These are my notes: Setup # Install Docker and the Colima container runtime brew install docker colima # Start the runtime colima start (Note, I had to run: colima stop -f ; colima delete — then run Colima start again) # create docker image: docker run -d \\n -v "$(pwd):/workspace" \\n -v ollama_data:/root/.ollama \\n -p 11434:11434 \\n --name ollama-dev \\n ollama/ollama:0.21.0\n docker exec -it ollama-dev ollama pull glm-5.1:cloud docker exec -u 0 -it ollama-dev sh -c "apt-get update && apt-get install -y emacs-nox" docker exec -it \   --env OLLAMA_API_KEY=$OLLAMA_API_KEY \   ollama-dev sh -c 'export PATH="/root/.local/bin:$PATH" && ollama launch hermes --yes' Bash shell: docker exec -it ollama-dev bash # cd root # ls -a .   ..   .bash_history   .bashrc   .cache   .config   .hermes   .local   .npm   .ollama   .profile   .ssh   .zshrc # pwd /root Run Hermes Agent docker exec -it \   --env O...

 I try to only change my default tool stack slowly. Stability saves time at the cost of missing out on the fun of continually trying new things. To get stuff done, and since I am retired this is mostly writing, creating new example programs for my books, and updating older books,  I rely on: Proton's Lumo private AI Chat: almost all web searching and casual AI Chat. Google's Gemini: research. Google's gemini-cli and Antigravity for simple coding. Hermes Agent using GLM-5.1 on a dedicated VPS: all complex software design, deep research, large scale code refactoring, and updating book chapters with minor edits when I have modified software examples. ollama launch claude --model qwen3.6:35b-a3b-nvfp4: when I really want the joy of using a local model.