Show HN: AgentArmor – open-source 8-layer security framework for AI agents

Sobre

I&#x27;ve been talking to founders building AI agents across fintech, devtools, and productivity – and almost none of them have any real security layer. Their agents read emails, call APIs, execute code, and write to databases with essentially no guardrails beyond &quot;we trust the LLM.&quot;<p>So I built AgentArmor: an open-source framework that wraps any agentic architecture with 8 independent security layers, each targeting a distinct attack surface in the agent&#x27;s data flow.<p>The