Multimodal memory agent on macOS
-
Updated
Oct 19, 2026 - TypeScript
Multimodal memory agent on macOS
Local, full Windows search replacement, clipboard manager, and launcher: files, apps, settings and semantic media search with Google's EmbeddingGemma 2.
Local image search engine powered by AI
📸 Local-first screenshots you can actually find again. Fully offline. using EmbeddingGemma2, Tesseract OCR, Whistle STT, Rust & React
embeddinggemma-2 transcribe on linux
EmbeddingGemma 2 LiteRT-LM on-device text, image, audio, and video-frame retrieval smoke tests with reproducible Mac evidence
Text-to-Image Search with EmbeddingGemma 2 as default.
인터넷 없이 내 컴퓨터에서만 동작하는 AI 기반 갤러리 앱
A Chrome extension that predicts doomscrolling rabbit holes before they happen. EmbeddingGemma maps what you read into personal attention territories, and a fine-tuned Gemma 3 270M writes your daily autopsy. Everything runs in your browser.
Private Windows 11 launcher for apps, files and system actions. Optional local AI: Laya decision models (English, multilingual, typed-decisions) for ranking and intent, Google EmbeddingGemma 2 for multimodal search, and a research-only Qwen3-4B-Instruct-2507 helper. Built with C#/.NET/WPF.
To associate your repository with the embeddinggemma-2 topic, visit your repo's landing page and select "manage topics."