Aman janwani's profile on Product Hunt

About

I'm a full-stack developer working on VPN and infra products at 24Bytes and building my own tools on the side. Started coding in 2020, mostly live in Next.js, Node, and NestJS, and lately have spent a lot of time in Kubernetes and Ansible keeping infrastructure running across regions. I like shipping small, real things fast, seeing if people actually want them, and building on whatever gets real traction. Always looking for the next problem worth solving.

Links

Portfolio

Github

Badges

Tastemaker

Gone streaking

Gone streaking 5

Maker History

AgentinelStop AI agents from installing malicious packages.
Issues2ActionTurn GitHub issues into clear dev plans — instantly with AI.
Jun 2025
Time PortOne link. Infinite timelines. Auto-magically dynamic.
Jun 2025
Page Whisper📖 Chat with books. Learn faster. Think deeper.
Mar 2025

🎉

Joined Product HuntOctober 16th, 2021

Forums

p/agentinel

•

1d ago

Am I overthinking AI security, or is this actually useful? Need your feedback.

Hey everyone

I've been building a zero-trust local firewall for AI coding agents (like Cursor, Claude Code, etc.).

The problem I m trying to solve is that LLMs constantly hallucinate package names. Bad actors are starting to register those fake packages with malicious code (slopsquatting). So if your AI agent autonomously runs `npm install` or `pip install` on a hallucinated package, your machine gets compromised instantly.

I just spent weeks updating my tool (Agentinel) to natively intercept terminal commands across JS, Python, and Rust in under 1 millisecond. It uses a massive offline vulnerability database to block the AI from pulling malware before the shell even executes it.

•

22h ago

Agentinel - The local security guardrail for AI coding agents

Because your AI loves slopsquatting. The zero-cost, locally-run firewall for AI agents. Designed to instantly intercept hallucinated and malicious packages across JavaScript, Python, and Rust before your terminal runs them.

•

22h ago