Maker update: Launch Claude Code, Codex, Gemini CLI, and OpenCode from one place.
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.
Quick Launch lets you create API profiles once, then launch the right agent with the right config injected automatically.
Supported CLIs today:
- Claude Code
- Codex
- Gemini CLI
- OpenCode
Supported provider profiles include Azure OpenAI, DeepSeek, Moonshot/Kimi, MiniMax, OpenRouter, Gemini, Z.AI, and custom endpoints.
VibeAround understands which API kinds each provider supports and which API kinds each CLI can use, so it only shows valid launch options.
For example, Codex/OpenCode + Azure OpenAI Responses API can launch with the right base URL, model, API key, and reasoning effort without hand-editing config files.
How are you switching between multiple AI coding agents today?



Replies