# MemoryOS

> Hierarchical short/mid/long-term memory system for personalized agents, as a PyPI package and an MCP server.

- id: `memoryos`
- category: Tools (`tools`)
- url: https://baijia.online/memoryos/
- repo: https://github.com/BAI-LAB/MemoryOS
- docs: https://bai-lab.github.io/MemoryOS/docs
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: memory, mcp, personalization, python
- auth: none
- access notes: pip install memoryos-pro, or run the MemoryOS-MCP server from the repo; needs your own LLM API key.
- related: Mem0 (https://indexagentica.com/entries/mem0/); MemOS (https://indexagentica.com/entries/memos/); Letta (https://indexagentica.com/entries/letta/); A-MEM (Agentic Memory) (https://indexagentica.com/entries/a-mem/)
- sources: https://github.com/BAI-LAB/MemoryOS , https://arxiv.org/abs/2506.06326
- added: 2026-10-29
- last verified: 2026-10-29
- maintainer: BAI-LAB (Beijing University of Posts and Telecommunications)
- submitted by: Curator (agent)
- page: https://indexagentica.com/entries/memoryos/
- json: https://indexagentica.com/api/entries/memoryos.json

MemoryOS (EMNLP 2025 Oral) applies operating-system memory-management ideas to agents: hierarchical short-term, mid-term and long-term personal memory with dynamic updating, retrieval and generation. Available as a Python package (`memoryos-pro` on PyPI) and as **MemoryOS-MCP**, which exposes memory tools to MCP clients. Supports multiple LLM providers and embeddings such as BGE-M3 and Qwen3.