Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
- GitHub 星标
- 1.1万
- 许可证
- Apache-2.0
- 收录日期
- 2025-07-06
GitHub 信息
- GitHub 星标
- 1.1万
- 许可证
- Apache-2.0
- 主要语言
- TypeScript
- 最近推送
- 2026年8月21日 07:01
- 维护者
- MemTensor
- 收录日期
- 2025-07-06
README 演示图
从仓库 README 提取的截图/GIF（已过滤徽章、头像等装饰图）。
安装
dsh plugin --profile web add github:MemTensor/MemOS标签
README 徽章
将这段 Markdown 添加到插件 README，链接到对应的详情页。
[](https://dshget.com/plugins/MemTensor/MemOS)相关插件
开发与运行时EverOS
★ 12559One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
memmy-agent
★ 1189🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
ruflo
★ 69768Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration