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