# sokrypton/ColabFold

Making Protein folding accessible to all!

Repository: https://github.com/sokrypton/ColabFold
Canonical: https://ross.abutalabs.com/products/colabfold
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: bioinformatics, multiple-sequence-alignment, protein-structure, structure-prediction
Last push: 2026-08-10T05:54:14+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 81, longevity 100
- inputs: {"age_days": 1871, "days_push": 23, "days_rel": 50, "gap_med": 64.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2889, forks 742 (observed 2026-08-28T04:07:28.289112+00:00)

## What it is
ColabFold is a set of tools and Google Colab notebooks that make protein structure prediction with AlphaFold2, AlphaFold3, ESMFold, and related models accessible to everyone. It provides both browser-based notebooks and a local Python package for predicting protein structures and complexes.

## Use cases
- predict protein 3D structure from amino acid sequence
- model protein-protein complexes
- run alphafold2 without a local GPU
- batch predict many protein structures
- generate multiple sequence alignments with mmseqs2
- predict structures locally on my own machine

## When to choose
- you need protein structure prediction without setting up AlphaFold yourself
- you want free GPU-based prediction via Google Colab
- you want a pip-installable wrapper for local AlphaFold-style predictions

## When to avoid
- you need full control over AlphaFold internals or custom training
- you cannot use Google Colab and lack a capable GPU locally
- you need guaranteed privacy for proprietary sequences in the cloud notebooks

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, deep-learning, sdk
- domain: bioinformatics, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: protein-folding, alphafold, structure-prediction, google-colab, jupyter-notebooks, mmseqs2, computational-biology, web-server, gpu

## Member repositories
- sokrypton/ColabFold (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:28.289112+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 2026-08-30T07:35:21.526910+00:00, confidence not recorded.
  - readme: https://github.com/sokrypton/ColabFold (fetched 2026-08-28T04:07:28.289112+00:00, sha 37765eb7f790)
  - registry_pypi: https://pypi.org/pypi/colabfold/json (fetched 2026-08-29T09:50:30.800970+00:00, sha 1c77229be6fd)
- Data as of 2026-08-30T08:39:29.467469+00:00.