Home Projects LongMem
LongMem
Python

LongMem

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

by Victorwz · GitHub
Stars
Forks
License
Created
Last commit
Language
large-language-modelslong-context-modelinglong-term-memoryApache-2.0Python
View on GitHub
In plain words

Enhance language models with the ability to remember information over longer conversations.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
LongMem — GitHub preview card
📈 Star history
828827
2026-07-202026-08-31
📈 Track LongMem

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

LongMem has 827 stars on GitHub. It has been forked 74 times. LongMem is written mainly in Python. It has been in active development since 2023. LongMem is available under the Apache-2.0 license. Its main topics are large-language-models, long-context-modeling, long-term-memory.

Frequently asked questions

What is LongMem?

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

Is LongMem open source?

LongMem is an open-source project. It is released under the Apache-2.0 license.

Is LongMem free?

Yes. LongMem is free and open source — you can use, modify and self-host it.

What license does LongMem use?

LongMem is available under the Apache-2.0 license.

What language is LongMem written in?

LongMem is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — LongMem

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=victorwz-longmem)](https://olud.ai/project/victorwz-longmem.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.