# qhjqhj00/MemoRAG

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

Repository: https://github.com/qhjqhj00/MemoRAG
Canonical: https://ross.abutalabs.com/products/memorag
Language: Python
License: Apache-2.0
License Family: permissive
Topics: memory, rag, long-llm
Last push: 2025-09-11T08:51:14+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 40, longevity 52
- inputs: {"age_days": 729, "days_push": 356, "days_rel": 708, "gap_med": 10, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2265, forks 157 (observed 2026-08-28T04:06:32.610214+00:00)

## What it is
MemoRAG is a Python RAG framework that uses a super-long memory model to build a global understanding of an entire corpus (up to ~1M tokens) and recalls query-specific clues to improve evidence retrieval and answer generation. It ships with pretrained memory models on HuggingFace, a Lite mode, and training scripts/datasets.

## Use cases
- build a RAG pipeline over very large document collections
- answer questions over a million-token corpus with global context
- improve retrieval quality beyond standard vector-search RAG
- run memory-augmented QA over long PDFs or books
- fine-tune a custom memory model for domain-specific RAG
- generate context-rich answers when queries have implicit information needs

## When to choose
- your corpus is too large for a single LLM context window
- standard RAG retrieval misses globally relevant evidence
- you want an open-source, research-backed RAG framework with pretrained memory models
- you need to recall query clues from a global memory of the whole database

## When to avoid
- you lack GPU resources for running 7B memory models
- your corpus is small and fits in a standard LLM context
- you need a fully managed hosted RAG service
- you only need simple keyword or vector search without generation

## Facets
- artifact type: framework
- maturity: active
- function: rag, llm-inference, machine-learning, search-engine
- domain: large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: memory-model, long-context, knowledge-discovery, retrieval, huggingface, retrieval-augmented-generation, natural-language-processing, gpu

## Member repositories
- qhjqhj00/MemoRAG (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:32.610214+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 2026-08-30T02:42:25.370389+00:00, confidence not recorded.
  - readme: https://github.com/qhjqhj00/MemoRAG (fetched 2026-08-28T04:06:32.610214+00:00, sha efc2c7d91891)
- Data as of 2026-08-30T08:39:29.467469+00:00.