M
MemOS
MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
★10.6kstars
TypeScript
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A open-source Plugins, MCP & Skills project, built with TypeScript, focusing on agent and agentic-ai
Who made it?Maintained by MemTensor team, 10.6K⭐ on GitHub, #101 out of 2373 in Plugins, MCP & Skills
Why does it exist?In the Plugins, MCP & Skills space, agent workflows faced efficiency bottlenecks. MemOS was built by MemTensor to address these agentic-ai challenges.
What can it do?Key use cases: ai-agents, chatgpt, claude
How to install with AI?Use an AI coding assistant to automatically run npm/pnpm install and configure the project per the README.
🔗 github.com/MemTensor/MemOS | 官网 https://memos.openmem.net
🔗 github.com/MemTensor/MemOS | 官网 https://memos.openmem.net
Topics
agentagentic-aiaiai-agentschatgptclaudehermesllmlong-term-memorymcpmemorymemory-managementmulti-agentopenclawpythonragself-evolvingself-hostedskillstoken-savings