# amd/gaia

Build AI agents for your PC

Repository: https://github.com/amd/gaia
Canonical: https://ross.abutalabs.com/products/amd-gaia
Homepage: https://github.com/amd/gaia
Language: Python
License: MIT
License Family: permissive
Topics: ai, amd, genai, ryzenai, agents, aipc, local, privacy
Last push: 2026-08-26T18:08:48+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 44
- inputs: {"age_days": 626, "days_push": 7, "days_rel": 20, "gap_med": 6.5, "n_releases_24m": 47}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1530, forks 162 (observed 2026-08-28T04:04:58.758195+00:00)

## What it is
GAIA is AMD's open-source Python framework for building AI agents that run entirely locally on AMD Ryzen AI hardware, using NPU and iGPU acceleration. It includes a CLI, TUI, and SDK for creating privacy-first agents without cloud dependencies.

## Use cases
- build ai agents that run locally on my pc
- run llm agents offline without cloud api costs
- deploy ai agents in air-gapped environments
- build privacy-first chatbot for sensitive data
- use amd ryzen ai npu for local inference
- create local ai assistant for healthcare or finance

## When to choose
- you have AMD Ryzen AI hardware and want hardware-accelerated local inference
- privacy, compliance (HIPAA/GDPR), or air-gapped deployment rules out cloud APIs
- you want zero ongoing cloud costs for agent workloads

## When to avoid
- you don't have AMD Ryzen AI hardware
- you need cloud-scale models or multi-cloud provider support
- you need a battle-tested framework with a large ecosystem like LangChain

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, cli, chatbot
- domain: large-language-models, privacy, developer-tools
- platform: windows, python
- tags: local-llm, ryzen-ai, npu, on-device-ai, air-gapped, amd, ai-agents, linux, macos, desktop

## Member repositories
- amd/gaia (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:58.758195+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:23.940670+00:00, confidence not recorded.
  - readme: https://github.com/amd/gaia (fetched 2026-08-28T04:04:58.758195+00:00, sha 946e39a8725c)
  - homepage: https://github.com/amd/gaia (fetched 2026-08-29T11:33:48.731621+00:00, sha fd583c059b27)
- Data as of 2026-08-30T08:39:29.467469+00:00.