OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Antsk

Antsk is a .NET 9 and Blazor platform for creating an AI knowledge base and agent experience using Semantic Kernel and Kernel Memory. It supports retrieval-augmented question answering over imported documents, local model integrations and offline operation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Antsk — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Antsk when you need a self-hosted document knowledge base and agent interface, particularly where local-model use or offline operation matters and a .NET stack is suitable.

Who it is for

  • Organisations building an internal document-questioning knowledge base.
  • C# and .NET teams looking for a knowledge-base and agent platform built on their ecosystem.
  • Operators who need to use local inference models and run without an internet connection.

Documented uses

  • Import supported office and text files into a searchable knowledge base.
  • Ask questions grounded in retrieved document content.
  • Build a locally hosted AI assistant using supported local inference and embedding components.
  • Monitor application data with Aspire.
Before you choose

Requirements & limits

The project describes an open-source edition and a separate commercial Pro edition. Its README states the open-source edition may be used commercially subject to retaining its logo and copyright information.

  • Offline operation relies on local model and supporting components rather than a cloud inference service.
  • The documented stack includes .NET 9, Blazor Server, ASP.NET Core, Semantic Kernel and Kernel Memory.
  • The README lists SQLite and Disk as defaults and also names other relational database and vector-store options.
  • The project lists 4 CPU cores, 8 GB RAM and 50 GB SSD as a minimum, with greater resources recommended for production.
  • The README identifies visual workflow orchestration and GraphRAG as Pro features.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare AntSK for a production deployment

Apply the README’s listed security settings before deploying AntSK in production.

Before you start

  • AntSK configuration access, including appsettings.json or the ability to set environment variables.
  • A production reverse proxy such as Nginx or Caddy for HTTPS termination.

Steps

  1. Set a strong login password in the Login section of appsettings.json or through environment variables; do not use weak passwords such as admin / 123456.

  2. Keep AntSK behind an internal network or reverse proxy instead of exposing its default http://*:5000 listener directly to the public internet.

  3. Terminate TLS with HTTPS at the reverse proxy and restrict CORS to trusted domains.

  4. Apply least privilege to API callers with separate SecretKeys and RBAC roles; audit login and conversation logs, protect log-directory access, back up the database and model directories, and monitor security announcements for updates.

Expected outcome

The listed production security measures are applied before deployment.

Guide limitations

  • The README does not provide detailed configuration examples or commands for these changes.
  • These measures are security guidance; they do not establish that a deployment has been tested or verified.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AntskImport supported office and text files into a searchable knowledge base.Linux, Self-hosted, WindowsThe project describes an open-source edition and a separate commercial Pro edition. Its README states the open-source edition may be used commercially subject to retaining its logo and copyright information.
VectaurantFind menu options by describing preferences, such as asking what is vegan or spicy.CLI, Docker, Linux, macOS
Aml Multiagent RagIngest PDF regulations, extract and chunk their text, and build a searchable vector collection.Docker, Self-hostedThe repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
shuyu-labs/AntSK · Official homepage title · retained in its source language
How we review sourcesSuggest a correction