AMD GAIA is an open-source project on GitHub with about 1,597 stars, most recently updated in 2026. GAIA is AMD’s open-source agent factory for building AI agents that run locally on AMD Ryzen AI PCs. It combines coding-agent skills, evaluations and an auto-fix loop to build and improve agent harnesses, with local inference that keeps data private, avoids cloud usage fees and supports air-gapped deployment with hardware acceleration.
Published on GitHub under the MIT license, AMD GAIA has attracted a community of about 1,597 stars, which places it among the more visible open-source AI projects in its niche. Development was still active as of 2026, based on the repository’s latest updates. Because the full source code is public, teams can audit how it works, adapt it to their own stack, and self-host it rather than depending on a closed hosted product.
The repository is tagged with topics including agents, ai, aipc, amd, genai, which gives a quick picture of where it fits in the open-source AI ecosystem. New users can explore the examples and documentation in the repository to understand the main workflows before integrating it into their own projects, and the public issue tracker shows what the maintainers are actively working on and what the community is asking for.
GAIA is MIT-licensed open source from AMD and completely free; agents run on your own hardware, so there are no cloud inference bills.
AMD GAIA is best suited for developers and PC enthusiasts with AMD Ryzen AI hardware who want capable local agents without sending data to the cloud. Anyone evaluating it should start with the GitHub repository, where the documentation, examples and issue tracker show exactly what the current version can do.