Gentoo Packages

Search

Install

Install this package:

emerge -a sci-ml/amd-gaia

Package Information

Description:

GAIA is AMD's open-source agent framework for local AI agents on Ryzen AI hardware (NPU + iGPU). It orchestrates LLM-driven workflows over any OpenAI-compatible inference endpoint, with built-in integrations for Docker, Jira, code-search, RAG, MCP servers, and Whisper / Kokoro voice pipelines. The reference local backend is Lemonade Server (sci-ml/lemonade); GAIA itself is hardware-agnostic so long as the upstream LLM API is OpenAI-compatible.

Homepage:

https://github.com/amd/gaia

License:

MIT

Versions

Metadata

Description

• GAIA is AMD's open-source agent framework for local AI agents on Ryzen AI hardware (NPU + iGPU). It orchestrates LLM-driven workflows over any OpenAI-compatible inference endpoint, with built-in integrations for Docker, Jira, code-search, RAG, MCP servers, and Whisper / Kokoro voice pipelines. The reference local backend is Lemonade Server (sci-ml/lemonade); GAIA itself is hardware-agnostic so long as the upstream LLM API is OpenAI-compatible.

Maintainers

• Ivan S. Titov (iohann.s.titov@gmail.com) - Type: person

Upstream

• Remote IDs:
  • github: amd/gaia
  • pypi: amd-gaia

<pkgmetadata>
	<maintainer type="person">
		<email>iohann.s.titov@gmail.com</email>
		<name>Ivan S. Titov</name>
	</maintainer>
	<longdescription lang="en">
    GAIA is AMD's open-source agent framework for local AI agents on
    Ryzen AI hardware (NPU + iGPU). It orchestrates LLM-driven workflows
    over any OpenAI-compatible inference endpoint, with built-in
    integrations for Docker, Jira, code-search, RAG, MCP servers, and
    Whisper / Kokoro voice pipelines. The reference local backend is
    Lemonade Server (sci-ml/lemonade); GAIA itself is hardware-agnostic
    so long as the upstream LLM API is OpenAI-compatible.
  </longdescription>
	<use>
		<flag name="api">Install FastAPI / uvicorn HTTP-server bindings (gaia.api)</flag>
		<flag name="eval">Install evaluation harness deps (anthropic, reportlab, tiktoken; scikit-learn before 0.25, pyarrow from 0.25) for gaia.eval benchmarks</flag>
		<flag name="image">Pull dev-python/term-image for terminal-rendered image output (gaia.image)</flag>
		<flag name="mcp">Install Model Context Protocol client/server support (gaia.mcp)</flag>
		<flag name="talk">Pull sounddevice (audio I/O) for gaia.talk's voice pipeline; Whisper and Kokoro run inside Lemonade Server</flag>
		<flag name="ui">Build the gaia.ui web frontend (FastAPI + faiss-backed RAG over documents via PyMuPDF; sentence-transformers before 0.25); requires +api</flag>
	</use>
	<upstream>
		<remote-id type="github">amd/gaia</remote-id>
		<remote-id type="pypi">amd-gaia</remote-id>
	</upstream>
</pkgmetadata>

Lint Warnings

• [Warning] Ebuild 0.25.3 has a line exceeding 80 positions on line 14.
• [Warning] Ebuild 0.25.3 has a line exceeding 80 positions on line 38.
• [Warning] Ebuild 0.25.3 has a line exceeding 80 positions on line 45.
• [Warning] Ebuild 0.25.3 has a line exceeding 80 positions on line 122.
• [Warning] Ebuild 0.25.1 has a line exceeding 80 positions on line 14.
• [Warning] Ebuild 0.25.1 has a line exceeding 80 positions on line 38.
• [Warning] Ebuild 0.25.1 has a line exceeding 80 positions on line 45.
• [Warning] Ebuild 0.25.1 has a line exceeding 80 positions on line 122.
• [Warning] Ebuild 0.25.0 has a line exceeding 80 positions on line 14.
• [Warning] Ebuild 0.25.0 has a line exceeding 80 positions on line 38.
• [Warning] Ebuild 0.25.0 has a line exceeding 80 positions on line 45.
• [Warning] Ebuild 0.25.0 has a line exceeding 80 positions on line 119.
• [Notice] Package has only unstable keywords for arch(es): [ amd64 ], all versions are unstable: [ 0.25.0, 0.25.1, 0.25.3 ]

USE Flags

Manage flags for this package: euse -i <flag> -p sci-ml/amd-gaia | euse -E <flag> -p sci-ml/amd-gaia | euse -D <flag> -p sci-ml/amd-gaia

Manifest