Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A Collection of Papers about Memory for Language Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 620 |
| 2026-08-04 | 624 |
| 2026-08-06 | 624 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome-Memory-for-Agents
The paper list is maintained by Hongyi Liu, Yu Fu, Kaiyan Zhang, contributed by Yuxin Zuo, Che Jiang, Guoli Jia, Yuru Wang, Kaikai Zhao, Yuchen Fan, Zhenzhao Yuan, Kai Tian, Weizhi Wang.
<div align="center">
<img src="assets/cover.png" width=60%>
</div>
## Table of Contents
- [Awesome-Memory-for-Agents](#awesome-memory-for-agents)
- [Table of Contents](#table-of-contents)
- [Overview](#overview)
- [Paper List](#paper-list)
- [Application](#application)
- [Personalization](#personalization)
- [Learning from Experience](#learning-from-experience)
- [Long-horizon Agentic Task](#long-horizon-agentic-task)
- [Survey](#survey)
- [Benchmark](#benchmark)
- [Product \& Project](#product--project)
## Overview
This repository provides a curated list of papers on agent memory, structured by a core taxonomy. We first divide agent memory based on its persistence:
- **Short-Term Memory:** Transient information managed within the context window for a single task;
- **Long-Term Memory:** Persistent information stored externally across tasks.
Within *Long-Term Memory*, we further distinguish based on its reliance on task outcomes (success/failure) for curation:
- **Experience** involves knowledge explicitly validated by task outcomes;
- **Memory** denotes information without reference to task outcomes.
This taxonomy maps directly to the three primary application scenarios that organize the papers in this repository:
| Application | Memory Content | Description |
| :------------------------ | :----------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Personalization | User profiles, interaction history, facts, etc. | Continuous personalized interaction, mainly targeting the conversation scenario and using an external memory pool with retrieval-based memory interaction |
| Learning from Experience | Trajectories, success/failure lessons, reusable skills, etc. | Cross-task experience accumulation & transfer |
| Long-horizon Agentic Task | Intermediate results, reasoning traces, environmental observations, etc. | Context management within a single long-horizon task via summarization, reflection, or scratchpad, etc. |
## Paper List
### Application
#### Personalization
| Date | Title | Paper |
|:------:|:------|:------:|
| 2026-04 | Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents | [](https://arxiv.org/abs/2604.22085) |
| 2026-04 | FileGram: Grounding Agent Personalization in File-System Behavioral Traces | [](https://arxiv.org/abs/2604.04901) |
| 2026-01 | Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents | [](https://arxiv.org/abs/2601.03785) |
| 2026-01 | Grounding Agent Memory in Contextual Intent | [](https://arxiv.org/abs/2601.10702) |
| 2026-01 | Continuum Memory Architectures for Long-Horizon LLM Agents | [
Kaiyan Zhang · @FrontisAI · China
28
12
4
Shuai Liu · Nanyang Technological University · Singapore
2
1
Max Baluev
1
1
1
1
swordlight_ai
1
Varun Pratap Bhardwaj
1
Sam Valladares · Israel
1
1
1
1
1
1
1
1
Nir Diamant · DiamantAI
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ca94adffdc154f01, llm:Repository description: 'A Collection of Papers about Memory for Language Agents' (topic: memory for language agents).
matched fp:ca94adffdc154f01, llm:Repository description: 'A Collection of Papers about Memory for Language Agents' (topic: memory for language agents).
matched fp:ca94adffdc154f01, llm:Repository description: 'A Collection of Papers about Memory for Language Agents' (topic: memory for language agents).