laya-jev-GraphRAG
Agentic GraphRAG engine using swappable System One decision models (local Laya / cloud Jev). Features a complete 4-phase pipeline (Ingestion, Pre-Retrieval, Traversal, Post-Retrieval) and evaluation across Neo4j, Memgraph, Apache AGE, and Kùzu driven by a custom A* traversal algorithm.
A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A* traversal for any graph database.
How it uses Jev
laya-jev-GraphRAG is a graph-database-agnostic Agentic GraphRAG framework — a production-ready intelligence layer you drop on top of your existing graph database to make it fully agentic. It doesn't replace your graph DB; it gives it a brain.
Getting started
bash git clone https://github.com/bodepudimuneendra-netizen/laya-jev-GraphRAG.git cd laya-jev-GraphRAG/graphrag neo4j laya
- Languages
- Python 99% · Dockerfile 1%
- License
- Apache-2.0
- Last activity
- Sep 2026
- Added
- 2026-09-24
- Stars at snapshot
- 22
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.