Microsoft open-sources Kernel Memory, a ready-to-use RAG pipeline supporting multi-modal data

blaizedsouza · x · 2026-08-21

Microsoft has quietly released Kernel Memory, an open-source, out-of-the-box RAG (Retrieval Augmented Generation) pipeline. Users simply drop in data—PDFs, Word docs, web pages, or images—and the system automatically handles text extraction, chunking, embedding, and storage. It supports semantic and hybrid search, returning grounded answers with citation links and token usage stats. The tool flexibly integrates with various models (e.g., Azure OpenAI, Ollama, Anthropic) and vector databases (e.g., Qdrant, pgvector), with every step being swappable, significantly lowering the barrier to building memory systems for agents and AI apps.

Original post →

More from coding & agent

coding & agent channel →