Understand the project
Practical overview
When it fits
Use Pyod when an anomaly-detection project is implemented in Python and may need detectors for multiple data types rather than a single tabular dataset.
Who it is for
- Python developers building anomaly-detection workflows
- Data and machine-learning teams working with varied data modalities
- Teams developing fraud-detection or operational-monitoring systems
- Builders exploring graph, text, image or audio anomaly analysis
Documented uses
- Detect unusual records in tabular data
- Identify unusual events in time-series data
- Find anomalous nodes or relationships in graph data
- Analyze image, audio or text inputs for unusual patterns
- Coordinate anomaly-detection work through the described ADEngine orchestration
Before you choose
Requirements & limits
The project has a public GitHub repository and is released under the BSD-2-Clause license. It is described as a Python library for desktop, server and self-hosted environments.
- Python is the documented programming language and ecosystem.
- The supported scope spans tabular, time-series, graph, text, image and audio data.
- The repository describes more than 60 detectors rather than a single detection method.
- ADEngine orchestration and an agentic workflow are documented as part of the project description.
- The BSD-2-Clause license is identified in the public repository.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 2 October 2026
- Original website title
- yzhao062/pyod · Official homepage title · retained in its source language