Chai-1
Family overview — summarizes releases; licenses and availability belong to each release.
Maintained by Chai Discovery125
Chai-1 is a multi-modal foundation model from Chai Discovery for predicting molecular structures, covering proteins, small molecules, DNA, RNA, glycosylations, and other modifications. It was first released in September 2024, and its license changed in November 2024 (see the release record). The chai_lab package (latest PyPI release 0.6.1, March 2025) runs it locally.134
- Repository: GitHub repository (chai-lab) (external site: github.com)
- Model hub: Chai-1 weights (Hugging Face) (external site: huggingface.co)
- License: LICENSE (Apache 2.0) (external site: github.com)
- Paper: Chai-1 technical report (bioRxiv, doi:10.1101/2024.10.10.615955) (external site: doi.org)
Releases assessed
| Release | Weights | Tier (USASI rubric v0.2) | License | Released |
|---|---|---|---|---|
| Chai-1 (weights used by chai_lab 0.6.1) | Weights: Public | Model-disclosure tier (USASI rubric v0.2): Open-weight | Apache-2.0 | Unknown |
What it is useful for
Folding complexes given as FASTA input, optionally with MSAs, templates, user-specified inter-chain contact or covalent-bond restraints, and custom embeddings, per the repository README.1
Organization context
U.S. eligibility
Eligible · basis: U.S.-governed project
Chai-1 is developed and published by Chai Discovery in its GitHub and Hugging Face organizations, and the LICENSE names Chai Discovery as copyright holder. Chai Discovery's careers page places its team in San Francisco, California, and its website terms choose California law with San Francisco courts.12567
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.