Learning resourceResearch and knowledge

kernel-memory

Study how to build document indexing, retrieval, and cited memory for AI applications.

Stars
2,169
Forks
400
License
MIT
Updated
Updated Jul 13, 2026

Checking live repository facts…

Project overview

Kernel Memory is a reference implementation for turning documents into an AI memory layer through extraction, chunking, indexing, retrieval-augmented generation, and source citations. It can run as an asynchronous service or as an embedded component in .NET applications. The repository is archived and explicitly presented as unsupported research code, so it should be used for learning and architectural reference rather than production deployment.

Repository facts

Primary language
C#
License
MIT
Repository updated
Jul 13, 2026
Default branch
main

Resource types

Learning resourceAPI or server

Use cases

Research and knowledgeBackend development

Runtime

DockerServerless

Protocols & integrations

OpenAPI

Capabilities

Background executionMemorySummarization

Audience

Developers

Related projects

Browse more similar projects