No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by tianyupaipai-cmd · MCP Server · ★ 172
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is xinchao-nian safe to install? View the security audit →
心潮·念（Xinchao · Nian） 一个会惦记你的 AI 心智：心潮（动态驱力/欲望引擎）+ Ombre Brain（记忆库）深度融合，一键联合部署。 心潮 让它有随时间变化的内在状态——想念、期待、挂念、好奇、独处欲……不是每次对话都从零开始。 Ombre Brain 给它一个真正的长期记忆库——breath 浮现、hold 沉淀、dream 消化、trace 追溯。 融合 让"欲望影响记忆影响行动"闭环：驱力偏置召回哪些记忆浮现，浮现的记忆又回推驱力。 快速开始 OB Dashboard：（本机，建议再用 Nginx/隧道反代） 两服务在同一 docker 网络内部通信，对外只暴露本机端口。 连接 Claude.ai MCP 连接器 心潮·念自带 OAuth 2.1 MCP 端点，可直接作为 Claude.ai 的 MCP 连接器使用。 重要：连接器必须指向心潮（端口 18110），不是 Ombre Brain（端口 18001）。 OB 的 18001 端口仅用于 Dashboard 管理和内部通信，不要把它当 MCP 连接器添加到 Claude.ai。 在 中启用并重启： 然后在 Claude.ai 添加 MCP 连接器，URL 填 。 授权页面会显示「心潮念」，输入你设置的 即可。 如果你看到的授权页面显示的是「Ombre Brain」而不是「心潮念」，说明你连错了端口—— 检查你的反代/隧道是否指向 18110（心潮），而不是 18001（OB）。 连接心潮念公开可视化 前提是你已经按上面的步骤部署并启动了心潮·念。 是可视化 前端，不会替你运行心潮，也无法访问另一台设备的 。 先在 配好并重启： 然后按使用场景选择： 网页浏览器和心潮在同一台设备：在网页选择“我的心潮就在这台设备上”， 地址填 ，口令填 。 用手机访问电脑/主机里的心潮，或心潮跑在 VPS/N100：先用 Cloudflar
| Stars | 172 |
| Forks | 76 |
| Language | Python |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 63.3047568428019/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-13 |
| Created | 2026-08-09 |
| Platforms | docker, mcp, python |
| Est. Tokens | ~14k |
These tools work well together with xinchao-nian for enhanced workflows:
Looking for a xinchao-nian alternative? If you're comparing xinchao-nian with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S
A personal AI assistant for everyone
🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autono
Opensource Memory for Agents
Long-term memory layer for OpenClaw & MoltBook agents that learns and recalls your project context automatical
Explore other popular mcp server tools:
xinchao-nian is 心潮念（Xinchao·Nian）— 会惦记你的AI心智：心潮动态驱力引擎 + Ombre Brain 记忆库深度融合，一键联合部署。非商业(含OB二改约束)。. It is categorized as a MCP Server with 172 GitHub stars.
xinchao-nian is primarily written in Python. It covers topics such as ai-companion, docker-compose, mcp.
You can find installation instructions and usage details in the xinchao-nian GitHub repository at github.com/tianyupaipai-cmd/xinchao-nian. The project has 172 stars and 76 forks, indicating an active community.
xinchao-nian is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to xinchao-nian on Agent Skills Hub include powermem, Wax, Sentient. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: