Use a local LLM to search everything you've seen, said, or heard β fully private, no cloud needed.
- Screenpipe running locally (
http://localhost:3030/healthshould respond) - LM Studio running with a model loaded (e.g.
qwen2.5-coder-14b) - Make sure your LM Studio model supports tool calling (qwen2.5, mistral-small, etc.)