Machine Unlearning Python Packages

dare-rf

Machine Unlearning for Random Forests

tombstone-erase

Track where a data subject's data actually went across a RAG/LLM stack, erase it everywhere, and get a receipt that says what was verified and what was not.

conmedrl

Offline constrained reinforcement learning toolkit for critical-care research, with ICU data processing, FQI/FQE, and interoperability tools.

supreme-unlearning

Multi-GPU framework for reproducible image-unlearning evaluation, with independent training, unlearning and evaluation seeds and extensible datasets, models, methods and metrics. Published at WIPE-OUT 2 (ECML-PKDD 2026).

traceprop

Computation-level data lineage, gradient attribution, and provenance-guided unlearning in production ML.

forgetful-ml

An unlearning framework that enables AI models to selectively forget learned data, ensuring compliance, privacy, and adaptability.

unlearun

Machine Unlearning in Large Language Models for PyTorch