nuphus — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 mrpulor-gh · Agent Tool · ★ 74

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

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

About nuphus

Nuphus — 本地优先面向个人用户日常编程、办公、自动化工作流的 AI 协作伙伴 中文 | English 版本: 0.2.15 · 状态: Alpha(积极开发中) · 平台: Windows / macOS / Linux 技术栈: Tauri v2 · Rust · React 18 · TypeScript Nuphus 是运行在你电脑上的 AI Agent——本地、私有、拥有真实的桌面执行力,手机是它的第二块屏幕。 它识别屏幕、操作鼠标键盘、控制窗口、读写文件、调度浏览器,把 LLM 的推理变成真实的自动化。数据留在本机,模型由你选择,Agent 替你做事情。你在桌面发起的每一个会话,手机上都实时同步——同一份记忆、同一个 Agent、同一场对话,随时随地继续。 设计哲学 不在乎华丽的炫技,只在乎实用的能力。极简实用主义,功能按需呈现,拒绝堆砌套壳、重复探索和无意义消耗,主张一切落到日常工作中。 Leader:串行思考,并行执行 Nuphus 的核心引擎用 Rust 构建,工具调用在毫秒级完成,延迟瓶颈在模型推理而非引擎。Agent 决策本身就是因果链——每一步依赖上一步的结果,桌面系统操作更应遵循串行逻辑。 全局理解,掌控任务 — Leader 解析目标、规划路径、监督进度、汇总交付 内部编排(串行) — 调度内置 GoalType Exec

agent-skillsai-agentai-agentsautomationcomputer-usedesktop-automationllmlocal-firstmobileopen-source

Quick Facts

Stars74
Forks16
LanguageRust
CategoryAgent Tool
LicenseApache-2.0
Quality Score60.995480972912/100
Open Issues3
Last Updated2026-09-20
Created2026-08-21
Platformsbrowser, rust
Est. Tokens~24k

Compatible Skills

These tools work well together with nuphus for enhanced workflows:

  • bladebro — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • agent-workspace-linux — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)

nuphus alternative? Top 6 similar tools

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

  • ai-agent-automation by vmDeshpande · ⭐ 178

    Modular AI agent workflow automation platform with schedulers, tools, and observability. https://vmdeshpande.g

  • Hermes-Studio by JPeetz · ⭐ 303

    Web UI & dashboard for Hermes Agent — chat, memory, skills, terminal, approvals, multi-agent orchestration. Se

  • pie-ai-agent by WiseriaAI · ⭐ 182

    Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skil

  • meridian by markmdev · ⭐ 181

    Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp

  • yume by aofp · ⭐ 149

    Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support

  • Claude-Agent-Team-Manager by DatafyingTech · ⭐ 140

    Visual org-chart desktop app for managing Claude Code agent teams, skills, and configurations

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is nuphus?

nuphus is Nuphus — 本地优先的 AI Agent:真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.. It is categorized as a Agent Tool with 74 GitHub stars.

What programming language is nuphus written in?

nuphus is primarily written in Rust. It covers topics such as agent-skills, ai-agent, ai-agents.

How do I install or use nuphus?

You can find installation instructions and usage details in the nuphus GitHub repository at github.com/mrpulor-gh/nuphus. The project has 74 stars and 16 forks, indicating an active community.

What license does nuphus use?

nuphus is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to nuphus?

The top alternatives to nuphus on Agent Skills Hub include ai-agent-automation, Hermes-Studio, pie-ai-agent. 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 Agent Tool tools