Skip to main content

GAIA is a lightweight agent framework designed for the edge and AI PCs.

Project description

GAIA Logo GAIA: AI Agent Framework for AMD Ryzen AI

GAIA Build Installer GAIA CLI Tests Latest Release PyPI GitHub downloads OS - Windows OS - Linux Python 3.10+ License: MIT Discord

GAIA is AMD's open-source framework for building intelligent AI agents that run 100% locally on AMD Ryzen AI hardware. Keep your data private, eliminate cloud costs, and deploy in air-gapped environments—all with hardware-accelerated performance.

Get Started →


Why GAIA?

Feature Description
100% Local All data stays on your machine—perfect for sensitive workloads and air-gapped deployments
Zero Cloud Costs No API fees, no usage limits, no subscriptions—unlimited AI at no extra cost
Privacy-First HIPAA-compliant, GDPR-friendly—ideal for healthcare, finance, and enterprise
Ryzen AI Optimized Hardware-accelerated inference using NPU + iGPU on AMD Ryzen AI processors

Build Your First Agent

from gaia.agents.base.agent import Agent
from gaia.agents.base.tools import tool

class MyAgent(Agent):
    """A simple agent with custom tools."""

    def _get_system_prompt(self) -> str:
        return "You are a helpful assistant."

    def _register_tools(self):
        @tool
        def get_weather(city: str) -> dict:
            """Get weather for a city."""
            return {"city": city, "temperature": 72, "conditions": "Sunny"}

agent = MyAgent()
result = agent.process_query("What's the weather in Austin?")
print(result)

See the full quickstart guide →


Key Capabilities

  • Agent Framework — Base class with tool orchestration, state management, and error recovery
  • RAG System — Document indexing and semantic search for Q&A
  • Voice Integration — Whisper ASR + Kokoro TTS for speech interaction
  • Vision Models — Extract text from images with Qwen2.5-VL
  • Plugin System — Distribute agents via PyPI with auto-discovery
  • Web UI Packaging — Generate modern interfaces for your agents

Quick Install

pip install amd-gaia

For complete setup instructions including Lemonade Server, see the Quickstart Guide.


System Requirements

Requirement Minimum Recommended
Processor AMD Ryzen AI 300-series AMD Ryzen AI Max+ 395
OS Windows 11, Linux -
RAM 16GB 64GB

Documentation

  • Quickstart — Build your first agent in 10 minutes
  • SDK Reference — Complete API documentation
  • Guides — Chat, Voice, RAG, and more
  • FAQ — Frequently asked questions

Contributing

We welcome contributions! See our Contributing Guide for details.

  • Build agents in your own repository using GAIA as a dependency
  • Improve the framework — check GitHub Issues for open tasks
  • Add documentation — examples, tutorials, and guides

Contact


License

MIT License

Copyright(C) 2024-2025 Advanced Micro Devices, Inc. All rights reserved. SPDX-License-Identifier: MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

amd_gaia-0.14.3.tar.gz (764.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

amd_gaia-0.14.3-py3-none-any.whl (751.3 kB view details)

Uploaded Python 3

File details

Details for the file amd_gaia-0.14.3.tar.gz.

File metadata

  • Download URL: amd_gaia-0.14.3.tar.gz
  • Upload date:
  • Size: 764.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for amd_gaia-0.14.3.tar.gz
Algorithm Hash digest
SHA256 bf1cfa92695969718fcfe913083054effe221c9f10aeb7b210bf474f33d5771b
MD5 781e807ea9865bc02a46e8dc17d9ee33
BLAKE2b-256 eaae153afe53a25bf0a387a942712146548160194d885f9079636850c7986e08

See more details on using hashes here.

File details

Details for the file amd_gaia-0.14.3-py3-none-any.whl.

File metadata

  • Download URL: amd_gaia-0.14.3-py3-none-any.whl
  • Upload date:
  • Size: 751.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for amd_gaia-0.14.3-py3-none-any.whl
Algorithm Hash digest
SHA256 a26d311ab8c5d5b95496127129a7802d89a22ab99c4d071fa31ef7582a5b820a
MD5 a613f6dac29b55ad8736a52edbbefaae
BLAKE2b-256 69914588c73a2ed3525413f7bf1967a09d8e0904f1d9db64647637a5cf5cbf0d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page