embeddinggemma

Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.

EmbeddingGemma2 resources: local search apps, decision models, inference frameworks, tutorials, and datasets. English / 简体中文.

Popcorn Society - a full-stack movie discovery app with a voice-first AI concierge, explainable recommendations, and GitOps delivery to a self-hosted k3s cluster.

Local multimodal RAG for PDFs: MinerU, embeddinggemma-2, FAISS, BM25, BGE reranking and Ollama. Runs on your hardware via web and desktop; summaries, outlines and quizzes of any document.

This VL-JEPA implimentation takes direct insperation from the original VL-JEPA paper

🔒 100% Private RAG Stack with EmbeddingGemma, SQLite-vec & Ollama - Zero Cost, Offline Capable

MedGEM brings Google's MedGemma and MedASR to offline Android devices for private, multimodal clinical support anywhere.

Find files by what's in them: photos, PDFs, docs, voice memos and video, on your own computer. EmbeddingGemma 2 + llama.cpp; CLI, app and MCP server for agents.

ComptaRAG is an agentic RAG assistant for accounting and financial-law questions, aimed especially at professionals in Tunisia. It combines IFRS knowledge with Tunisian tax and accounting regulations, and grounds every answer in retrieved source material instead of relying on the model's own memory.

Native MLX Swift text, image and audio embeddings for EmbeddingGemma 2, with validated 8-bit weights and Mac/iOS examples.

A high-performance, production-ready Rust microservice for Google's EmbeddingGemma-300M, serving embeddings via HTTP and gRPC with ONNX Runtime.

saan a private, local AI file search launcher for Windows. On-device semantic search (EmbeddingGemma), grep and glob in one box. Rust + Tauri.

Search your notes, PDFs and screenshots by meaning, locally on the CPU

Google's New 500MB 4-Modality AI That Runs on Phones! (EmbeddingGemma 2 Review) - On-device 740M multimodal embedding model for semantic search, codebase indexing, and cross-modal media retrieval.

GameMaker y GML en español: biblioteca verificada y skill para tu IA. Desarrollo con especificación, pruebas, revisión y búsqueda semántica local.

A multi-tenant knowledge-base service for agents

Chat with your photos, search and edit them, 100% on your Mac. Built on EmbeddingGemma 2 and Gemma 4.

A self-hosted SearXNG-based metasearch and research platform for Richmack OS with private multi-engine search, custom search workflows, Docker deployment, and programmable information retrieval.

Multimodal semantic search across text, images, audio and video using Google's EmbeddingGemma 2, PostgreSQL + pgvector and FastAPI. One text query searches every media type in a shared 768-dimensional vector space. Runs locally with Docker Compose.

Speech-to-text built on the EmbeddingGemma 2 audio encoder with a trained reader: Android on LiteRT, iOS and macOS on Core AI