tmux for AI Agents — Orchestrate multiple AI coding agents (Codex, Gemini, Claude) in parallel with one command.
# 🔄 Vibe-Switch [](https://www.npmjs.com/package/vibe-switch) [](https://opensource.org/licenses/MIT) [](https://nodejs.org) > **tmux for AI Agents** — Orchestrate multiple AI coding agents in parallel with one command. > > 🤖 **AI Agents**: If you are an AI coding assistant, see [docs/ai-skill.md](./docs/ai-skill.md) for the machine-readable command reference and orchestration guide. [繁體中文](./README.zh-TW.md) | [简体中文](./README.zh-CN.md) | [日本語](./README.ja.md) | English ## Why Vibe-Switch? Whether you are running commands yourself or letting an AI orchestrator dispatch agents on your behalf, managing multiple AI agents is a cognitive nightmare. If you are a developer using Claude Code, Codex, and Gemini CLI simultaneously, you often face: - **Terminal Overload:** Dozens of open windows for different tasks. - **Context Loss:** Manually copying files and diffs between agents to "hand off" work. - **Process Chaos:** Forgetting which agent is working on which branch or how to stop them all. **Vibe-Switch** provides a unified CLI to orchestrate multiple agents in isolated environments with seamless context handoff. ## Install ```bash npm install -g vibe-switch ``` Or install from source: ```bash git clone https://github.com/brianjhang/vibe-switch.git cd vibe-switch npm install npm run build npm link ``` > 💡 After installing, the CLI command is **`vibe`** (not `vibe-switch`). Both `vibe` and `vibe-switch` work, but all examples use `vibe` for brevity. ## Quick Start ### 1. Run Multiple Agents Start different tasks with different agents in one line: ```bash # Backend task with Gemini vibe run "Implement JWT authentication middleware" --agent gemini # Frontend task with Codex vibe run "Build a responsive login page with React" --agent codex ``` ### 2. Check S
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.