klieret/wandb-offline-sync-hook

A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!

48
/ 100
Emerging

When running machine learning experiments on isolated compute nodes without internet access, this tool helps you regularly send your experiment results to Weights & Biases (W&B) for live tracking. Your offline experiment logs go in, and continuously updated W&B dashboards come out. This is for machine learning engineers, researchers, or data scientists training models in secure or air-gapped environments.

Use this if you train machine learning models on compute nodes that lack internet access but share a file system with a head node that does have internet, and you want to keep your Weights & Biases dashboards updated in near real-time.

Not ideal if your compute nodes already have direct internet access or if you are not using Weights & Biases for experiment tracking.

machine-learning-operations experiment-tracking secure-ml-training distributed-training data-science-workflow
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

90

Forks

10

Language

Python

License

MIT

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/klieret/wandb-offline-sync-hook"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.