Omni – Local-first multimodal file search on macOS

Name: Omni – Local-first multimodal file search on macOS
Availability: InStock
Author: artex_xh

by artex_xh·Jun 5, 2026·6 points·2 comments

Visit Project View on HN

AI Analysis

●●●BangerWizardryZero to OneDark Horse

Native MLX-Swift transformer port with no Python when every alternative needs cloud APIs.

Strengths

•Pure Swift MLX-Swift transformer port runs entirely on Apple silicon GPU
•Unified vector space indexes text, code, PDFs, images, audio, video together
•Local HTTP server exposes search to agents like OpenClaw and Hermes

Weaknesses

•Indexing slow even on M3 Ultra, fans spin hard with high power draw
•Apple silicon only, macOS 14+ requirement excludes Intel Macs and Windows

Post Description

Finally made something I've always wanted, using the model we built.

• SOTA omni embedding model, fully local, indexes text, PDF, image, audio, and video • Swift-native app UI + mlx-swift-transformer core. No Python. • Tested on M3 Pro 18G / M3 Ultra 512G / M4 Pro 48G. All work fine. • HTTP server exposes search to local agents like OpenClaw & Hermes − Indexing still feels slow even on the latest M3 Ultra, ranging from 10K tps to 300 tps depending on file type − Fans go crazy, high power draw while indexing − Search is near-instant. Multimodal relevance is sometimes arguable, but the idea is recall (the agentic LLM takes the results and refines for the final answer), so maybe that's fine