring out how to use this thing – I’m glad they’re making this as transparent as possible.
Tags: ai-assisted-programming, generative-ai, ai-agents, openai, ai, github, llms
AI Summary and Description: Yes
Summary: The announcement of OpenAI Codex introduces a cloud-based software engineering agent that empowers users to automate coding tasks using a unique environment. It features two execution modes—ask mode and code mode—meeting the needs of software developers by integrating closely with repositories and allowing for rapid testing and iteration. This innovation has significant implications for AI in software development and DevSecOps methodologies.
Detailed Description: OpenAI Codex is a newly announced cloud-based software engineering agent that represents a significant advancement in AI-assisted programming. Here are the major points of interest:
– **Cloud-based Software Engineering Agent**: Codex operates in a dedicated environment where users can specify prompts for coding tasks.
– **Execution Modes**:
– **Ask Mode**: This mode clones a read-only version of the user’s repository, allowing for efficient follow-up tasks without risking alterations to the original code.
– **Code Mode**: This mode sets up a complete environment for the agent, enabling it to create, run, and test code automatically.
– **Integration with GitHub**: Codex has similarities with GitHub Copilot Workspace, sharing concepts but extending functionality with its robust Code Interpreter style that allows for continuous testing.
– **Transparency and Documentation**: OpenAI has provided a full Dockerfile for the operating environment on GitHub, enhancing transparency and offering a practical guide for users.
– **Multiple Codex Products**: OpenAI has released various versions of Codex, including Codex CLI and codex-mini, illustrating an expanding range of tooling for developers across different needs.
Overall, OpenAI Codex enhances AI capabilities in software development through improved automation and integration, which is particularly relevant for engineers focused on security and compliance in DevSecOps contexts. This development invites professionals to explore how such tools could streamline workflows, enhance code security, and support rigorous testing and compliance practices in their infrastructure.