Show HN: Omni – airgapped macOS multimodal search over local files

Category: ai-ml

Tags: semantic-search, local-ai, macos, multimodal, mlx

Score: 7.8/10 (Innovation: 7, Technical: 9, Documentation: 8, Utility: 7)

Omni is an airgapped macOS app that performs multimodal semantic search over local files using an on-device MLX-Swift port of a unified embedding model. It's notable for combining multiple modalities (text, code, images, audio, video) into a shared vector space with native Apple GPU acceleration and an innovative batching/priority system for responsive indexing and search.

Target audience: backend devs, data engineers

Repository: https://github.com/hanxiao/omni-macos/ · Swift · Apache-2.0 · 1 stars

View on Hacker News