USC-FORTIS/AD-AGENT
A multi-agent framework to fully automate anomaly detection in different modalities, tabular, graph, time series, and more (work in progress)!
LLM-driven agents orchestrate the full AD lifecycle—preprocessing, algorithm selection, detection, and explanation—by integrating domain-specific libraries (PyOD, PyGOD, TSLib) with LLM reasoning for automated pipeline generation from natural language. The multi-agent architecture decouples specialized modules for extensibility, while privacy-aware design and human-in-the-loop capabilities enable iterative refinement and regulated deployment.
Stars
90
Forks
31
Language
Python
License
BSD-2-Clause
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/USC-FORTIS/AD-AGENT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
U1MindSec/genai-security-agent-capstone-2025
Capstone project for building a GenAI-driven Security Assistant using LangGraph, Gemini, and SerpAPI.
OjasD07/scaler-openenv-hackathon
A realistic OpenEnv environment for training AI agents to perform enterprise email triage across...
JackTheProgrammer/Sentinel-ML-security-CRAG-agent
A CRAG agent crafted using Gemini, langgraph and python to audit the ML scripts before deploying...
789sultansahil-boop/AI-101-Python-for-AI-From-Basics-to-Real-World-Projects
🐍 My Python journey for AI & Agentic Systems — learning from basics to building real AI Agents,...
igotbitchesallongmydickneveryday/genai-security-agent-capstone-2025
🛡️ Detect and remediate cloud security misconfigurations in real-time with a Generative...