Monitoring is boring

We build tools to analyze and monitor machine learning models, so you don't have to.

Yes, it is open source.
MONITORING
IS BORING


We build tools to analyze and monitor machine learning models, so you don't have to.

Yes, it is open source.
GitHub stars Evidently AI - Open-source monitoring for machine learning models | Product Hunt
How are your models doing in production?
Model Health
Quickly visualize model performance and important metrics. Get a prioritized list of issues to debug.
GET STARTED
Data Drift
Compare recent data with the past. Learn which features changed and if key models drivers shifted. Visually explore and understand drift.
GET STARTED
Target Drift
Understand how model predictions and target change over time. If the ground truth is delayed, catch the model decay in advance.
GET STARTED
Data Integrity
Know when the data is to blame. Detect missing values or features out of range. Grasp overall quality at one glance.

Available soon.
Feature Analysis
Drill down to explore feature behavior. Spot shifts in correlations and statistical properties.

Available soon.
Performance by Segment
Slice the model performance by data regions. See beyond aggregate quality, and discover where the model fails.

Available soon.
How it works
In Jupyter notebook
Prepare the data as a Pandas DataFrame, and we spin up the dashboards instantly.
As a report
Export HTML reports in one command. Share the visuals with the team and business stakeholders.


As part of the pipeline
Integrate Evidently with other tools like Mlflow or Airflow to schedule checks and log the results.
What the community says
Check out Evidently: I haven't seen a more promising model drift detection framework released to open-source yet!
Ben Wilson
Principal RSA, Databricks
I love the plug-and-play features for monitoring ML models.
Emmanuel Raj
Senior Machine Learning Engineer, TietoEVRY
Evidently is a first-of-its-kind monitoring tool that makes debugging machine learning models simple and interactive. It's really easy to get started!
Niklas von Maltzahn
Head of Decision Science, JUMO
I was searching for an open-source tool, and Evidently perfectly fit my requirement for model monitoring in production. It was very simple to implement, user-friendly and solved my problem!
Manoj Kumar
Data Scientist, Walmart Labs
Get started
$ pip install evidently
Check the complete documentation.