name: chai1
description: >
Structure prediction for protein, nucleic-acid, and small-molecule complexes
with the Chai-1 foundation model (Chai Discovery 2024,
github.com/chaidiscovery/chai-lab). Reach for this skill to predict an
antibody-antigen or protein-ligand complex from a single FASTA, to re-fold
designed binders as an AlphaFold-multimer alternative, or to drive
co-folding from Python for batched campaigns on a GPU.
license: Apache-2.0
category: biomodels
requirements: [gpu]
metadata:
display-name: Chai-1
github.com/chaidiscovery/chai-lab/blob/main/LICENSE: Apache-2.0
(relicensed at v0.4.0). verified 2026-06-30
third_party:
- kind: weights
name: Chai-1
provider: Chai Discovery
license: Apache-2.0
terms_url: https://github.com/chaidiscovery/chai-lab/blob/main/LICENSE
# SKILL.md — --use-msa-server / use_msa_server=True sends the sequence
# to the public ColabFold MMseqs2 server. No published ToS — wiki is the
# closest data-use reference.
- kind: service
name: ColabFold MSA server (api.colabfold.com)
provider: Steinegger Lab
info_url: