VibeAround v0.6.3: a web workspace for multiple coding agents
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:
- Start Claude Code, Codex CLI, Gemini CLI, OpenCode, and other agents
- Resume previous sessions
- Switch between agents and provider profiles
- Review code changes with rendered diff views
- Attach files, images, and documents
- Control thinking/tool visibility
- Open Web Terminal for local PTY sessions
- Launch live previews for dev servers, Markdown, and HTML
v0.6.3 also cleans up the model-routing layer:
- Renamed the old API proxy wording to API Bridge across the app, docs, profile routing, and launch UI
- Published the bridge layer as an independent Rust crate: va-ai-api-bridge, nicknamed va-aab
- VibeAround now consumes va-ai-api-bridge from crates.io instead of a submodule/local checkout
- Bridge routes remain compatible with OpenAI Responses, OpenAI Chat Completions, Anthropic Messages, and Gemini Generate Content
- Improved IM command workflow controls
- Refreshed dependencies and release packaging
Release:
https://github.com/jazzenchen/VibeAround/releases/tag/v0.6.3
Bridge crate:
https://crates.io/crates/va-ai-api-bridge
Feedback is very welcome, especially from people using multiple coding agents or non-default model providers.
Replies
The side by side agent workflow is probably the most interesting part here, managing multiple coding agents across different interfaces still feels fragmented in most tools . Nice direction for simplifying that experience.
VibeAround
@jared_coleman Exactly. That fragmentation is the main pain I am trying to reduce.
There are already many good coding agents, but they often live in separate terminals, desktop apps, or provider-specific flows. VibeAround's web workspace is meant to give them one shared operating surface: launch, resume, inspect, preview, and switch without constantly changing tools.
Side-by-side agents is a strong idea, does it help compare results easily?
VibeAround
@sanjau_sanjay Yes, that is definitely where I want to go.
Today, side-by-side agents already make it easier to inspect different sessions, diffs, and previews in one place. A more explicit comparison workflow is on the roadmap.
The direction I am excited about is comparing freely across model and agent combinations: different models in the same agent, the same model across different agents, or different provider profiles running the same task.
The ability to attach files images and documents while comparing outputs across agents could make this a strong research and debugging environment too.
VibeAround
@bernard_lewis Totally agree. I already have file uploads in place for files, images, and documents, which makes VibeAround useful for research and debugging workflows where the agent needs more context than plain text.
The next step I want to add is the other direction: when an AI agent produces files, VibeAround should return them as proper download links, so generated artifacts are easy to inspect, save, and pass between devices or sessions.
The rendered diff reviews and live previews are a huge quality of life upgrade. Makes the workflow feel closer to a real IDE experience.
This is basically the multi-agent IDE moment getting formalized. Feels like the real unlock isn’t any single coding agent it’s the orchestration layer where you can actually run, compare, and manage them like worker in parallel.
VibeAround
@kathe__jordan Yes, that multi-agent IDE framing is very close to how I think about it.
I do not believe the unlock is one agent to rule them all. It is a workspace where different agents, models, provider profiles, terminals, diffs, and previews can be managed together without constantly switching mental context.
bem interessante