We just launched stable support for local LLM models with Ollama in Agent today - our Computer-use agent framework on macOS. Repo here: <a href="https://github.com/trycua/cua">https://github.com/trycua/cua</a><p>Run models like Gemma3, Phi4, Qwen2.5, Llama3.1 & more supported by Ollama, keeping your data completely private - no cloud required.<p>Agent with local LLMs combines UI grounding with pixel-detection for accurate computer control with
Pyautogen OmniParser - all in Cua's sandboxed environment for security.<p>Privacy-conscious? Local models through Ollama run entirely on your machine while maintaining the same powerful agent capabilities backed by MPS on Apple Silicon.<p>Simple to set up: just `pip install "cua-agent[all]"` and connect to your local Ollama models. Check out our examples on our repo: <a href="https://github.com/trycua/cua">https://github.com/trycua/cua</a>