VibeAround v0.7.7: Local Agent API, remote sessions, managed toolchains

I’ve been shipping VibeAround pretty actively recently, and v0.7.7 is one of the bigger workflow updates so far.

VibeAround is an all-in-one hub for AI coding agents. The goal is to keep the agents you already use, such as Claude Code, Codex CLI, Gemini CLI, OpenCode, Claude Desktop, and Codex Desktop, in one workflow: launch, bridge, inspect, continue, preview, and control them across devices.

What’s new in v0.7.7:

Local Agent API
Expose local Claude / Codex-style agents as OpenAI / Anthropic-compatible APIs for development and local testing.
Remote / IM session continuity
Better handover and pickup across desktop, mobile, browser, and IM channels, with per-channel default session routing.
Managed toolchain mode
More consistent agent resolution across launch, PTY, ACP, IM sessions, and Startkit, while still respecting manual executable paths.
UI and workflow polish
Refined Remote Dashboard settings, Local API Workbench, model picker details, default workspace controls, launch headers, and several dense settings surfaces so the app is easier to scan and operate.
Provider catalog and model picker updates
Refreshed model/provider metadata for Kimi, DashScope, Volcengine, ZAI, MiMo, MiniMax, and other compatible API providers.
Launch and request inspection improvements
Cleaner Claude / Codex launch behavior, no temporary Claude settings rewrites, and better inspection of original requests, bridged requests, raw responses, and bridged responses.
Windows stability fixes
Fixed daemon restart and stale port issues on Windows.