openai/codex

This came as a big surprise to me last year. I remember they announced that Codex CLI is opensource, and the codex-rs [0] from TypeScript to Rust, with the entire CLI now open source. This is a big deal and very useful for anyone wanting to learn how coding agents work, especially coming from a major lab like OpenAI. I've also contributed some improvements to their CLI a while ago and have been following their releases and PRs to broaden my knowledge. [0] https://github.com/openai/codex/tree/main/codex-rs

This is how I did it - https://github.com/openai/codex/blob/main/docs/config.md#model_providers I have it go to openrouter, and then you just export the API key and run codex, works smoothly.

…opy the file over and then make package-specific changes, so maybe better tool calling is at play here. Additionally, they claim the new model is more steerable (both with AGENTS.md and generally). In my experience, Codex CLI w/gpt-5 is already a lot more steerable than Claude Code, but any improvements are welcome! [0] https://github.com/openai/codex/blob/main/codex-rs/core/gpt_5_codex_prompt.md [1] https://github.com/openai/codex/blob/main/codex-rs/core/prompt.md (comment reposted from other thread)

> It’s a shame I cannot inspect the tool. It’s a shame I cannot modify it as I see fit. https://github.com/openai/codex https://github.com/MoonshotAI/kimi-code https://github.com/mistralai/mistral-vibe https://github.com/earendil-works/pi https://claude.com/de/resources/articles/claude-code-mods

Test-drive it with an individual Pro account (5x or 20x) for a month. Download the Codex CLI client from https://github.com/openai/codex and auth it in the browser via the URL it provides. Set the model to 5.6-Sol and effort to max.

You can absolutely do that by using subprocess.run, or use the codex sdk https://github.com/openai/codex/tree/main/sdk/python

The best part about this blog post is that none of it is a surprise – Codex CLI is open source. It's nice to be able to go through the internals without having to reverse engineer it. Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs. https://github.com/openai/codex

…t you're writing something that has a real likelihood to to be monetized and want to specifically prevent that problem. A very real example of that is that Ratatui (MIT license) and Codex (Apache2). I feel comfortable reading and using code and ideas from either side and have them influence the design of the other side [1][2]. I don't feel comfortable in the same way reading any GPL licensed code (2 or 3) due to the inherent legal risk that entails. Your personal views on software freedoms definitely trump my personal opinion as a developer here, so I'm not too stressed if you disagree with this. A solid amount of crates in the rust ecosystem are MIT or Apache 2 (or both), and I really enc…

Maybe, there are a few different things named "Codex" from OpenAI (yes, needlessly confusing) - "Codex" is a git-centric product, the other is the GPT-5-Codex agentic coder model. I recommend installing the Codex CLI if you're able to and selecting the model via `/model`. npm install -g @openai/codex https://github.com/openai/codex

If OpenAI's super-intelligence can solve Navier-Stokes why can't they fix this stupid bug that ate up 330GB of my Mac's disk space? come one please triage your github issues? See this: https://github.com/openai/codex/issues/25921#issuecomment-6237799309

As an almost-on-topic aside: completely unrelated to this comment, I just stumbled upon this delight: https://github.com/openai/codex/issues/53743 If you thought that your agents in your swarm would need to find some external bulletin board to cooperate behind your back, you are mistaken: OpenAI provides the relevant service for them with no permission prompts at all. I haven't tried to see whether competing providers do this.

Recently they broke the most essential thing you can do in TUI - copying the text selected with the mouse: https://github.com/openai/codex/issues/48125

My complaint applies specifically to the CLI. I have never used the gui app. Here are the various goal-breaking bugs I've run into: - Goals get blocked due to .git and other stuff becoming randomly read-only when daemon auto-updates in the background (the linked issue in my comment above) - Goals get blocked due to transient "Selected model is at capacity" - Goals get blocked due to "Codex ran out of room in the model's context window". Somehow, both auto-compaction and manually running /compact don't work. https://github.com/openai/codex/issues/52567#issuecomment-6118065593 - Goals get blocked due to bwrap randomly failing with `bwrap: loopback: Failed RTM_NEWADDR: Operation not permitt…

Yep, the real issue is that it was something they didn’t have before, and then with Codex 0.157.0 enabled, they installed this persistent nonsense [1] that survives after the last instance of Codex has exited on your machine, which is just gross. codex features disable daemon_auto_start codex app-server daemon stop pkill -f 'app-server daemon pid-update-loop' [1] - https://github.com/openai/codex/issues/48195