.NET packages

  • Microsoft.KernelMemory.WebClient: The web client library, can be used to call a running instance of the Memory web service. .NET Standard 2.0 compatible.

    Nuget package Example code

  • Microsoft.KernelMemory.SemanticKernelPlugin: a Memory plugin for Semantic Kernel, replacing the original Semantic Memory available in SK. .NET Standard 2.0 compatible.

    Nuget package Example code

  • Microsoft.KernelMemory.Abstractions: The internal interfaces and models shared by all packages, used to extend KM to support third party services. .NET Standard 2.0 compatible.

    Nuget package

  • Microsoft.KernelMemory.MemoryDb.AzureAISearch: Memory storage using Azure AI Search.

    Nuget package

  • Microsoft.KernelMemory.MemoryDb.Postgres: Memory storage using PostgreSQL.

    Nuget package

  • Microsoft.KernelMemory.MemoryDb.Qdrant: Memory storage using Qdrant.

    Nuget package

  • Microsoft.KernelMemory.AI.AzureOpenAI: Integration with Azure OpenAI LLMs.

    Nuget package

  • Microsoft.KernelMemory.AI.LlamaSharp: Integration with LLama LLMs.

    Nuget package

  • Microsoft.KernelMemory.AI.OpenAI: Integration with OpenAI LLMs.

    Nuget package

  • Microsoft.KernelMemory.DataFormats.AzureAIDocIntel: Integration with Azure AI Document Intelligence.

    Nuget package

  • Microsoft.KernelMemory.Orchestration.AzureQueues: Ingestion and synthetic memory pipelines via Azure Queue Storage.

    Nuget package

  • Microsoft.KernelMemory.Orchestration.RabbitMQ: Ingestion and synthetic memory pipelines via RabbitMQ.

    Nuget package

  • Microsoft.KernelMemory.ContentStorage.AzureBlobs: Used to store content on Azure Storage Blobs.

    Nuget package

  • Microsoft.KernelMemory.Core: The core library, can be used to build custom pipelines and handlers, and contains a serverless client to use memory in a synchronous way, without the web service. .NET 6+.

    Nuget package Example code

Packages for Python, Java and other languages

Kernel Memory service offers a Web API out of the box, including the OpenAPI swagger documentation that you can leverage to test the API and create custom web clients. For instance, after starting the service locally, see http://127.0.0.1:9001/swagger/index.html.

A python package with a Web Client and Semantic Kernel plugin will soon be available. We also welcome PR contributions to support more languages.