# Awesome-AI-Memory — Papers & Projects for LLM Memory

> Curated knowledge base for LLM/agent memory systems (399 papers, 104 projects): long-term memory design, retrieval, eval; verified 862★, pushed 2026-05-14.

## Install

Copy the content below into your project:

## Quick Use

```bash
git clone https://github.com/IAAR-Shanghai/Awesome-AI-Memory
cd Awesome-AI-Memory
# Use ripgrep to find subtopics quickly:
rg -n "episodic|semantic|RAG|benchmark|evaluation" -S README.md | head
```

## Intro

Curated knowledge base for LLM/agent memory systems (399 papers, 104 projects): long-term memory design, retrieval, eval; verified 862★, pushed 2026-05-14.

**Best for:** Researchers/engineers building long-term memory for agents who want a single curated map of the field

**Works with:** GitHub browsing or cloning; paper/project lists linked from README (badges show 399 papers + 104 projects)

**Setup time:** 5-15 minutes

### Key facts (verified)

- GitHub: 862 stars · 78 forks · pushed 2026-05-14.
- License: Apache-2.0 · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `git clone https://github.com/IAAR-Shanghai/Awesome-AI-Memory`.

## Main

- Use it as a reading queue: start from the scope/goal section, then jump to the linked Papers and Projects lists (README badges show counts).

- When designing memory, keep components explicit: storage (vector/graph/sql), write policy, retrieval policy, and compression/forgetting.

- Track evaluation early: use the repo’s benchmark/evaluation sections to choose measurable tasks (long-context, personalization, multi-session).

- Keep your own “memory design doc” next to your codebase and cite entries from this repo as references for tradeoffs.

### Source-backed notes

- README includes badges with quantitative counts: 399 papers and 104 open source projects.
- README describes the motivation (context window limits) and positions memory systems as external/persistent structures for agents.
- README links to separate Chinese README and outlines scope and exclusions.

### FAQ

- **Is this an implementation?**: No — it’s a curated list of papers/projects; use it to choose architectures and references.
- **How do I keep it actionable?**: Pick one memory pattern, one benchmark, and one open-source project to replicate as a baseline.
- **Where are the numbers from?**: The counts (papers/projects) are shown in README badges at the top of the repo.

## Source & Thanks

> Source: https://github.com/iaar-shanghai/awesome-ai-memory
> License: Apache-2.0
> GitHub stars: 862 · forks: 78

---

<!-- ZH -->

## Quick Use

```bash
git clone https://github.com/IAAR-Shanghai/Awesome-AI-Memory
cd Awesome-AI-Memory
# Use ripgrep to find subtopics quickly:
rg -n "episodic|semantic|RAG|benchmark|evaluation" -S README.md | head
```

## Intro

Awesome-AI-Memory 是持续更新的 AI 记忆知识库，README 标注 399 篇论文与 104 个开源项目，覆盖长期记忆、检索、压缩与评测；已验证 862★，更新于 2026-05-14。

**Best for:** 要为 agent 做长期记忆系统的研究者/工程师，希望用一个清单快速定位论文、项目与评测

**Works with:** 直接在 GitHub 浏览或 clone；README 关联论文与项目清单（badge 标注 399 papers + 104 projects）

**Setup time:** 5-15 minutes

### Key facts (verified)

- GitHub：862 stars · 78 forks；最近更新 2026-05-14。
- 许可证：Apache-2.0；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口命令：`git clone https://github.com/IAAR-Shanghai/Awesome-AI-Memory`。

## Main

- 把它当阅读与选型队列：先看 Scope/Goal，再跳到 Papers/Projects 清单（README badge 标注数量）。

- 做记忆系统时把组件拆清楚：存储（向量/图/SQL）、写入策略、检索策略、压缩/遗忘策略。

- 尽早绑定评测：用仓库里的 benchmark/evaluation 线索挑能量化的任务（长对话、个性化、多会话一致性）。

- 把“记忆系统设计文档”跟代码放一起，并把这里的条目作为参考来源记录权衡理由。

### Source-backed notes

- README badge 标注量化数据：399 篇论文与 104 个开源项目。
- README 说明动机：上下文窗口有限，记忆系统通过外部/可控的持久化结构扩展能力。
- README 提供中文版本并列出 scope 与 out-of-scope 范围。

### FAQ

- **这是可直接运行的实现吗？**：不是；它是论文与项目清单，用于选型与查资料。
- **怎么让它更可落地？**：先选一个记忆模式 + 一个 benchmark + 一个开源实现做 baseline 复现。
- **这些数量从哪来？**：README 顶部 badge 直接标注 papers 与 projects 的数量。

## Source & Thanks

> Source: https://github.com/iaar-shanghai/awesome-ai-memory
> License: Apache-2.0
> GitHub stars: 862 · forks: 78


---
Source: https://tokrepo.com/en/workflows/awesome-ai-memory-papers-projects-for-llm-memory
Author: AI Open Source