Codex vs. Claude Code (Today)

Re:Codex vs. Claude Code (Today) by CjHuber on Friday December 26, 2025 @08:21AM (#46391722)

I do feel like the Codex CLI is quite a bit behind CC. If I recall correctly it took months for Codex to get the nice ToDo Tool Claude Code uses in memory to structure a task into substeps. Also I‘m missing the ability to have the main agent invoke subagents a lot.

All this of course can be added using MCPs, but it’s still friction. The Claude Code SDK is also way better than OpenAI Agents, it’s almost no comparison.

Also in general when I experienced bugs with Codex I was always almost sure to find an open GitHub issue with people already asking about a fix for months.

Still I like GPT-5.2 very much for coding and general agent tasks, and there is EveryCode which is a nice fork of Codex that mitigates a lot of shortcomings

[ Parent | on HN ]

Re:Codex vs. Claude Code (Today) by frwickst on Friday December 26, 2025 @08:30AM (#46391797)

You can use Every Code [1] (a Codex fork) for this, it can invoke agents, but not just codex ones, but claude and gemini as well.

[1] https://github.com/just-every/code

[ Parent | on HN ]

Re:Codex vs. Claude Code (Today) by CjHuber on Friday December 26, 2025 @08:41AM (#46391892)

Seems like you wrote at the same time I did my edit, yes Every Code is great however Ctlr+T is important to get terminal rendering otherwise is has performance problems for me

[ Parent | on HN ]

Re:Codex vs. Claude Code (Today) by sumedh on Friday December 26, 2025 @08:32AM (#46391814)

> with people already asking about a fix for months.

OpenAI needs to get access to Claude Code to fix them :)

[ Parent | on HN ]

Re:Codex vs. Claude Code (Today) by dist-epoch on Friday December 26, 2025 @08:56AM (#46392005)

The general consensus today is that ToDo tool is obsolete and lowers performance for frontier models (Opus 4.5, GPT-5.2)

[ Parent | on HN ]