Aelios — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 wusaki0723 · MCP Server · ★ 124

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

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

About Aelios

Aelios 给 AI 装一颗跨窗口的长期记忆大脑。换窗口、换客户端、换模型,记忆跟着你走。 这份 README 分两段。上半段给人看:草履虫也能懂,照着做就能用。下半段给 AI 看:端点、MCP、管线细节,给 Codex / Claude Code / Cursor 维护调试用。 我是人类,想部署使用 → 看 人类版 我是 AI 助手,想维护调试 → 看 AI 版 人类版 一句话 Aelios 是一个跑在 Cloudflare 上的记忆服务。你的 AI 客户端(Chatbox、Cherry Studio、网页、脚本)连上它之后,AI 就能永远记住你的偏好、规则、项目背景和重要的话——不是这一次记得,是下一次、下下次都记得。 它替你解决了什么 每次开新窗口 AI 就失忆 → 它把聊天存下来,自动整理成长期记忆,下次自动召回。 记忆太多把 AI 搞蠢 → 它先粗筛、再精排、再压缩,最后只塞几百字进上下文。 换个客户端记忆就没了 → 记忆存在你自己的 Cloudflare 里,换客户端只改一个地址。 想给 Claude Code / Codex 加记忆 → 它能当成 MCP 工具挂上去,跨设备随身。 三步搞定 部署 Fork wusaki0723/Aelios 到自己 GitHub。 Cloudflare Dashboard → Workers & Pages → Create application → 连你的 GitHub → 选你的 fork。 填配置: Project name: Production branch: Root directory: Build command: Deploy command: ⚠️ 必须是 ,不是 ,不是 。这条命令会自动建好 D1 数据库 + Vectorize 向量库 + Queue 队列。用错命令数据库不会建。 设一把钥匙 部署完,去 Worker 的 Settings → Variables and Secrets 加三个: 名字里带 / 的必须选 Secret(加密、不进 git),不要选 Variable。详见 SECRETS.md。 保存后重新部署。你会拿到一个地址

ai-memorycloudflare-workersd1long-term-memorymcpvectorize

Quick Facts

Stars124
Forks75
LanguageTypeScript
CategoryMCP Server
LicenseAGPL-3.0
Quality Score62.7162834931077/100
Open Issues1
Last Updated2026-09-22
Created2026-03-07
Platformsmcp, node
Est. Tokens~17k

Aelios alternative? Top 6 similar tools

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

  • MisakaNet by Ikalus1988 · ⭐ 501

    📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verifie

  • FlareMo by realchendahuang · ⭐ 254

    Cloudflare 原生的团队知识库:一个人用是私人笔记,一个团队用是共享知识库;提供 Memos 兼容 API 与 MCP。

  • claude-mem-lite by sdsrss · ⭐ 61

    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

  • mira-OSS by taylorsatula · ⭐ 477

    This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure whe

  • aser by AmeNetwork · ⭐ 472

    Aser is a lightweight, self-assembling AI Agent frame.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Aelios?

Aelios is 分层长期记忆内核 · Cloudflare Workers + D1 + Vectorize · 即时捕获/4小时抽取/凌晨整理三档写入,六层记忆 + 可视化 curation面板。QQ群:1091783659. It is categorized as a MCP Server with 124 GitHub stars.

What programming language is Aelios written in?

Aelios is primarily written in TypeScript. It covers topics such as ai-memory, cloudflare-workers, d1.

How do I install or use Aelios?

You can find installation instructions and usage details in the Aelios GitHub repository at github.com/wusaki0723/Aelios. The project has 124 stars and 75 forks, indicating an active community.

What license does Aelios use?

Aelios is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to Aelios?

The top alternatives to Aelios on Agent Skills Hub include MisakaNet, FlareMo, claude-mem-lite. 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