MemoryOS

<div align="center"> <img src="https://github.com/user-attachments/assets/eb3b167b-1ace-476e-89dc-1a7891356e0b" alt="logo" width="400"/> </div> <a href="readme_cn.md" target="_blank"> <img src="https://img.shields.io/badge/Readme-中文-blue" alt="Readme:中文"> </a> <a href="https://arxiv.org/abs/2506.06326"> <img src="https://img.shields.io/badge/Arxiv-paper-red" alt="Mem0 Discord"> </a> <a href="#contact-us"> <img src="https://img.shields.io/badge/Wechat-群二维码-green" alt="Mem0 PyPI - Downloads"> </a> <a href="https://www.youtube.com/watch?v=WHQu8fpEOaU" target="blank"> <img src="https://img.shields.io/badge/Youtube-Video-red" alt="Npm package"> </a> <a href="https://discord.gg/SqVj7QvZ" target="_blank"> <img src="https://img.shields.io/badge/Discord-Join_us-yellow" alt="Discord"> </a> <a href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank"> <img src="https://img.shields.io/badge/License-Apache_2.0-blue" alt="License: Apache 2.0"> </a> <h5 align="center"> 🎉 If you like our project, please give us a star ⭐ on GitHub for the latest update.</h5>

MemoryOS is designed to provide a memory operating system for personalized AI agents, enabling more coherent, personalized, and context-aware interactions. Drawing inspiration from memory management principles in operating systems, it adopts a hierarchical storage architecture with four core modules: Storage, Updating, Retrieval, and Generation, to achieve comprehensive and efficient memory management. On the LoCoMo benchmark, the model achieved average improvements of 49.11% and 46.18% in F1 and BLEU-1 scores.

Paper: <a href="https://arxiv.org/abs/2506.06326" target="_blank">https://arxiv.org/abs/2506.06326</a>
Website: <a href="https://baijia.online/memoryos/" target="_blank">https://baijia.online/memoryos/</a>
Documentation: <a href="https://bai-lab.github.io/MemoryOS/docs" target="_blank">https://bai-lab.github.io/MemoryOS/docs</a>
YouTube Video: MemoryOS MCP + RAG Agent That Can Remember Anything
<a href="https://www.youtube.com/watch?v=WHQu8fpEOaU ">https://www.youtube.com/watch?v=WHQu8fpEOaU </a>

✨Key Features

🏆 TOP Performance in Memory Management The SOTA results in long-term memory benchmarks, boosting F1 scores by 49.11% and BLEU-1 by 46.18% on the LoCoMo benchmark.
🧠 Plug-and-Play Memory Management Architecture Enables seamless integration of pluggable memory modules—including storage engines, update strategies, and retrieval algorithms.
✨ Agent Workflow Create with Ease (MemoryOS-MCP) Inject long-term memory capabilities into various AI applications by calling modular tools provided by the MCP Server.
🌐 Universal LLM Support MemoryOS seamlessly integrates with a wide range of LLMs (e.g., OpenAI, Deepseek, Qwen ...)

🧠 Memory Family

Welcome to our Memory Family, a research line dedicated to exploring AI Memory.

Survey on AI Memory: Theories, Taxonomies, Evaluations, and Emerging Trends
TL;DR: Provides a unified theoretical framework for AI Memory, introducing a comprehensive taxonomy and systematically analyzing memory mechanisms, applications, and evaluation methods.
📄 Paper: http://github.com/BAI-LAB/Survey-on-AI-Memory/blob/main/Survey%20on%20AI%20Memory.pdf

LightSearcher: Efficient DeepSearch via Experiential Memory
TL;DR: Introduces experiential memory into deep search systems, enabling models to learn from successful reasoning trajectories and improve search efficiency.
📄 Paper: https://arxiv.org/abs/2512.06653

Memory OS of AI Agent
TL;DR: Proposes a memory operating system for AI agents that manages short-term, mid-term, and long-term personal memory through hierarchical storage, dynamic updating, retrieval, and generation, improving coherence and personalization in long conversations.
📄 Paper: https://arxiv.org/abs/2506.06326

