A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
- GitHub 星标
- 2,502
- 许可证
- MIT
- 收录日期
- 2026-02-09
GitHub 信息
- GitHub 星标
- 2,502
- 许可证
- MIT
- 主要语言
- Python
- 最近推送
- 2026年8月23日 04:54
- 维护者
- zilliztech
- 收录日期
- 2026-02-09
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)。
MemSearch skill distillation demo
https://github.com/user-attachments/assets/39a90f1c-54e3-4c7a-b168-051f0e096d39
memsearch demo
https://github.com/user-attachments/assets/427b7152-bc16-408c-a8b0-59a2b05fd1e0

Sign up and get API key
https://raw.githubusercontent.com/zilliztech/claude-context/master/assets/signup_and_get_apikey.png
安装
dsh plugin --profile web add github:zilliztech/memsearch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/zilliztech/memsearch)相关插件
开发与运行时MemOS
★ 11085Self-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.
dsh-chat-import
★ 123把 13 家 coding agent(Claude Code、Codex、ChatGPT、Cursor、Gemini、opencode 等)的完整对话历史导入为可续聊的 DeepSeek Harness 会话,并支持反向导出回 Claude Code。
EverOS
★ 12559One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.