# 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.

Repository: https://github.com/shuyu-labs/AntSK
Canonical: https://ross.abutalabs.com/products/antsk
Homepage: https://antsk.cn
Language: CSS
License: NOASSERTION
License Family: other
Topics: dotnet, ai, rag, agnet, sk
Last push: 2025-11-06T02:32:08+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 50, release rhythm 50, longevity 67
- inputs: {"age_days": 944, "days_push": 301, "days_rel": 332, "gap_med": 14.5, "n_releases_24m": 13}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1325, forks 214 (observed 2026-08-28T04:04:22.518628+00:00)

## What it is
AntSK is an enterprise AI knowledge base and agent platform built on .NET 9, Blazor, Semantic Kernel, and Kernel Memory. It supports importing documents (Word, PDF, Excel, Markdown, etc.) for RAG-based Q&A, running local offline models via llama.cpp/Ollama/LlamaFactory, text-to-image with Stable Diffusion, and exposing features through API and plugin systems.

## Use cases
- build an offline enterprise knowledge base chatbot
- ask questions over company PDFs and Word docs
- run a self-hosted RAG app with local LLMs
- create custom GPT-style AI assistants
- integrate AI Q&A into other apps via API
- query databases with natural language (Text2Sql)
- deploy AI in air-gapped or domestic (xinchuang) environments

## When to choose
- you need a .NET-based self-hosted RAG/knowledge base platform
- you must run models fully offline or on-premises for privacy
- you want document Q&A with local embedding and rerank models
- you need API/plugin extensibility and multi-model management

## When to avoid
- you need a lightweight library to embed in an existing app rather than a full platform
- you require a permissive open-source license for rebranding (logo/name changes are restricted)
- you need advanced features like GraphRAG, flow orchestration, or RBAC which are commercial-only

## Facets
- artifact type: application
- maturity: active
- function: rag, chatbot, llm-inference, agent-framework, search-engine, api-framework, plugin-system, stable-diffusion, ocr
- domain: large-language-models, chatbots, self-hosted, web-development
- platform: dotnet, cross-platform, self-hosted
- tags: semantic-kernel, kernel-memory, blazor, knowledge-base, offline-ai, gguf, ollama, text2sql, knowledge-graph, chinese-ai, retrieval-augmented-generation, ai-agents, natural-language-processing, docker, web-server

## Member repositories
- shuyu-labs/AntSK (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.518628+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:46:36.040140+00:00, confidence not recorded.
  - readme: https://github.com/shuyu-labs/AntSK (fetched 2026-08-28T04:04:22.518628+00:00, sha 17317c90ea6d)
  - homepage: https://antsk.cn (fetched 2026-08-29T12:05:35.633189+00:00, sha 147d416d4725)
  - site_page: https://antsk.cn/pricing.html (fetched 2026-08-29T12:05:35.637052+00:00, sha 32520ab57712)
- Data as of 2026-08-30T08:39:29.467469+00:00.