VibeAround v0.6.3 is out.

This release wraps up the bigger v0.6.x shift: VibeAround is becoming a hub for coding agents across desktop, web, terminal, and messaging.

The biggest visible change since v0.5.x is the Web experience: it is now a web-based workspace for running different coding agents side by side, one place to launch, resume, inspect, and switch between agents.

From the browser, you can now:

VibeAround v0.6.4 is out: https://github.com/jazzenchen/Vi...

This is a major continuity release. VibeAround now uses WorkspaceThread as the core runtime model, so IM and Web Chat can rejoin the same workspace-level thread while Codex, Claude, and other host agents keep their own resumable sessions underneath.

Highlights:

I published the first technical note in the AI API Bridge series for VibeAround.

It compares OpenAI Chat Completions and Responses structurally, and explains what has to be preserved when building a bridge between them.

Gist: https://gist.github.com/jazzench...

VibeAround v0.5.12 is live.

This release is mostly about making the daily local-agent workflow feel less fragile: launch the right coding agent, point it at the right provider profile, keep API translation out of your global config, and get back to coding.

What changed:

Better Codex launch support, including trusted launch hook handling.

VibeAround v0.5.15 is live.

This release is about making the local-agent workflow more reliable across more model providers and coding agents, especially if you use Gemini, Vertex AI, DashScope, DeepSeek, Kimi/Moonshot, or Codex with API Bridge-routed third-party models.

What changed:

- Gemini CLI is now a first-class connection target.

VibeAround v0.5.8 is live.

This release is a bigger rewrite of the Launch/Profile system, plus a more capable local API Bridge for coding agents.

The main idea: use the local coding agent you like, but route it to more model providers without constantly editing config files.

What changed:

This release makes coding-agent launch profiles easier to use across more providers and agents. Saved provider profiles can now be exposed through VibeAround s local API Bridge, so tools like Claude Code, Codex, and other compatible agents can connect with less manual setup.

The big update:

Local API Bridge: Use saved provider profiles as local agent endpoints for Claude Code, Codex, and other compatible tools.

More provider routes: DeepSeek, Kimi, MiniMax, Z.AI/GLM, and custom OpenAI-compatible endpoints now work better through profile-backed launch routes.

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.

One part of VibeAround that is easy to miss: your local coding agent can generate a preview link from an IM chat, then pair your phone browser with a short code.

That means you can check:

- Live local web pages from your phone

Just added a new Quick Launch module to VibeAround.

The problem: every AI coding CLI has its own config files, env vars, model names, API endpoints, and terminal behavior. If you use multiple agents or providers, switching gets messy fast.