AI-powered extension for Gemini CLI that creates custom agents through natural conversation
# Agent Creator Extension for Gemini CLI An AI-powered extension for [Gemini CLI](https://github.com/google-gemini/gemini-cli) that makes creating custom agents effortless through natural conversation. ## 🎯 What It Does This extension provides the `/new-agent` command that guides you through creating custom agent definitions using AI-assisted conversation. Instead of manually writing TOML files or filling out forms, you simply chat with the AI about what you want to build. ## ⚡ Quick Start ### Installation 1. **Clone this repository** into your Gemini extensions directory: ```bash git clone https://github.com/jduncan-rva/gemini-agent-creator.git ~/.gemini/extensions/agent-creator ``` 2. **Restart Gemini CLI** to load the extension 3. **Verify installation**: ```bash /extensions list ``` You should see `agent-creator` in the list. ### Usage #### Quick Mode (AI Expands Your Idea) Provide a brief description and let the AI flesh out a complete agent: ```bash /new-agent "reviews code for security vulnerabilities" ``` The AI will: 1. Analyze your description 2. Generate a comprehensive agent definition with smart defaults 3. Show you the complete TOML configuration 4. Ask for your approval before saving **Example descriptions:** - `"reviews python code for bugs"` - `"generates API documentation"` - `"writes unit tests for functions"` - `"explains complex code in simple terms"` - `"finds performance bottlenecks"` #### Interactive Mode (Guided Conversation) Run without arguments for step-by-step guidance: ```bash /new-agent ``` The AI will guide you through: 1. Defining what your agent does 2. Selecting which tools it needs 3. Writing its behavior and instructions 4. Defining input parameters 5. Reviewing the generated configuration 6. Saving to `~/.gemini/agents/` ## 📝 Example Session ### Quick Mode Example ``` > /new-agent "analyzes code for performance issues" Great! I'll create a performance analysis agent for you. Based on
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.