LightMem and Awesome-AI-Memory
LightMem is a concrete implementation of memory-augmented generation techniques, while Awesome-AI-Memory is a curated knowledge base and reference resource for understanding the broader landscape of LLM memory systems—making them complementary resources where the latter helps researchers understand and discover approaches like the former.
About LightMem
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
Employs a modular architecture with pluggable storage engines and retrieval strategies to manage long-term memory for LLMs and AI agents. Supports both cloud APIs (OpenAI, DeepSeek) and local deployment via Ollama, vLLM, and Transformers with integrated memory update mechanisms. Includes benchmark evaluation frameworks for LoCoMo and LongMemEval datasets, with hierarchical memory structures (StructMem) that preserve event-level bindings and cross-event connections.
About Awesome-AI-Memory
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。
Organizes 285+ papers and 87 open-source projects across a multi-dimensional taxonomy covering parametric vs. external memory, episodic/semantic/procedural types, and operations like writing, retrieval, updating, and compression. The repository systematically maps memory mechanisms including RAG, summarization, vector retrieval, and symbolic-neural hybrid approaches, with explicit focus on agent systems, multi-agent collaboration, and evaluation benchmarks for long-term consistency and personalization tasks.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work