Rasa provides an open source framework for automating text and voice conversations, including chatbots and voice assistants.
Open source
24 alternativesPyOD
PyOD provides Python tools for anomaly detection across tabular, time series, graph, text, image, and audio data.
About PyOD
PyOD is an open-source Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. It provides 61 detectors through a single API and includes ADEngine, an orchestration core that can choose, compare, and assess detectors automatically. The classic fit/predict API remains available.
For agent use, Claude Code and Codex can use the od-expert skill to drive ADEngine investigations, and MCP-compatible LLMs can access ten stateless tools for knowledge queries, planning, and detection. MCP support requires the optional mcp extra. Full multi-turn agentic investigation is available through the od-expert skill for Claude Code and Codex, while stateful investigate/iterate MCP tools are deferred.
Key features
- 61 detectors across tabular, time series, graph, text, image, and audio data
- Single API for classic fit and predict anomaly detection workflows
- ADEngine orchestration automatically selects, compares, and assesses detectors
- od-expert skill enables Claude Code and Codex agentic investigations
- MCP server exposes ten stateless tools for MCP-compatible LLMs
- Benchmark-backed routing uses ADBench, TSB-AD, BOND, and NLP-ADBench
Best for: Data scientists and machine learning engineers who want an open-source Python library for anomaly detection across multiple data modalities, including options for agent-driven workflows.
Good for
- Open-source Python library with a classic fit/predict API.
- Supports 61 detectors across tabular, time series, graph, text, image, and audio data through one API.
- Includes agent-facing paths: od-expert for Claude Code/Codex and an MCP server for compatible LLMs.
Watch out for
- Full multi-turn agentic investigation requires the od-expert skill for Claude Code or Codex.
- MCP server usage requires the optional mcp extra.
- Stateful investigate and iterate MCP tools are deferred.
PyOD at a glance
- Website
- github.com/yzhao062/pyod
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
PyOD alternatives
Tools and sites you could use instead, ranked by how closely they match.
DeepAnalyze uses an agentic language model for autonomous data science and report generation.
Open source
24 alternatives
Agentic Context Engine aims to help agents learn from their execution experience.
Open source
24 alternatives
This repository provides code for building agents controlled by large language models.
Open source
24 alternatives
Unified interface for constructing and managing workflows on different workflow engines.
Open source
24 alternatives
PromptMage helps create and manage workflows for large language models.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
PyOD FAQ
What data types does PyOD support?
It provides detectors for tabular, time series, graph, text, image, and audio data.
How can AI agents use PyOD?
Claude Code and Codex can use the od-expert skill, and MCP-compatible LLMs can use the MCP server's ten stateless tools for knowledge queries, planning, and detection.
How do I install PyOD and its MCP support?
Install the core library with pip install pyod. MCP support requires the optional mcp extra, installed with pip install pyod[mcp].
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.