Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

Evano Studio is an open-source local AI desktop app for agents, automation, knowledge, and productivity.

Gemma4.pas is a high-performance AI inference engine developed entirely in Delphi to run Google’s Gemma 4 model natively on Windows. Unlike most platforms, this project features zero external dependencies and utilizes Vulkan compute shaders to accelerate complex mathematical operations directly on the user's GPU.

Local document Q&A with Gemma 4 E4B's 128K context — no RAG, no cloud, answers cite the exact page they came from.

Applied Geometric Intelligence (AGI) - See papers for specifics

Multimodal, Multilingual AI clinical triage for healthcare workers in low-resource settings

Agentic RFP responder built in Go. Leverages Gemma 4 and an MCP knowledge base to automate proposal generation from historical quotes.

Live subtitles with vibes - AI powered real-time context-aware subtitles backed by Whisper/Qwen ASR and LLM refinement

Build and Run free AI agents with local LLM using Ollama and Langgraph

Agentic Document Intelligence system comparing OCR+Regex baseline vs LLM-powered (LangGraph + Ollama) extraction on real expense documents

AI agent that generates a personalised weekly schedule.

Real Time Multi Modal Voice Agent with Webcam / Desktop Screenshot Input

GEMMA - Guided Emergency & Medical Management Assistant

AI-Powered Repair Assistant

Globis Edge: Offline caseworker companion [Powered by Gemma 4]

Offline AI crop disease diagnostic tool for Indian farmers - Gemma 4 + Ollama

A free, fully-local English conversation practice app. Go WebSocket server that streams Gemma 4 (E4B) replies in real time, served on-device AI model with LiteRT-LM.