📣 Latest News

[new] 🔥🔥🔥 [2026-01-15]: ✨Released Survey on AI Memory: Theories, Taxonomies, Evaluations, and Emerging Trends!
[new] 🔥🔥 [2025-09-11]: 🚀Open-sourced the Playground platform!
[new] 🔥🔥 [2025-08-21]: 🎉Accepted by EMNLP 2025 main conference!
[new] 🔥 [2025-07-15]: 🔌 Support for Vector Database Chromadb
[new] 🔥 [2025-07-15]: 🔌 Integrate Docker into deployment
[new] [2025-07-14]: ⚡ Acceleration of MCP parallelization
[new] [2025-07-14]: 🔌 Support for BGE-M3 & Qwen3 embeddings on PyPI and MCP.
[new] [2025-07-09]: 📊 Evaluation of the MemoryOS on LoCoMo Dataset: Publicly Available 👉Reproduce.
[new] [2025-07-08]: 🏆 New Config Parameter
New parameter configuration: similarity_threshold. For configuration file, see 📖 Documentation page.
[new] [2025-07-07]: 🚀5 Times Faster
The MemoryOS (PYPI) implementation has been upgraded: 5 times faster (reduction in latency) through parallelization optimizations.
[new] [2025-07-07]: ✨R1 models Support Now
MemoryOS supports configuring and using inference models such as Deepseek-r1 and Qwen3..
[new] [2025-07-07]: ✨MemoryOS Playground Launched
The Playground of MemoryOS Platform has been launched! 👉MemoryOS Platform. If you need an Invitation Code, please feel free to reach Contact US.
[new] [2025-06-15]:🛠️ Open-sourced MemoryOS-MCP released! Now configurable on agent clients for seamless integration and customization. 👉 MemoryOS-MCP.
[2025-05-30]: 📄 Paper-Memory OS of AI Agent is available on arXiv: https://arxiv.org/abs/2506.06326.
[2025-05-30]: Initial version of MemoryOS launched! Featuring short-term, mid-term, and long-term persona Memory with automated user profile and knowledge updating.

🔥 MemoryOS Support List

<table> <thead> <tr> <th>Type</th> <th>Name</th> <th>Open Source</th> <th>Support</th> <th>Configuration</th> <th>Description</th> </tr> </thead> <tbody> <tr> <td rowspan="3">Agent Client</td> <td>Claude Desktop</td> <td>❌</td> <td>✅</td> <td>claude_desktop_config.json</td> <td>Anthropic official client</td> </tr> <tr> <td>Cline</td> <td>✅</td> <td>✅</td> <td>VS Code settings</td> <td>VS Code extension</td> </tr> <tr> <td>Cursor</td> <td>❌</td> <td>✅</td> <td>Settings panel</td> <td>AI code editor</td> </tr> <tr> <td rowspan="6">Model Provider</td> <td>OpenAI</td> <td>❌</td> <td>✅</td> <td>OPENAI_API_KEY</td> <td>GPT-4, GPT-3.5, etc.</td> </tr> <tr> <td>Anthropic</td> <td>❌</td> <td>✅</td> <td>ANTHROPIC_API_KEY</td> <td>Claude series</td> </tr> <tr> <td>Deepseek-R1</td> <td>✅</td> <td>✅</td> <td>DEEPSEEK_API_KEY</td> <td>Chinese large model</td> </tr> <tr> <td>Qwen/Qwen3</td> <td>✅</td> <td>✅</td> <td>QWEN_API_KEY</td> <td>Alibaba Qwen</td> </tr> <tr> <td>vLLM</td> <td>✅</td> <td>✅</td> <td>Local deployment</td> <td>Local model inference</td> </tr> <tr> <td>Llama_factory</td> <td>✅</td> <td>✅</td> <td>Local deployment</td> <td>Local fine-tuning deployment</td> </tr> </tbody> </table> All model calls use the OpenAI API interface; you need to supply the API key and base URL.

📑 Table of Contents

<a href='#features'>✨ Features</a>
<a href='#news'>🔥 News</a>
<a href='#list'>🔍Support Lists </a>
<a href='#structure'> 📁Project Structure</a>
<a href='#pypi-mode'>🎯 Quick Start</a>
- <a href='pypi-mode'>PYPI Install MemoryOS</a>
- <a href='#MCP-mode'>MemoryOS-MCP</a>
- <a href='#memoryos_chromadb-getting-started'>MemoryOS-chromadb</a>
- <a href='#docker-getting-started'>Docker</a>
- <a href='#playground-getting-started'>Playground</a>
<a href='#todo'>☑️ Todo List</a>
<a href='#reproduce'>🔬 How to Reproduce the Results in the Paper </a>
<a href='#doc'>📖 Documentation </a>
<a href='#cite'>🌟 Cite</a>
<a href='#community'>🤝 Join the Community</a>

🏗️ System Architecture

🏗️ Project Structure

memoryos/
├── __init__.py            # Initializes the MemoryOS package
├── __pycache__/           # Python cache directory (auto-generated)
├── long_term.py           # Manages long-term persona memory (user profile, knowledge)
├── memoryos.py            # Main class for MemoryOS, orchestrating all components
├── mid_term.py            # Manages mid-term memory, consolidating shor

MemoryOS

Install / Use

README

MemoryOS

✨Key Features

🧠 Memory Family

📣 Latest News

🔥 MemoryOS Support List

📑 Table of Contents

🏗️ System Architecture

🏗️ Project Structure