Serein — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 Yinglianchun · MCP Server · ★ 50

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Serein safe to install? View the security audit →

About Serein

Serein 让聊天里值得留下的东西,有地方保存,也有机会在下一次被想起。 Serein 是一个可自行部署、面向个人使用的 AI 记忆服务。它提供网页、聊天 API 网关和 MCP 工具,让不同聊天窗口读写同一份记忆。公开版从空库开始,不附带私人记忆或模型密钥。 功能 · 记忆怎么存 · Scene 与 Event · 怎么召回 · Hook 接入 · 召回格式 · 日记与暗房 · Arc/叙事卷 · 自动摘要 · 换窗 · 可选功能 · 论文 · 雨夜花园 · 安装 功能 可选功能按需开启;模型在“设置 → 模型”中添加,再到“配置”页选择各功能使用的模型。使用说明位于侧栏的 圆圈问号。 记忆怎么存 正文、原话与检索索引分开保存。 记忆可以被修改、归档和重新整理,原话仍用于核对当时究竟说了什么。 正文、版本和绑定关系等保存在 SQLite 主库;向量等派生索引另行保存,图片也有独立文件。备份整套实例时要一起保留,网页下载的数据库备份不等于完整安装目录。 Serein 只能读到已进入实例的资料。聊天客户端接上 MCP,并不意味着它的全部历史消息已经自动导入。 Scene 与 Event 两者都是记忆,但写下它们的时机和视角不同。 | 侧重点

ai-gatewayai-memoryllm-gatewaylong-term-memorymcp

Quick Facts

Stars50
Forks17
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score60.4342456814099/100
Last Updated2026-09-20
Created2026-07-18
Platformsmcp, python
Est. Tokens~17k

Compatible Skills

These tools work well together with Serein for enhanced workflows:

  • emergent — semantic(0.38)+complementary+same_lang+similar_pop+shared_platform (63%)

Serein alternative? Top 6 similar tools

Looking for a Serein alternative? If you're comparing Serein 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.

  • preloop by preloop · ⭐ 65

    The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs

  • claude-mem-lite by sdsrss · ⭐ 60

    Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across

  • roampal-core by roampal-ai · ⭐ 50

    Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo

  • anythingmcp by HelpCode-ai · ⭐ 250

    #1 MCP Gateway on GitHub 🔌 200+ ready connectors + any REST/SOAP/GraphQL/SQL system as custom connectors for

  • bitrouter by bitrouter · ⭐ 228

    The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight &

  • claude-self-reflect by ramakay · ⭐ 219

    Claude forgets everything. This fixes that. 🔗 www.npmjs.com/package/claude-self-reflect

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Serein?

Serein is 雨落下的地方,记忆会再次开花。可自部署的 AI 长期记忆与聊天网关。Self-hosted AI memory & chat gateway for long-term conversations.. It is categorized as a MCP Server with 50 GitHub stars.

What programming language is Serein written in?

Serein is primarily written in Python. It covers topics such as ai-gateway, ai-memory, llm-gateway.

How do I install or use Serein?

You can find installation instructions and usage details in the Serein GitHub repository at github.com/Yinglianchun/Serein. The project has 50 stars and 17 forks, indicating an active community.

What license does Serein use?

Serein is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to Serein?

The top alternatives to Serein on Agent Skills Hub include preloop, claude-mem-lite, roampal-core. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools