Happy slice of mcp pizzaMCP.pizza

MemoryOS

MCP.Pizza Chef: BAI-LAB

MemoryOS gives your AI assistant an organized, long-term memory so it can recall names, preferences, past decisions, and ongoing projects instead of forgetting everything when a conversation ends. It sorts what it remembers into recent, medium-term, and long-term layers, so older but important details stay reachable while less relevant details fade. It connects to apps like Claude Desktop, Cursor, VS Code, and Cline, and needs a personal access key for the AI model it runs on, plus some initial technical setup to install.

Data
Notes

Use This MCP server To

Have my assistant remember my name and preferences every time Pick up a project exactly where I left off last week Keep track of decisions I've made across many conversations Avoid repeating the same background information to my assistant Build a personal assistant that gets to know me over time Give a support bot memory of past chats with each customer

README

MemoryOS

logo

Readme:中文 Mem0 Discord Mem0 PyPI - Downloads Npm package Discord License: Apache 2.0

🎉 If you like our project, please give us a star ⭐ on GitHub for the latest update.

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.

MemoryOS FAQ

Can I use this to make my AI assistant remember me across separate conversations?
Yes — MemoryOS stores what you tell your assistant and brings the relevant pieces back automatically in later sessions, so you do not have to re-explain who you are or what you are working on every time.
Can I use this to keep a long-running project's details organized instead of losing them after each chat?
Yes — MemoryOS separates recent details from older, well-established facts, so your project context stays reachable even after many conversations have passed.
Which apps does this work in?
It is built to connect with Claude Desktop, Cursor, VS Code, and Cline, and it can work with other AI apps built to speak the same open connection language, known as MCP.
Do I need an account or a key to use it?
Yes — you need a personal access key for whichever AI model you connect it to, such as OpenAI, Claude, Gemini, DeepSeek, or Qwen.
Is this easy to set up?
Not for a non-technical person working alone — setup currently means installing Python, creating a dedicated environment, and running it with either Docker or the Python package manager, which usually calls for a developer's help.
Will it slow down my AI assistant?
The project's creators report it has been sped up significantly compared to earlier versions, though actual speed will still depend on which AI model and setup you choose.
Does it work with more than one AI model?
Yes — it is designed to work with a wide range of AI models, including OpenAI, DeepSeek, and Qwen, so you are not locked into a single provider.
Can I try it without setting anything up myself?
Yes — the creators offer a hosted playground you can request access to, which lets you try the memory features without installing anything.