ibm-granite-community/granite-retrieval-agent

Build Research and Rag agents with Granite on your laptop

54
/ 100
Established

Implements multi-agent RAG systems using Granite 4's hybrid Mamba-2/Transformer architecture, which achieves ~70% lower memory use and 2× faster inference than comparable models for local deployment. Provides two distinct agent frameworks: Autogen/AG2 for document and web retrieval, and CrewAI for image-based research with vision capabilities. Integrates with Ollama for model serving and Open WebUI for chat interfaces, with optional SearXNG integration for web search.

152 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

152

Forks

50

Language

Python

License

Apache-2.0

Last pushed

Oct 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ibm-granite-community/granite-retrieval-agent"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.