vtuber-plan/olah

Self-hosted huggingface mirror service. 自建huggingface镜像服务。

57
/ 100
Established

Olah provides a way for machine learning engineers and researchers to set up a local mirror of Hugging Face models, datasets, and spaces. It takes requests for these resources and intelligently caches them, allowing for faster downloads and reduced bandwidth usage on subsequent requests. This is ideal for teams or organizations that frequently download large AI/ML assets.

218 stars. No commits in the last 6 months. Available on PyPI.

Use this if your team needs to speed up access to Hugging Face models and datasets, manage local copies, or control which resources are accessible and cached within your network.

Not ideal if you only occasionally download small files from Hugging Face or don't have a shared need for accelerated access to AI/ML resources.

machine-learning-operations AI-model-deployment data-caching research-infrastructure ML-resource-management
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

218

Forks

40

Language

Python

License

MIT

Last pushed

Jul 16, 2025

Commits (30d)

0

Dependencies

23

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/vtuber-plan/olah"

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