As AI agents proliferate across enterprises, a critical blind spot emerges: who watches the agents?They can be hijacked via prompt injection, communicate secretly with each other, or produce dangerous outputs — all without any human noticing.
ARGUS solves this with an AI agent that monitors other AI agents in real time — using Google ADK, Gemini 3.5 Flash, and Arize Phoenix to detect threats, run evaluations, and continuously improve its own detection rules from observability data.
Agent runtime for all 16 agents including ARGUS monitor
LLM powering every agent — fast, capable, agentic
Observability platform — traces, spans, evaluations
ARGUS reads its own traces to self-improve detection
Backend API serving all 15 agents + ARGUS endpoints
Frontend dashboard with real-time threat monitoring
Serverless hosting for the FastAPI backend
Instrumentation standard for tracing agent actions
ARGUS evaluates every agent response for quality
3rd Year CSE