# IAAR-Shanghai/Awesome-AI-Memory

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design.  Awesome-AI-Memory 是一个 集中式、持续更新的 AI 记忆知识库，系统性整理了与 大模型记忆（LLM Memory）与智能体记忆（Agent Memory） 相关的前沿研究、工程框架、系统设计、评测基准与真实应用实践。

Repository: https://github.com/IAAR-Shanghai/Awesome-AI-Memory
Canonical: https://ross.abutalabs.com/products/awesome-ai-memory
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent-memory, ai-memory, continual-learning, llm-memory, long-term-memory, memory-systems, rag, memory-augmented-models, reasoning-over-time, ai-memory-system, awesome-ai-memory
Last push: 2026-09-02T06:40:49+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 35, longevity 19
- inputs: {"age_days": 275, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1196, forks 127 (observed 2026-09-03T02:15:06.163573+00:00)

## What it is
A curated, continuously updated knowledge base (awesome list) on AI memory for LLMs and agents, collecting research papers, frameworks, benchmarks, and system design practices. It covers long-term memory, retrieval, reasoning over time, and memory-native system design.

## Use cases
- find research papers on llm long-term memory
- learn how agent memory systems work
- compare memory frameworks for llm agents
- find benchmarks for evaluating ai memory systems
- research memory-augmented language models
- design a memory system for a chatbot
- keep up with the ai memory research landscape

## When to choose
- you need a curated survey of papers, tools, and benchmarks on LLM/agent memory
- you are researching memory-augmented models or long-term memory architectures
- you want a starting point to discover memory frameworks and implementations

## When to avoid
- you need a production memory system rather than a reference list
- you are looking for general RAG or context-window techniques unrelated to memory
- you need runnable software rather than curated links and papers

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, nlp, agent-framework, documentation
- domain: large-language-models, awesome-lists, tutorials
- platform: python
- tags: awesome-list, llm-memory, agent-memory, long-term-memory, memory-systems, curated-papers, survey, ai-agents, retrieval-augmented-generation, natural-language-processing

## Member repositories
- IAAR-Shanghai/Awesome-AI-Memory (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:06.163573+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 2026-08-30T06:25:26.202768+00:00, confidence not recorded.
  - readme: https://github.com/IAAR-Shanghai/Awesome-AI-Memory (fetched 2026-09-03T02:15:06.163573+00:00, sha c88524e69193)
- Data as of 2026-08-30T08:39:29.467469+00:00.