vtuber-plan/olah
Self-hosted huggingface mirror service. 自建huggingface镜像服务。
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.
Stars
218
Forks
40
Language
Python
License
MIT
Category
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.
Related tools
containers/ramalama
RamaLama is an open-source developer tool that simplifies the local serving of AI models from...
av/harbor
One command brings a complete pre-wired LLM stack with hundreds of services to explore.
RunanywhereAI/runanywhere-sdks
Production ready toolkit to run AI locally
runpod-workers/worker-vllm
The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
foldl/chatllm.cpp
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)