adk-code π AI coding assistant for your terminal. Powered by Google's ADK framework with multi-model support (Gemini π·, OpenAI π’, Vertex AI βοΈ). First ADK code agent in Go! π―
# adk-code > **An intelligent CLI coding assistant powered by Google's ADK framework** [](https://golang.org) [](LICENSE) [](https://github.com/raphaelmansuy/adk-code) ## What is adk-code? `adk-code` is a **multi-model AI coding assistant** that runs directly in your terminal. Ask natural language questions about your codeβit reads files, executes commands, makes edits, and runs searches autonomously. ### Key Features - **π€ Multi-Model Support**: Seamlessly switch between Gemini, OpenAI, and Vertex AI - **π οΈ 30+ Built-in Tools**: File operations, code editing, execution, Google Search, HTTP fetch, agent discovery, and more - **π MCP Integration**: Unlimited extensibility via Model Context Protocol - **πΎ Session Persistence**: Maintain context across conversations with automatic history and token-aware compaction - **π Web Integration**: Google Search and HTTP fetch tools for research and content retrieval - **β‘ Streaming Responses**: Real-time output as the model thinks and executes - **π¨ Beautiful Terminal UI**: Rich formatting, colors, pagination, and interactive displays - **π¦ Zero External Dependencies**: No Langchain, Claude Code, or Cline baggage ## Quick Start ### Installation #### Option A: Homebrew (macOS) β Recommended The easiest way to install on macOS: ```bash # Add the tap (one-time) brew tap raphaelmansuy/adk-code # Install adk-code brew install adk-code # Verify installation adk-code --version ``` **Supported on:** - macOS 10.13+ (High Sierra and later) - Intel (x86_64) and Apple Silicon (M-series) Macs **Update to latest:** ```bash brew upgrade adk-code ``` **Uninstall:** ```bash brew uninstall adk-code ``` See [homebrew-adk-code](https://github.com/raphaelmansuy/homeb
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.