🕵️ Multi-agent AI system template powered by Gemini CLI — automate daily ops with 10 specialized agents
# 🕵️ Project Phantom **A multi-agent AI system template powered by Gemini CLI.** Automate your daily operations with 10 specialized AI agents that collaborate, plan, and execute tasks — from GitHub project management to Gmail classification. ## ✨ Features - **10 specialized sub-agents** — each with a distinct role (strategist, executor, debugger, etc.) - **Gemini CLI native** — runs directly in your terminal, no extra infrastructure needed - **GitHub Project v2 integration** — automated task sync with Google Tasks - **Gmail auto-classification** — sorts emails into actionable categories using Gemini AI - **PDCA self-improvement** — agents log failures and learn from past mistakes - **Hook system** — pre/post tool execution guards (secret detection, git safety, etc.) ## 🚀 Quick Start ### Prerequisites **Supported OS:** Linux, macOS, Windows (WSL2 / Ubuntu recommended) | Tool | Version | Purpose | |------|---------|---------| | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | latest | Core runtime | | [Node.js](https://nodejs.org/) | v18+ | Gemini CLI dependency | | [Python](https://python.org/) | 3.10+ | Scripts & hooks | | [GitHub CLI](https://cli.github.com/) | latest | GitHub integration | | [Git](https://git-scm.com/) | latest | Version control | > **Windows users:** Tested on WSL2 (Ubuntu). Native PowerShell is not supported. See [Windows automated setup](#windows-automated-setup) below. **Required services:** - Google Workspace (Gmail, Google Drive, Google Tasks) - GitHub account with Project v2 - Claude API key ([Get one here](https://aistudio.google.com/apikey)) ### Installation #### Windows (automated setup) Right-click `setup/setup-windows.bat` → **Run as administrator**. The script will automatically install WSL, Ubuntu, Node.js, Gemini CLI, and GitHub CLI — then walk you through the rest. > **⚠️ Security software notice:** Some antivirus software (Norton, Windows Defender SmartScreen, etc.) may block `.bat` files from running. I
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.