BAI-LAB/MemoryOS
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.
This project helps create AI agents that remember and personalize interactions more effectively. By managing an agent's 'memories' (like conversation history, preferences, and knowledge), it enables more consistent and context-aware responses. It takes in various types of information an AI agent encounters and processes it to output a more personalized and coherent agent interaction, making it ideal for anyone building or deploying personalized AI assistants or conversational AI.
1,256 stars. Actively maintained with 4 commits in the last 30 days.
Use this if you need an AI agent to maintain long-term personal memory, understand context deeply, and provide highly personalized interactions over time.
Not ideal if you are looking for a simple, stateless AI agent or if your application does not require sophisticated memory management for personalization.
Stars
1,256
Forks
127
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 03, 2026
Commits (30d)
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/BAI-LAB/MemoryOS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
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
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...