PyOD

7.1easy start · #6 of 19
in Anomaly Detection Software

Free to practise onyes
Free trialnot on record
Well documentedyes
Runs where you workyes

Runs on api, Linux, Mac, self-hosted, Windows.

PyOD is ranked #6 of 19 in anomaly detection software on The Geeks Club. It runs on API, Linux, macOS, Self-hosted, Windows. There is a free plan.

PyOD plans and pricing

All plans

PyOD Free Open-source Python library · optional capabilities require pip extras pyod.readthedocs.io · 30 Sept 2026

Compared on anomaly detection software

Free plan: Yes
Detection method: hybrid
Real-time detection: Yes
Supported data: tabular, time series, graph, text, image, audio
Deployment options: self-hosted
Anomaly explanations: Yes

Best PyOD alternatives

See all 18

Metaplane 0 of 4 in the starter kit Lesson 17.6 OpenSearch 0 of 4 in the starter kit Lesson 27.2 Anomalib 0 of 4 in the starter kit Lesson 37.1 ManageEngine NetFlow Analyzer 0 of 4 in the starter kit Lesson 47.1 ObservabilityOS 0 of 4 in the starter kit Lesson 57.1 Soda 0 of 4 in the starter kit Lesson 77.1

The record

Purpose: PyOD is a Python library for anomaly detection.
Data types: PyOD 3 documents detectors for tabular, time-series, graph, text, image, and audio data.
Detector count: The documentation lists 61 detectors across its supported data types.
Usage: PyOD offers a classic detector API, ADEngine lifecycle orchestration, and an agentic investigation workflow.
Agent integrations: The installation guide describes activation paths for Claude Code, Codex, and MCP-compatible agents.
Python integration: ADEngine can be used as a standalone Python API without an LLM.
Distribution: The guide documents installation through pip, conda-forge, or from source.
Requirements: The installation guide lists Python 3.9 or higher as a requirement.
Optional components: Optional pip extras include support for PyTorch detectors, graph detectors, embeddings, audio, and an MCP server.
Support: The FAQ invites users to open an issue or contact the maintainer at [email protected].
Contribution criterion: PyOD says contributors to newly proposed detectors should commit to at least two years of maintenance.
Detector catalog: The documentation describes 61 detectors across multiple data types, exposed through one API.
Lifecycle orchestration: ADEngine profiles data, selects benchmark-backed detectors, runs multiple detectors in parallel, computes consensus scores, and reports diagnostics.
Agent support: PyOD provides an od-expert skill for Claude Code and Codex, plus an optional MCP server for MCP-compatible agents.
Price from: Free

Where it ranks on The Geeks Club

Best Anomaly Detection Software in 2026#6 of 19

Is PyOD yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote PyOD

Sources

pyod.readthedocs.io/en/latest/· checked 30 Sept 2026
pyod.readthedocs.io/en/latest/install.html· checked 30 Sept 2026
pyod.readthedocs.io/en/latest/pyod.ad_engine.html· checked 30 Sept 2026
pyod.readthedocs.io/en/latest/faq.html· checked 30 Sept 2026
pyod.readthedocs.io/en/latest/examples/adengine.html· checked 30 Sept 2026
pyod.readthedocs.io/en/latest/model_persistence.html· checked 30 Sept 2026
pyod.readthedocs.io/en/latest/about.html· checked 30 Sept 2026
pyod.readthedocs.io· checked 28 Sept 2026