qhjqhj00/MemoRAG

Empowering RAG with a memory-based data interface for all-purpose applications!

46
/ 100
Emerging

Combines long-context language models with retrieval-augmented generation by building global memory representations of entire document collections, enabling query-specific evidence retrieval without explicit indexing. Supports up to 1M tokens through beacon-based attention mechanisms and offers efficient context caching for 30x speedup; integrates with HuggingFace models (Qwen2, Llama, Mistral) and includes training datasets for task-specific fine-tuning.

2,227 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

2,227

Forks

155

Language

Python

License

Apache-2.0

Last pushed

Sep 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/qhjqhj00/MemoRAG"

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