by wangzhishou · Agent Tool · ★ 94
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱
| Stars | 94 |
| Forks | 7 |
| Language | Kotlin |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 53.4984483268/100 |
| Open Issues | 5 |
| Last Updated | 2026-08-31 |
| Created | 2026-08-08 |
| Est. Tokens | ~15k |
These tools work well together with OneBox for enhanced workflows:
Looking for a OneBox alternative? If you're comparing OneBox 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.
在 Android 上运行的 AI 代码编辑器，内置 Linux 终端、AI Agent 与 MCP 协议。
Turn your Solana Seeker (or any Android phone) into a 24/7 personal AI agent
c4 GenAI Suite
On-device AI for Android — LLM chat (GGUF/llama.cpp), vision models (VLM), image generation (Stable Diffusion)
Vibe-Coding is easy. DevOps is hard. OpenCode & Git token-efficient AI agent automation for your app, business
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Explore other popular agent tool tools:
OneBox is A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱. It is categorized as a Agent Tool with 94 GitHub stars.
OneBox is primarily written in Kotlin. It covers topics such as ai, ai-agent, ai-agents.
You can find installation instructions and usage details in the OneBox GitHub repository at github.com/wangzhishou/OneBox. The project has 94 stars and 7 forks, indicating an active community.
OneBox is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to OneBox on Agent Skills Hub include AiCode, SeekerClaw, c4-genai-suite. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: