Smart File Organizer: AI Watches Your Downloads Folder

Description and use

A local AI system running on a MacBook eliminates token costs and keeps data private.

Problem

Every token costs money, each API call adds up, and data goes to external servers.

Outcome

A local AI setup that eliminates token costs, keeps data private, and runs quickly on a MacBook.

Workflow

• Install Ollama and pull a model: brew install ollama && ollama pull llama3.2 && ollama serve
• Use the local model via HTTP API: send a POST to http://localhost:11434/api/generate with model and prompt JSON.
• Receive the response JSON and extract the response field.
• Print or use the answer in your application.

Evidence

Every token costs money. Every API call adds up. And your data goes to their servers.

Source

brew install ollama ollama pull llama3.2 ollama serve

Source

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Source