Vijil Dome: Open Source Runtime Security for AI Agents
Dome is a pip installable Python library that secures agents at runtime. It guards inputs and outputs with more than 20 content detectors, enforces tool level access control, attests agent and tool identity through SPIFFE, and emits structured audit logs. It works with LangGraph, Google ADK, Strands, and any other framework. Apache 2.0 licensed, with three lines of code to protect an agent.
.jpg)
Testimonials
“Our enterprise customers demand trust verification before deploying AI in hiring workflows. Vijil helps us ship AI agents in six weeks instead of six months while dramatically lowering compliance costs.”
“By adapting the Google Responsible Generative AI Toolkit to the needs of enterprises in various industries, Vijil provides critical capabilities for AI developers to preserve the privacy, security and safety of custom models downstream with the same rigor that went into their original release.”
