MemOS
MemOS: a memory OS for LLMs and AI agents with persistent memory and self-evolving capabilities
Install
dsh plugin --profile web add github:MemTensor/MemOS Screenshots 2
What it solves
MemOS addresses the lack of long-term memory and personalized interaction capabilities in AI agents. It provides a persistent, editable, and retrievable memory system through a unified memory API, multi-modal memory support, and asynchronous ingestion, thereby improving task completion rates and user interaction experiences.
Who it’s for
- Developers who need to add long-term memory and personalization to AI assistants
- Teams building multi-agent collaboration systems that require shared or isolated memory
- AI application developers looking to improve agent task completion rates and user interaction experiences
Compiled from the project README · All rights belong to the original author
Report issue / Request removal