ai-devkit — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 codeaholicguy · MCP Server · ★ 1.6k

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

🔒 Is ai-devkit safe to install? View the security audit →

About ai-devkit

AI DevKit The toolkit for AI-assisted software development. AI DevKit helps AI coding agents work more effectively with your codebase. It provides structured workflows, persistent memory, and reusable skills — so agents follow the same engineering standards as senior developers. Quick Start This launches an interactive setup wizard that configures your project for AI-assisted development in under a minute. Supported Agents ❌ Not Ready

agent-frameworkagent-skillsaiai-agentsai-codingantigravityclaude-codeclicodex-clicoding-agents

Quick Facts

Stars1,635
Forks252
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score64.4153214474336/100
Open Issues37
Last Updated2026-09-22
Created2025-10-14
Platformsclaude-code, cli, codex, gemini, mcp, node
Est. Tokens~14k

Compatible Skills

These tools work well together with ai-devkit for enhanced workflows:

  • codex-mcp-server — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • agent-skills — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • vibe-log-cli — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • claude-talk-to-figma-mcp — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)

ai-devkit alternative? Top 6 similar tools

Looking for a ai-devkit alternative? If you're comparing ai-devkit 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.

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • pilot-shell by maxritter · ⭐ 2.1k

    Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • OpenContext by 0xranx · ⭐ 1.2k

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • memorix by AVIDS2 · ⭐ 797

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • claude-scholar by Galaxy-Dawn · ⭐ 5.2k

    Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ai-devkit?

ai-devkit is The control plane for AI coding agents.. It is categorized as a MCP Server with 1.6k GitHub stars.

What programming language is ai-devkit written in?

ai-devkit is primarily written in TypeScript. It covers topics such as agent-framework, agent-skills, ai.

How do I install or use ai-devkit?

You can find installation instructions and usage details in the ai-devkit GitHub repository at github.com/codeaholicguy/ai-devkit. The project has 1.6k stars and 252 forks, indicating an active community.

What license does ai-devkit use?

ai-devkit 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 ai-devkit?

The top alternatives to ai-devkit on Agent Skills Hub include hcom, pilot-shell, quint-code. 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 MCP Server tools