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.
677 stars and 61 monthly downloads. Actively maintained with 7 commits in the last 30 days. Available on PyPI.
Stars
677
Forks
58
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Monthly downloads
61
Commits (30d)
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/zjunlp/LightMem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Related tools
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
mem0ai/mem0
Universal memory layer for AI Agents
memodb-io/memobase
User Profile-Based Long-Term Memory for AI Chatbot Applications.
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...