VibeAround v0.5.3: smoother local agent workflow with OpenAI Chat API providers like DeepSeek V4

VibeAround v0.5.3 is live!

The big update: Codex can now work with OpenAI Chat API-compatible providers through VibeAround.

That means you can run Codex locally, but route it through providers such as DeepSeek V4 or other OpenAI-compatible endpoints without constantly editing config files or changing your global setup.

VibeAround is built for people who want to keep coding agents local, while making them easier to launch, resume, and reach from different devices.

Also new in 0.5.3:

• Launch profile proxy support for Codex

• DeepSeek reasoning replay from Codex sessions

• Better launch profiles and tray launch entries

• Draggable profile ordering

• Default profile highlighting

• More reliable preview isolation by workspace and port

• UTF-8 safe prompt log previews

• A sturdier process supervisor underneath agents, channels, and tunnels

The goal is simple: keep your coding agents local, but make them reachable from IM, browser, terminal, or phone, with less provider setup friction.

Would love feedback from Codex users, especially if you use OpenAI-compatible providers or switch between multiple API profiles.

Download: https://github.com/jazzenchen/VibeAround/releases/tag/v0.5.3