It's great. Much stronger on the UX side for things that devs need than Claude / Codex. Feels like the issue tracker isn't a black hole. Release notes aren't "Fixes and unicorns", but real links to PRs. I use both Codex and Claude models in it, often interchangably - sub agents from one to the other as needed.
(Bias, I'm more familiar with Codex than Claude as I worked on Codex when I was at OpenAI, but mainly on the TUI not the app - take my better than Claude with a grain of salt perhaps).
(Bias, I'm more familiar with Codex than Claude as I worked on Codex when I was at OpenAI, but mainly on the TUI not the app - take my better than Claude with a grain of salt perhaps).