m9 is a native desktop app that turns your Mac into an enterprise-grade retrieval machine. Hybrid pipeline, parallel embedding, absolute privacy. Your data never leaves your computer.
Request informationm9 is not a ChatGPT wrapper. It's a native RAG engine built from scratch to maximize Apple Silicon hardware.
BM25 (keyword) + Dense (semantic) pipeline combined with Reciprocal Rank Fusion. It doesn't rely on vectors alone: it also finds exact matches for specific terms, names, acronyms and codes.
Leverages Apple Silicon Performance + Efficiency cores with batch-concurrent embedding. Hundreds of chunks per second, directly on the integrated GPU via Ollama.
No data leaves your Mac. LLM and embedding run locally with Ollama. No remote servers, no cloud APIs, no tracking. Your documents stay yours.
Before searching, m9 reformulates your question into different variants to maximize recall. Synonyms, paraphrases and automatic reformulations expand search coverage.
PDF, DOCX, TXT, Markdown, web pages. Ingestion from files, folders or integrated web crawler with configurable depth and automatic download of PDFs found online.
Every answer includes citations with reference to the source file and exact chunk. Maximum transparency: you can always verify where every piece of information comes from.
From ingestion to response, every stage is optimized for quality and speed.
Parallel extraction from PDF, DOCX, TXT, Web
Intelligent sentence-aware segmentation with overlap
Batch parallel embedding on Apple Silicon GPU
Dual index: LanceDB (vectors) + MiniSearch (BM25)
Reciprocal Rank Fusion with optimized BM25+Dense weights
Local LLM generates response with verifiable citations
In an era when data is the new oil, m9 chooses a different path: everything stays on your Mac.
Modern stack, native macOS, no dependencies on external services.
Fill out the form and we'll get back to you for a custom demo and quote.