Shelly — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 RYOITABASHI · Agent Tool · ★ 56

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

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

About Shelly

Shelly Terminal + AI + Browser + Markdown + Preview A native Android terminal IDE for running the real Codex CLI in an app-owned PTY, with API-backed AI agents — Gemini, Cerebras, Groq, Perplexity, and local models — plus Git, Bash, Python, and editors bundled in the APK. No Termux install, no distro bootstrap, no separate package manager setup. No WebView terminal, no remote IDE bridge. Open the app, authenticate your own AI accounts, and work in local multi-pane terminals on Android. <img alt="TypeScript" src="https://img.shields.io/badge/TypeScript-3178C6?style=flat-square&logo=type

aiandroidchat-uiclaudeclaude-codeexpogemini-cliidekotlinllm

Quick Facts

Stars56
Forks8
LanguageTypeScript
CategoryAgent Tool
LicenseGPL-3.0
Quality Score66.9535349199933/100
Last Updated2026-08-30
Created2026-03-04
Platformsclaude-code, cli, gemini, node
Est. Tokens~26k

Compatible Skills

These tools work well together with Shelly for enhanced workflows:

  • metro-mcp — semantic(0.16)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)

Shelly alternative? Top 6 similar tools

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

  • claude-code-android by ferrumclaudepilgrim · ⭐ 189

    Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • com.niki914.nexus.agentic by Xposed-Modules-Repo · ⭐ 155

    Nexus | Take over your Android voice assistant with a custom AI agent — connect any LLM (Claude, GPT, Gemini),

  • claude-toolbox by serpro69 · ⭐ 149

    Minimal by design, explicitly multi-lang, production-ready and battle-tested collection of configs and plugins

  • agentic-nexus by niki914 · ⭐ 111

    Android Native Agent that makes screen operations, runs shell commands, uses Skills & MCP tools, and controls

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Shelly?

Shelly is AI-powered chat-first terminal IDE for Android. Built entirely on a phone, by someone who can't write code.. It is categorized as a Agent Tool with 56 GitHub stars.

What programming language is Shelly written in?

Shelly is primarily written in TypeScript. It covers topics such as ai, android, chat-ui.

How do I install or use Shelly?

You can find installation instructions and usage details in the Shelly GitHub repository at github.com/RYOITABASHI/Shelly. The project has 56 stars and 8 forks, indicating an active community.

What license does Shelly use?

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

What are the best alternatives to Shelly?

The top alternatives to Shelly on Agent Skills Hub include claude-code-android, claude-code-open, claude-historian-mcp. 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