Ollama

If you’ve been waiting for a computer-use agent you can run on your own machine (sandboxed, human-in-the-loop, open source), Microsoft’s Magentic-UI is the repo to clone this week. It now leads with MagenticLite (“Big tasks. Small models.”), a redesign from Microsoft Research AI Frontiers that pairs a small-model orchestrator with a dedicated browser-use model and keeps you in control the whole way.

I run LLMs on my own machine for two reasons: my prompts never leave my hardware, and I can experiment all day without watching an API meter. The setup used to be the hard part. Wrangling Python environments, CUDA drivers, and model weights by hand was enough friction that most people quit before the first token.