aimagelab/mammoth

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

67
/ 100
Established

This framework helps machine learning researchers efficiently develop, test, and compare different continual learning algorithms. It takes your datasets and model definitions as input, and outputs performance metrics and comparisons across over 70 existing methods. Machine learning researchers and practitioners focused on models that adapt over time would use this tool.

788 stars. Actively maintained with 10 commits in the last 30 days.

Use this if you are a machine learning researcher or practitioner who needs to rigorously benchmark and experiment with continual learning algorithms and datasets.

Not ideal if you are looking for a pre-built, production-ready continual learning solution for immediate deployment without deep algorithm development.

continual-learning machine-learning-research model-benchmarking deep-learning-development AI-research
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

788

Forks

149

Language

Python

License

MIT

Last pushed

Mar 02, 2026

Commits (30d)

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aimagelab/mammoth"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.