steineggerlab/foldseek
Foldseek enables fast and sensitive comparisons of large structure sets. observed · 2026-08-28
Health v2 · maintenance only
67/100
- Activity 99
- Release rhythm 8
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2781
- days_rel: 591
- days_push: 9
- n_releases_24m: 1
Adoption not part of the score
1283 stars · 157 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
Foldseek is a command-line tool for fast and sensitive comparison, search, and clustering of large protein 3D structure sets, including monomer and multimer (complex) searches. It runs on CPU with optional GPU acceleration and can compare proteins directly from sequences using a language model without precomputed structures.
Use cases
- search a protein structure database for structural homologs
- cluster large sets of predicted protein structures
- align protein complexes with Foldseek-Multimer
- compare protein structures from sequence only using a language model
- find structural similarities across the protein universe at scale
- accelerate structure search with GPU support
When to choose
- you need to search or cluster millions of protein structures quickly
- you want sensitive structure alignment from the command line or a cluster
- you need monomer and protein-complex (multimer) structural comparisons
- you want sequence-based structural comparison without precomputed structures
When to avoid
- you only need sequence similarity search without structural context (use BLAST or MMseqs2)
- you need a GUI-only workflow (though a webserver exists, the core tool is CLI)
- you work outside structural biology and protein analysis
Facets
cli-tool · maturity active
search-engine gpu-computing bioinformatics data-science cli cloud protein-structure structure-alignment structural-bioinformatics protein-clustering multimer-search protein-language-model high-performance-computing clustering algorithms linux macos docker
2 sources
- readme: https://github.com/steineggerlab/foldseek · fetched 2026-08-28 · 8ce2841d0946
- homepage: https://foldseek.com · fetched 2026-08-29 · 50aeb2e0083d
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| steineggerlab/foldseek | main | 67 |
For agents
markdown · JSON · MCP: product_card(name="steineggerlab/foldseek")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem