csghub-server and csghub

The csghub-server is the backend infrastructure that powers the csghub frontend platform, making them complementary components of the same LLM management ecosystem rather than alternatives.

csghub-server
76
Verified
csghub
67
Established
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 1,414
Forks: 380
Downloads:
Commits (30d): 65
Language: Go
License: Apache-2.0
Stars: 5,495
Forks: 682
Downloads:
Commits (30d): 7
Language: Vue
License: Apache-2.0
No Package No Dependents
No Package No Dependents

About csghub-server

OpenCSGs/csghub-server

csghub-server is the backend server for CSGHub which helps user to manage datasets, modes, and also run Model Inference, Finetune and Application Spaces.

Built on Go with a REST API, it provides content moderation, dataset file preview (including `.parquet` formats), and Git LFS support for large file management. The architecture abstracts multiple git backends (Gitea, GitLab) and S3-compatible storage systems, enabling flexible deployment across different infrastructure providers while tracking asset metrics like downloads and engagement.

About csghub

OpenCSGs/csghub

CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

Built on a microservice architecture with standardized OpenAPIs, CSGHub enables git-based asset versioning and multi-source data synchronization while supporting deployment via Docker Compose or Kubernetes. The platform includes an AI-powered Copilot for space and asset management, end-to-end data processing with intelligent annotation, and enterprise security controls for on-premises environments where Hugging Face integration isn't feasible.

Scores updated daily from GitHub, PyPI, and npm data. How scores work