A lightweight, privacy-friendly chatbot powered by local LLMs using Ollama and Streamlit.
Runs entirely offline, directly on your Mac — no API keys, no cost, full control.

This project demonstrates how to build a fully local AI assistant that uses open-source Large Language Models.
The chatbot is built with Python, Streamlit, and Ollama, providing a real-time conversational UI similar to ChatGPT — but everything runs on your machine.

• 🧩 Local inference with llama3, mistral, or any Ollama-compatible model
• ⚡ Instant setup — no API keys, no billing, no internet required
• 🧠 Conversational memory within the chat session
• 💻 Built with Streamlit for a clean web interface
• 🧰 Extensible architecture — easy to integrate new models or APIs later

Still in development...