RosettaCommons/foundry
Central repository for biomolecular foundation models with shared trainers and pipeline components
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
No releases in the last 90 days; the most recent was 317 days ago, with 42 contributors on GitHub.
Peaked at #10 in the weekly ranking the week of Dec 7, its best in the past year.
Use Cases & Benefits
- Provides a unified platform for training and using biomolecular foundation models for protein design, folding, and inverse folding.
- Integrates multiple state-of-the-art models with shared infrastructure, enabling seamless workflows and consistent biomolecular structure processing.
- Use for designing novel protein structures under complex constraints using the RFdiffusion3 generative model.
- Use for predicting protein and protein-DNA complex structures with the RosettaFold3 neural network.
- Use for designing diverse protein sequences for fixed backbones using lightweight inverse-folding models like ProteinMPNN and LigandMPNN.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
- Contributing guide: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
Foundry provides tooling and infrastructure for using and training all classes of models for protein design, including design (RFD3), inverse folding (ProteinMPNN) and protein folding (RF3).
All models within Foundry rely on AtomWorks - a unified framework for manipulating and processing biomolecular structures - for both training and inference.
Downloading weights Models can be downloaded to a target folder with:
where
checkpoint-dirwill be~/.foundry/checkpointsby default. Foundry always searches~/.foundry/checkpointsplus any colon-separated entries in$FOUNDRY_CHECKPOINT_DIRSduring inference or subsequent commands to find checkpoints.base-modelsinstalls the latest RFD3, RF3 and MPNN variants - you can also download all of the models supported (including multiple checkpoints of RF3) withall, or by listing the models sequentially (e.g.foundry install rfd3 rf3 ...). To list the registry of available checkpoints:To check what you already have downloaded (searches
~/.foundry/checkpointsplus$FOUNDRY_CHECKPOINT_DIRSif set):See
examples/all.ipynbfor how to run each model and design proteins end-to-end in a notebook.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
202+32
Open issues
101+17
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| RosettaCommons/foundry | 1.0K | — | 39 | 317 days ago |
| Category median | 56.0K | +2.3K | 29 | — |
Discover Repositories
Search across tracked repositories by name or description