by NevaMind-AI · MCP 服务器 · ★ 13.9k
memU 24/7 Always-On Proactive Memory for AI Agents English Français memU is a memory framework built for 24/7 proactive agents. It is designed for long-running use and greatly reduces the LLM token cost of keeping agents always online, making always-on, evolving agents practical in production systems. memU continuously captures and understands user intent. Even without a command, the agent can tell what you are about to do and
| Stars | 13,854 |
| Forks | 1,036 |
| Language | Python |
| Category | MCP 服务器 |
| Quality Score | 45.478/100 |
| Open Issues | 97 |
| Last Updated | 2026-06-14 |
| Created | 2025-07-29 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~19k |
Explore other popular mcp 服务器 tools:
memU is The memory harness for proactive AI agents — structured storage, intent capture, 10x token reduction.. It is categorized as a MCP 服务器 with 13.9k GitHub stars.
memU is primarily written in Python. It covers topics such as agent-memory, agentic-workflow, claude.
You can find installation instructions and usage details in the memU GitHub repository at github.com/NevaMind-AI/memU. The project has 13.9k stars and 1036 forks, indicating an active community.