shuyu-labs/AntSK

An AI knowledge base/agent built with .Net 9, AntBlazor, Semantic Kernel, and Kernel Memory, supporting local offline AI large models. It can run offline without an internet connection. Supports Aspire for monitoring application data.

54
/ 100
Established

# Technical Summary for AntSK Combines Semantic Kernel for AI orchestration with Kernel Memory for persistent knowledge storage, enabling RAG (retrieval-augmented generation) pipelines with local vector embeddings (BGE) and reranking. Exposes extensible plugin architecture supporting .NET DLLs, HTTP APIs, and Semantic Kernel functions, plus integrates multiple model backends (OpenAI, Azure OpenAI, iFlytek Spark, Alibaba, Ollama, LlamaFactory) with hot-swappable model switching. Built on .NET 9 Blazor Server with SqlSugar ORM supporting PostgreSQL/SQLite/MySQL, Qdrant/pgvector for vector storage, and includes OCR and Stable Diffusion text-to-image capabilities.

1,535 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,535

Forks

209

Language

CSS

License

Category

dotnet-azure-rag

Last pushed

Nov 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/shuyu-labs/AntSK"

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