# microsoft/kernel-memory

Research project. A Memory solution for users, teams, and applications.

Repository: https://github.com/microsoft/kernel-memory
Canonical: https://ross.abutalabs.com/products/kernel-memory
Language: C#
License: MIT
License Family: permissive
Topics: indexing, llm, memory, rag, semantic-search
Last push: 2026-06-08T22:17:50+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 40, longevity 81
- inputs: {"age_days": 1147, "days_push": 86, "days_rel": 481, "gap_med": 4.5, "n_releases_24m": 27}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2235, forks 413 (observed 2026-08-28T04:06:29.234416+00:00)

## What it is
Kernel Memory is a multi-modal AI service and .NET library for indexing datasets through hybrid data pipelines, enabling RAG, semantic search, and natural-language querying with citations. It ships as a web service, Docker container, ChatGPT/Copilot/Semantic Kernel plugin, and embedded .NET library.

## Use cases
- build a RAG pipeline over my documents
- index pdfs and query them with natural language
- add semantic memory to a chatbot or copilot
- run a memory retrieval service in Docker
- integrate memory as a Semantic Kernel plugin
- get answers from indexed data with source citations

## When to choose
- you want a reference implementation to learn RAG and memory architecture patterns in .NET
- you need a ready-made Semantic Kernel or ChatGPT memory plugin example
- you want to study hybrid ingestion pipelines with embeddings and citations

## When to avoid
- you need production software with active support - the project is archived and unsupported
- you are not on the .NET/Azure ecosystem and want a maintained solution
- you need guaranteed updates, security patches, or community help

## Facets
- artifact type: library
- maturity: abandoned
- function: rag, search-engine, llm-inference, etl, nlp, sdk, plugin-system
- domain: artificial-intelligence, large-language-models, databases
- platform: dotnet, cloud, self-hosted
- tags: semantic-memory, embeddings, semantic-kernel-plugin, chatgpt-plugin, copilot, azure, document-indexing, archived-project, research-project, retrieval-augmented-generation, search, natural-language-processing, docker, web-server

## Member repositories
- microsoft/kernel-memory (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.234416+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 2026-08-30T02:44:20.117317+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/kernel-memory (fetched 2026-08-28T04:06:29.234416+00:00, sha 9585848963b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.