HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
qhjqhj00
MemoRAG
Python2024–2024
qhjqhj00 / MemoRAG

MemoRAG

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

3Distinct people
3Mentions
0Explicit recommenders
2.3KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

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

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 7:57:46 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour3 dated mentions

Observed mentions: 2024-09-20 14:41:16 UTC to 2024-09-20 18:14:02 UTC.

012024-09-20 14:00:00 UTC to 2024-09-20 15:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsSep 20, 14:002024-09-20 15:00:00 UTC to 2024-09-20 16:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-09-20 16:00:00 UTC to 2024-09-20 17:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsSep 20, 16:002024-09-20 17:00:00 UTC to 2024-09-20 18:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2024-09-20 18:00:00 UTC to 2024-09-20 19:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsSep 20, 18:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Sep 20, 14:002024-09-20 14:00:00 UTC2024-09-20 15:00:00 UTC110
Sep 20, 15:002024-09-20 15:00:00 UTC2024-09-20 16:00:00 UTC000
Sep 20, 16:002024-09-20 16:00:00 UTC2024-09-20 17:00:00 UTC000
Sep 20, 17:002024-09-20 17:00:00 UTC2024-09-20 18:00:00 UTC101
Sep 20, 18:002024-09-20 18:00:00 UTC2024-09-20 19:00:00 UTC101

What Hacker News says

1 sources
> AFAICT from a quick glance at the code (https://github.com/qhjqhj00/MemoRAG/blob/main/memorag/memora...), it is indeed "fine tuning" (jargon!) a model on your chosen book, presumably in the most basic/direct sense: asking it reproduce sections of text at random from the book given their surrounding context, and rewarding/penalizing the neural network based on how well it did. Maybe your use of quotes is intentional here, but for posterity's sake there is no actual fine-tuning happening using user input in the code you linked, insofar as the weights of the model aren't being touched at all, nor are they modifying anything else that could impact the original weights (like a LoRA adapter). You touch on this, I think (?), in some of your subsequent language but it read as a little confusing to me at first glance. Or maybe I've been too deep
Read the rest
in the ML weeds for too many years at this point. The paper details the actual process, but the TL;DR is that the memory module they use, basically a draft model, does go through a pretraining phase using the redpajama dataset, and then an SFT phase with a different objective. This all happens before and irrespective of the inference-time task (i.e. asking questions about a given text). Also, as has been pointed out in other comments, the draft model could really be any model that supports long context and has decent retrieval performance. So the actual training phases here may be non-essential depending on your infra/cost constraints.
In MemoRAG – Enhance RAG with memory-based knowledge discovery for long contexts

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.