online-ml/river
🌊 Online machine learning in Python
When your data is constantly arriving in real-time, such as sensor readings, financial trades, or website clicks, River helps you build machine learning models that learn and adapt continuously. You feed in individual data points as they appear, and the system provides predictions or insights immediately, updating its understanding without needing to reprocess all past information. This is ideal for data scientists or machine learning engineers who need to deploy models that can react instantly to evolving data streams.
5,746 stars. Used by 5 other packages. Actively maintained with 61 commits in the last 30 days. Available on PyPI.
Use this if you need a machine learning model that can learn incrementally from a continuous stream of new data and adapt to changes over time without requiring full retraining.
Not ideal if your data arrives in large batches and remains static, as traditional batch machine learning methods are likely simpler and more efficient for those scenarios.
Stars
5,746
Forks
609
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 09, 2026
Commits (30d)
61
Dependencies
3
Reverse dependents
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/online-ml/river"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
IFCA-Advanced-Computing/frouros
Frouros: an open-source Python library for drift detection in machine learning systems.
NannyML/nannyml
nannyml: post-deployment data science in python
Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics
Implementation/Tutorial of using Automated Machine Learning (AutoML) methods for static/batch...
etsi-ai/etsi-watchdog
Real-time data drift detection and monitoring for machine learning pipelines.
Western-OC2-Lab/PWPAE-Concept-Drift-Detection-and-Adaptation
Data stream analytics: Implement online learning methods to address concept drift and model...