pheonix-delta/WiredBrain-Hierarchical-Rag

Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.

34
/ 100
Emerging

This project helps researchers and domain experts answer complex questions from very large datasets, like dense technical documentation or vast research papers, right on their own computer. You provide your specialized documents, and it gives you highly accurate, verified answers without needing expensive cloud services. It's designed for professionals who need trustworthy information from extensive knowledge bases.

Use this if you need to extract precise, hallucination-free answers from hundreds of thousands of documents in specialized domains using your existing consumer-grade computer.

Not ideal if you need instant, conversational chatbot-like responses, as this system prioritizes deep verification and truth over speed.

technical-research knowledge-management information-retrieval data-sovereignty scientific-analysis
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 6 / 25

How are scores calculated?

Stars

37

Forks

2

Language

Python

License

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/pheonix-delta/WiredBrain-Hierarchical-Rag"

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