sci-ml/amd-gaia (bentoo)

Search

Install

Install this package:

emerge -a sci-ml/amd-gaia

Package Information

Description:
GAIA is AMD's agent framework for machines that run their models locally. It provides the CLI (gaia, gaia-cli), an MCP bridge (gaia-mcp), a chat and agent runtime, a RAG pipeline and a browser UI, and it drives all of them through an OpenAI-compatible HTTP endpoint. GAIA does not perform inference itself and contains no acceleration backend: it is a client. The server it is designed against is Lemonade (sci-ml/lemonade in this overlay), which is what reaches Ryzen AI NPU and iGPU hardware; any other OpenAI-compatible endpoint works too. Because the model is reached over HTTP and the code is pure Python, nothing in this package is architecture specific. Upstream ships a long list of optional extras. Only the ones whose every dependency is already packaged are exposed as USE flags here; the rest are documented, with the missing package named, in a comment in the ebuild rather than silently dropped. The browser UI bundle under gaia/apps/webui/dist is shipped pre-compiled by upstream and is installed as-is — this package needs no npm or Node.js at build time.
Homepage:
https://github.com/amd/gaia https://pypi.org/project/amd-gaia/
License:
MIT

Versions

Version EAPI Keywords Slot
0.23.0 8 ~amd64 ~arm64 0

Metadata

Description

Maintainers

Upstream

Raw Metadata XML
<pkgmetadata>
	<maintainer type="person">
		<email>lucascs@protonmail.com</email>
		<name>Lucas C.S.</name>
	</maintainer>
	<longdescription lang="en">
		GAIA is AMD's agent framework for machines that run their models
		locally. It provides the CLI (gaia, gaia-cli), an MCP bridge
		(gaia-mcp), a chat and agent runtime, a RAG pipeline and a browser UI,
		and it drives all of them through an OpenAI-compatible HTTP endpoint.

		GAIA does not perform inference itself and contains no acceleration
		backend: it is a client. The server it is designed against is Lemonade
		(sci-ml/lemonade in this overlay), which is what reaches Ryzen AI NPU
		and iGPU hardware; any other OpenAI-compatible endpoint works too.
		Because the model is reached over HTTP and the code is pure Python,
		nothing in this package is architecture specific.

		Upstream ships a long list of optional extras. Only the ones whose
		every dependency is already packaged are exposed as USE flags here;
		the rest are documented, with the missing package named, in a comment
		in the ebuild rather than silently dropped.

		The browser UI bundle under gaia/apps/webui/dist is shipped
		pre-compiled by upstream and is installed as-is — this package needs
		no npm or Node.js at build time.
	</longdescription>
	<use>
		<flag name="api">Pull in <pkg>dev-python/fastapi</pkg>, <pkg>dev-python/uvicorn</pkg> and <pkg>dev-python/httpx</pkg>, required by the local REST server (the "gaia api" command) and by the browser UI it serves</flag>
	</use>
	<upstream>
		<changelog>https://github.com/amd/gaia/releases</changelog>
		<doc>https://github.com/amd/gaia/blob/main/README.md</doc>
		<bugs-to>https://github.com/amd/gaia/issues</bugs-to>
		<remote-id type="github">amd/gaia</remote-id>
		<remote-id type="pypi">amd-gaia</remote-id>
	</upstream>
</pkgmetadata>

Lint Warnings

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

Flag Description 0.23.0
api Pull in <pkg>dev-python/fastapi</pkg>, <pkg>dev-python/uvicorn</pkg> and <pkg>dev-python/httpx</pkg>, required by the local REST server (the "gaia api" command) and by the browser UI it serves

Manifest

Type File Size Versions
Unmatched Entries
Type File Size
DIST amd_gaia-0.23.0.tar.gz 2108089 bytes