tracks up to 100 unmarked animals from videos recorded in laboratory conditions using artificial intelligence. Free and open source.

Install and all its extra tools for Windows, MacOS and Linux.

User guide

Learn how to use, from beginner to advanced usages.

Included tools

Validate, generate videos, match identities across videos and analyze trajectories.

Good videos

How to record good videos, experimental setups and example videos.

The data used in this article can be found in this repository together with videos, their optimal tracking parameters and the resulting tracked sessions.

Google Drive data repository

Source Code

The code is open and accessible at polavieja_lab/idtrackerai, feel free to contribute.

Can animals really be recognized?

A Jupyter Notebook that proves that zebrafish can be distinguished using a CNN.

Google Groups

Join the users group to ask questions and get announcements about new releases.

Polavieja Lab

This work belongs to Polavieja lab, Mathematics of Behavior and Intelligence (Champalimaud Foundation, Lisbon, Portugal).


If you encounter any problem or doubt, contact us at


See the frequently asked questions page to see if your issue has been already answered.

Funded by Fundação Champalimaud and FCT under project PTDC/BIA-COM/5770/2020