# facebookarchive/MemNN

Memory Networks implementations

Repository: https://github.com/facebookarchive/MemNN
Canonical: https://ross.abutalabs.com/products/memnn
Language: Lua
License: NOASSERTION
License Family: other
Archived: true
Last push: 2020-07-28T09:20:33+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4005, "days_push": 2227, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1755, forks 369 (observed 2026-08-28T04:05:32.117173+00:00)

## What it is
Facebook AI Research's reference implementations of memory-augmented neural networks (MemN2N, Key-Value Memory Networks, Entity Networks) written in Lua/Torch7 and Matlab. It accompanies several research papers on end-to-end memory networks, bAbI tasks, and dialogue-based learning.

## Use cases
- implement end-to-end memory networks for question answering
- run MemN2N experiments on bAbI tasks
- train key-value memory networks for document reading
- study dialogue-based language learning models
- reproduce research results from memory network papers

## When to choose
- you need reference implementations of MemN2N or Entity Networks from the original papers
- you are doing research on memory-augmented neural architectures
- you work with Torch7/Lua and want historical FAIR code

## When to avoid
- you need a maintained or production-ready library
- you want modern PyTorch or TensorFlow implementations
- you are not familiar with the deprecated Torch7 framework

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, nlp, rag
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: lua
- tags: memory-networks, memn2n, torch7, babi, research-code, facebook-archive, natural-language-processing, linux, macos

## Member repositories
- facebookarchive/MemNN (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.117173+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 2026-08-30T03:27:55.135339+00:00, confidence not recorded.
  - readme: https://github.com/facebookarchive/MemNN (fetched 2026-08-28T04:05:32.117173+00:00, sha d04bf11f0298)
- Data as of 2026-08-30T08:39:29.467469+00:00.