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 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 →


Download

Download for Windows Download for macOS Download for Linux

See the installation guide for setup instructions.


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
  • Agent UI — Privacy-first desktop app with chat, file browser, document indexing, and tool execution
  • RAG System — Document indexing and semantic search for Q&A over 50+ file formats
  • Voice Integration — Whisper ASR + Kokoro TTS for speech interaction (P0 enabling technology)
  • Vision Models — Extract text from images with Qwen3-VL-4B
  • MCP Integration — Connect to any MCP server for external tool access
  • Plugin System — Distribute agents via PyPI with auto-discovery

C++ Framework

A C++17 port of the GAIA base agent framework is available under cpp/. It implements the same agent loop, tool registry, and MCP client interface without any Python dependency — suitable for embedding in native applications or resource-constrained environments.

#include <gaia/agent.h>

class MyAgent : public gaia::Agent {
protected:
    std::string getSystemPrompt() const override {
        return "You are a helpful assistant.";
    }
};

C++ build and usage instructions →


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

Releases

See the full Release Notes on the documentation site, or browse GitHub Releases.

Release Process

To publish a new release (e.g. v0.17.0), create a release PR that updates these 3 files:

# File What to change
1 src/gaia/version.py Set __version__ = "0.17.0"
2 docs/releases/v0.17.0.mdx Create release notes (see format guide)
3 docs/docs.json (a) Add "releases/v0.17.0" to the Releases tab pages array, (b) update the navbar label to "v0.17.0 · Lemonade X.Y.Z"

Then merge and tag:

git tag v0.17.0 && git push origin v0.17.0

CI validates all three files are consistent with the tag before publishing to GitHub Releases and PyPI.


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) 2024-2026 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-0.17.3.tar.gz (1.1 MB view details)

Uploaded Source

Built Distribution

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

amd_gaia-0.17.3-py3-none-any.whl (1.1 MB view details)

Uploaded Python 3

File details

Details for the file amd_gaia-0.17.3.tar.gz.

File metadata

  • Download URL: amd_gaia-0.17.3.tar.gz
  • Upload date:
  • Size: 1.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for amd_gaia-0.17.3.tar.gz
Algorithm Hash digest
SHA256 50fc8caa21e3bc10ba58807fefb5d56c5558711dfe13dfafb48a0b22158b9af1
MD5 ab6fcb32ca70487067a9d7bc20a59683
BLAKE2b-256 615a2c0e495cf4c6c95120be0d406a39aca020ccfdb331d6e6538a25f93ae124

See more details on using hashes here.

Provenance

The following attestation bundles were made for amd_gaia-0.17.3.tar.gz:

Publisher: publish.yml on amd/gaia

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amd_gaia-0.17.3-py3-none-any.whl.

File metadata

  • Download URL: amd_gaia-0.17.3-py3-none-any.whl
  • Upload date:
  • Size: 1.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for amd_gaia-0.17.3-py3-none-any.whl
Algorithm Hash digest
SHA256 58adce5151c16b4b250a86b030955606072b507e84fd18c273a5cbc878f5cbb0
MD5 cd16be095769372cb1768f0de0acac07
BLAKE2b-256 4c2ad829af4f9161989ef41a97b7158c4099748b9f63e473e336c698c424e7ed

See more details on using hashes here.

Provenance

The following attestation bundles were made for amd_gaia-0.17.3-py3-none-any.whl:

Publisher: publish.yml on amd/gaia

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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