yzhao062/pyod — A Python library for anomaly detection across tabular, time series, graph, text, and image data.

Description and use

pyod is an open‑source Python library that provides a comprehensive suite of more than 60 anomaly‑detection algorithms, covering tabular, time‑series, graph, text, and image data. It includes a benchmark‑validated ADEngine for orchestrating detectors and an agentic workflow that enables AI agents to select, combine, and deploy models automatically. The project targets developers who need a versatile, plug‑and‑play solution for building and scaling anomaly‑detection pipelines.

Problem

yzhao062/pyod helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

A Python library for anomaly detection across tabular, time series, graph, text, and image data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

Source