swnotmetal/Project-Koma
by Various
Lightweight, agent-friendly AI security toolkit for Node.js & TypeScript. Check if your agent has loaded the skill, Stop prompt injection, audio hallucinations, and RAG data scrapi
MCP
swnotmetal/Project-Koma
Added 8 Sept 2026
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 claudeClients listed in this record (not verified here)
Claude Code, VS Code, ChatGPT
Notes
12 stars on GitHub. Last updated 2026-09-07. Licensed MIT.
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
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
MetaGPT
Various
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
AutoGPT
Community
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.