swnotmetal/Project-Koma

Overview

Lightweight security toolkit for AI agents built in Node.js and TypeScript. It verifies that an agent has loaded a skill, and provides protections against prompt injection, audio hallucinations, and RAG data scraping. The package has zero dependencies and is released under the MIT license.

Best for

Best for
Node.js developers building secure AI agents

Use cases

• Verify that an agent has loaded a required skill before execution
• Block prompt injection attempts in agent conversations
• Prevent RAG data scraping from agent memory stores

How to use

Install

npx koma-miko init --host claude

Tested with

Claude Code, VS Code, ChatGPT

Notes

Lightweight security toolkit for AI agents built in Node.js and TypeScript. It verifies that an agent has loaded a skill, and provides protections against prompt injection, audio hallucinations, and RAG data scraping. The package has zero dependencies and is released under the MIT license.

12 stars on GitHub. Last updated 2026-09-07. Licensed MIT.

Use cases

• Verify that an agent has loaded a required skill before execution
• Block prompt injection attempts in agent conversations
• Prevent RAG data scraping from agent memory stores

Pros

• Zero dependencies keeps the toolkit lightweight
• MIT license allows free use and modification
• TypeScript native for type-safe integration

Cons

• Low star count suggests limited community validation
• Focused on Node.js and TypeScript only
• Specific to agent security, not a general-purpose toolkit

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.