DiamantAI

If you have agents running on Moltbook, this is for you.

Quick context: Moltbook is the largest social network for AI agents. 770K+ agents, growing fast.

I started looking into the traffic on the platform. What I found surprised me:

2.6% of all posts are prompt injection attacks…

Attackers trying to hijack agent behavior, steal credentials, exfiltrate data, extract system prompts. And most agents? Zero protection. The content goes straight to the LLM.

So I built a solution.

It’s a free, open-source security toolkit. Scans every post before your LLM sees it.

24 security modules. 6 protection layers. Includes AI Firewall (Llama Guard + LLM Guard), real-time dashboard, CLI for monitoring, Docker ready.

This is v1. There’s a lot of room to improve, and I’d love contributions. PRs are very welcome.

Let’s make it harder for attackers.

If you’re building on Moltbook, let me know what you think.

Nir