How does it run the LLMs? Or does it call a API to llama.cpp/ollama/etc. ?

During normal usage, how often does it try to parse info from the screen capture? Once a minute?

You can decide which AI provider you use, either local through Ollama for example, using your own cloud API key, or using Screenpipe cloud. We also support confidential inference through tinfoil.sh

Screenpipe captures accessibility tree and screenshot when you perform a meaningful action. It doesn't use AI at recording time (except PII removal and OCR infrequently). So it can be every few hundred milliseconds to few minutes or more (if screen idle or sleeping)

We usually benchmark CPU usage on $200 Windows/MacOS laptop