by jieapi · MCP Server · ★ 119
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
在 Android 上运行的 AI 代码编辑器,内置 Linux 终端、AI Agent 与 MCP 协议。
| Stars | 119 |
| Forks | 22 |
| Language | Kotlin |
| Category | MCP Server |
| License | GPL-3.0 |
| Quality Score | 52.5839142337766/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-11 |
| Created | 2026-07-12 |
| Platforms | claude-code, mcp |
| Est. Tokens | ~15k |
These tools work well together with AiCode for enhanced workflows:
Looking for a AiCode alternative? If you're comparing AiCode 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.
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH
Nexus | Take over your Android voice assistant with a custom AI agent — connect any LLM (Claude, GPT, Gemini),
Android Native Agent that makes screen operations, runs shell commands, uses Skills & MCP tools, and controls
AI-powered chat-first terminal IDE for Android. Built entirely on a phone, by someone who can't write code.
Turn your Solana Seeker (or any Android phone) into a 24/7 personal AI agent
Explore other popular mcp server tools:
AiCode is 在 Android 上运行的 AI 代码编辑器,内置 Linux 终端、AI Agent 与 MCP 协议。. It is categorized as a MCP Server with 119 GitHub stars.
AiCode is primarily written in Kotlin. It covers topics such as ai-agent, ai-code-editor, aicode.
You can find installation instructions and usage details in the AiCode GitHub repository at github.com/jieapi/AiCode. The project has 119 stars and 22 forks, indicating an active community.
AiCode is released under the GPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to AiCode on Agent Skills Hub include compose-skill, claude-code-android, com.niki914.nexus.agentic. 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: