flowix — security grade SAFE, quality 55/100

Security audit verdict: SAFE · quality 55/100

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 text2future · Codex Skill · ★ 415

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

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

About flowix

简体中文 / English / Roadmap / What's New Flowix Memo Flowix 是一款本地优先的桌面笔记应用。 和传统的 Notion、Obsidian 等不同,Flowix 聚焦在管理 AI 输入与 AI 对话,把人和 AI 的写作都装进同一份文档进行管理。 → 调研 & 开发项目管理 用笔记本来组织需求 和 反馈结果。把工作、研究、客户项目、日记在笔记本内按标签管理。AI Agent 可以理解需求和你的组织习惯,进行内容读取和任务完成。 AI输出内容,可直接输出到特定的标签内进行组织。需求、草稿、产物可以清晰管理。 → 适合和 AI Agent 一起处理笔记 支持在文档里调用内置 AI Agent,也可以连接 Claude Code、Codex、Hermes 等本地 CLI 代理。同一个文档可插入不限的 AI 对话。实现对话管理。 每次对话可直接理解当前文档内容,可阅读当前笔记本、其他笔记本、引入的资料库、代码库,取决于这次任务需要多少上下文。 → 长期记忆沉淀资料 笔记以本地 Markdown 文件保存。你能在系统文件夹里直接看到这些 文件,也可以用自己的同步盘、备份工具或版本管理方式来保存它们。 这种方式的好处是,内容不会被锁在某个专有云服务里;以后即使换工具,笔记仍然是普通 Markdown 文件,可以被其他编辑器继续读取。 → 轻量写作 & 结构化管理 日常记录时,你可以把 Flowix 当成普通 Markdown 编辑器,直接写标题、段落和清单;需要管理时,再给笔记加标签或属性。 标签写在正文里,比如 或 ;属性写在 Markdown frontmatter 里,例如状态、类型、来源和关键词。这些信息会跟着文件一起保存,也能被其他兼容 Markdown 的工具读取。 强大的 AI 管理能力 Flowix 内置 AI Agent, 采用 BYOK 模式使用你倾向的模型,同时支持使用 Claude Code, Codex, Hermes 等本地 CLI Agent进行工作。

agent-memoryclaude-codecodex-clidesktopdshdsh-plugindsh-plugin-desktophermes-agentmarkdown-editormemory-system

Quick Facts

Stars415
Forks53
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score55.0789825811856/100
Open Issues20
Last Updated2026-09-20
Created2026-05-25
Platformsclaude-code, cli, codex, node
Est. Tokens~14k

Compatible Skills

These tools work well together with flowix for enhanced workflows:

  • reevesagents — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)

flowix alternative? Top 6 similar tools

Looking for a flowix alternative? If you're comparing flowix with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • wesight by freestylefly · ⭐ 924

    Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus

  • mnemon by mnemon-dev · ⭐ 578

    LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. W

  • modsearch by liustack · ⭐ 482

    🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na

  • memtrace-public by syncable-dev · ⭐ 472

    Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·

  • agentrq by agentrq · ⭐ 1.1k

    AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agent

  • agent-sessions by jazzyalex · ⭐ 869

    Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is flowix?

flowix is Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding. It is categorized as a Codex Skill with 415 GitHub stars.

What programming language is flowix written in?

flowix is primarily written in TypeScript. It covers topics such as agent-memory, claude-code, codex-cli.

How do I install or use flowix?

You can find installation instructions and usage details in the flowix GitHub repository at github.com/text2future/flowix. The project has 415 stars and 53 forks, indicating an active community.

What license does flowix use?

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

What are the best alternatives to flowix?

The top alternatives to flowix on Agent Skills Hub include wesight, mnemon, modsearch. 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 Codex Skill tools