# ContinualAI/avalanche

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

Repository: https://github.com/ContinualAI/avalanche
Canonical: https://ross.abutalabs.com/products/avalanche
Homepage: http://avalanche.continualai.org
Language: Python
License: MIT
License Family: permissive
Topics: continual-learning, deep-learning, pytorch, lifelong-learning, framework, benchmarks, strategies, metrics, continualai, evaluation, library, training
Last push: 2025-03-11T16:17:01+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 10, release rhythm 8, longevity 100
- inputs: {"age_days": 2372, "days_push": 540, "days_rel": 673, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2088, forks 319 (observed 2026-08-28T04:06:12.144557+00:00)

## What it is
Avalanche is an end-to-end continual learning library built on PyTorch, developed by ContinualAI. It provides modules for benchmarks, training strategies, and evaluation metrics for reproducible continual/lifelong learning research.

## Use cases
- run continual learning experiments in pytorch
- benchmark continual learning algorithms
- reproduce continual learning paper results
- train models incrementally without catastrophic forgetting
- evaluate lifelong learning strategies with standard metrics
- create custom task streams from my own datasets

## When to choose
- you do continual or lifelong learning research on PyTorch
- you need standardized CL benchmarks, strategies, and metrics
- you want reproducible baselines for CL papers

## When to avoid
- you need standard supervised training without incremental data streams
- you work outside PyTorch (e.g., TensorFlow/JAX)
- you need production ML serving rather than research prototyping

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, benchmarking, llm-training
- domain: machine-learning, deep-learning
- platform: python, cross-platform
- tags: continual-learning, lifelong-learning, pytorch, catastrophic-forgetting, benchmarks, research, gpu

## Member repositories
- ContinualAI/avalanche (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:12.144557+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:55:40.775377+00:00, confidence not recorded.
  - readme: https://github.com/ContinualAI/avalanche (fetched 2026-08-28T04:06:12.144557+00:00, sha 3a64e7b002e9)
  - homepage: http://avalanche.continualai.org (fetched 2026-08-29T10:35:40.193039+00:00, sha 6016e6eb30b1)
  - site_page: https://avalanche.continualai.org/getting-started/why-avalanche (fetched 2026-08-29T10:35:40.202224+00:00, sha 0be6b331d708)
  - site_page: https://avalanche.continualai.org/getting-started/alpha-version (fetched 2026-08-29T10:35:40.204222+00:00, sha ef2ee686344a)
  - site_page: https://avalanche.continualai.org/getting-started/how-to-install (fetched 2026-08-29T10:35:40.206105+00:00, sha abf70988593f)
  - site_page: https://avalanche.continualai.org/getting-started/learn-avalanche-in-5-minutes (fetched 2026-08-29T10:35:40.208037+00:00, sha 2c5e7b10b81c)
  - site_page: https://avalanche.continualai.org/about-us/the-team (fetched 2026-08-29T10:35:40.212123+00:00, sha 561b504b7adb)
  - site_page: https://avalanche.continualai.org/about-us/join-us (fetched 2026-08-29T10:35:40.214213+00:00, sha b6988d494212)
  - site_page: https://avalanche.continualai.org/questions-and-issues/faq (fetched 2026-08-29T10:35:40.210392+00:00, sha b3fd4ca32af7)
- Data as of 2026-08-30T08:39:29.467469+00:00.