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.
More from coding & agent
- Devin Oncall tops SREGym with 100% end-to-end success, auto-resolving production incidents — tianyin_xu · 2026-10-16
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Cortex A/B-tests coding-agent skills and rules by replaying developer corrections before keeping them — Samuele Giampieri · 2026-10-16
- Tool calls are the hidden bottleneck killing AI coding speed — Crabbox and 5 fixes — steipete · 2026-10-16
- Agentic sandbox WorldBox doubles GPT-6 Astra's MazeBench score, 23 to 61 gems — ZhitingHu · 2026-10-16
- Two prompts: Gemini 4 Argon turns a single-player game into full multiplayer — chongdashu · 2026-10-16