SreejanPersonal/JARVIS-AGI — reverse-engineered prompt

Build me a Python AI voice assistant called JARVIS that I can run from the terminal. I want to talk to it with my microphone, have it understand what I said, think through the request using AI, and speak the answer back in a natural voice.

It should be able to handle normal assistant tasks like answering questions, searching the web, remembering conversation context, setting simple timers or reminders, checking basic information like weather, and reacting to voice or hotword activation. I’d also like support for image or camera analysis if available, so I can ask it what it sees.

Please set up the project cleanly with folders for the brain, speech to text, text to speech, prompts, tools, and assets. Include a simple env example for any API keys, a main script that starts the assistant, and clear install and run instructions. Look up current docs online if you need to.