https://amd-gaia.ai/docs Skip to main content GAIA SDK home pagelight logodark logo Search... [?]K * v0.17.2 * Lemonade 10.0.0 * Main Site * Download * Download Search... Navigation Getting Started Welcome Documentation Python Specifications Python Reference Python Deployment Roadmap Releases * GitHub * Discord * PyPI Getting Started * Welcome C++ Framework * Setup * Quickstart * Overview * Integration Guide * Testing * API Reference * C++ Security * User Guides Python Framework * Setup * Quickstart * Install GAIA * Agent UI * User Guides * Playbooks * SDK Reference On this page * Build AI Agents That Run Locally * Get Started * Capabilities * Resources Getting Started Welcome Copy page Build local AI agents in Python and C++ for AMD hardware. Copy page Build AI Agents That Run Locally GAIA is an open-source framework for building AI agents in Python and C++ that run entirely on local hardware. Agents reason, call tools, search documents, and take action -- with no cloud dependency and no data leaving the device. Local Inference All processing stays on-device No Cloud Dependency No API keys or external services required Python & C++ Full SDK in both languages AMD Optimized NPU and GPU acceleration on Ryzen AI * Python * C++ from gaia.agents.base.agent import Agent agent = Agent() response = agent.process_query("Summarize my meeting notes") #include gaia::Agent agent; auto result = agent.processQuery("Summarize my meeting notes"); Get Started Agent UI Install via npm and run AI agents locally -- two commands to get started. Python Quick Start Install GAIA, start Lemonade Server, and run your first agent. C++ Quickstart Build a native C++17 agent binary -- no Python runtime required. Capabilities * Python * C++ Agent UI Privacy-first desktop chat with drag-and-drop document Q&A. Install via npm or gaia --ui. Document Q&A (RAG) Retrieve, index, and answer questions over local PDFs, code, and text files. Speech-to-Speech Whisper ASR and Kokoro TTS -- offline voice interaction pipeline. Code Generation Multi-file code generation with validation, testing, and orchestration. Image Generation Multi-modal image generation with LLM prompt enhancement. MCP Integration Connect agents to external tools via Model Context Protocol. Agent Routing Intelligent request routing across multiple specialized agents. System Health Agent MCP-powered diagnostics -- CPU, memory, disk, network, and GPU monitoring. Wi-Fi Troubleshooter Diagnose and resolve wireless connectivity issues with registered tools. Custom Agents Build your own C++17 agent with tool registration and state management. MCP Integration Connect to MCP servers for extensible tool access. Resources SDK Reference Complete API documentation GitHub View source code Component Specs Technical specifications Glossary Technical terms explained Discord Join community --------------------------------------------------------------------- Was this page helpful? YesNo Setup [ ] [?]I githubdiscordtwitterlinkedin Powered byThis documentation is built and hosted on Mintlify, a developer documentation platform