phi3-mini

AronaOS is an offline AI-powered personal assistant that helps you manage tasks, set reminders, and recall context-aware conversations. Built with Python, Flask, and local LLMs like Phi-3 Mini, it's designed for both privacy and productivity.

🎧💡 EchoSummarize: A YouTube video summarizer using the Phi-3.5-mini LLM, providing fast and accurate summaries of video transcripts.

Ollama Text Based DnD AI Dungeon Master

Offline voice + text chatbot running on local Llama model — zero API costs, full privacy. Streamlit UI with speech input and text conversation. Runs 100% on your machine.

Local Small Language Model + FastAPI + LangGraph + SQLite implementation of a local-first multi-agent application processing pipeline.

Serving and deploying LLMs with Bento Ecosystem.

AI Powered KOL Recommendation System

Deploy your own n8n instance on Kubernetes with preconfigured Ollama and the phi3:mini model for local AI workflows.

Hybrid AI orchestration stack combining local LLMs (Ollama), vector search (Qdrant), and Azure AI Foundry for scalable RAG, Agentic AI, and Vision. Built with .NET 8 and Python.

An AI analyst with a hybrid LLM architecture 🤖. Uses a fine-tuned Phi-3 Mini (3.8B) for local RAG answer generation & Gemini 1.5 Pro for query analysis of SEC filings (AAPL, MSFT, GOOG, AMZN, META).

A complete AI-powered FAQ chatbot for Telegram

A fully local, privacy-first PDF chatbot using Weaviate Hybrid Search + Ollama (Gemma/Phi). Upload any PDF and ask questions — no cloud APIs, runs entirely on your machine.

Small POC for a STT Python module using faster-whisper to convert wav files into parsed text.

Fully automated AI development stack with Ollama, n8n, React, and Node.js. One-command deployment with cross-platform support (Linux/macOS/Windows).

A Retrieval-Augmented Generation (RAG) assistant designed to run 100% locally. It enables the analysis of sensitive industrial documents without data leaving the infrastructure, ensuring privacy and eliminating cloud costs.

To build a Retrieval-Augmented Generation (RAG) system from scratch, you must first create an ingestion pipeline to load and process your data into a vector store (by chunking documents, generating embeddings, and storing them). Then, you build a retrieval pipeline to embed a user's query, search the vector store for relevant chunks, and pass these

Generate meaningful git commits with local AI. Powered by Microsoft's Phi-3 Mini SLM.

A whiteboard capture platform that turns classroom boards into searchable lecture records, summaries, and exportable documents

SafeLens is an Autonomous Privacy Agentic AI Web Extension that lives in your browser, detects invisible trackers, and "poisons" their data.

LLM & NLP Automated customer support ticket prioritizer.