Ollama 0.15.0 was released today, introducing the new "ollama launch" command. This command allows users to directly integrate Ollama's models with various large language models, including Claude Code, Codex, OpenCode, and Droid, without requiring separate configuration. The update also resolves an issue where creating multi-line strings with triple quotes would not function correctly when using "ollama run". Additionally, support for Ctrl+J and Shift+Enter has been added to insert newlines in "ollama run". Memory usage for GLM-4.7-Flash models has been further reduced in this version. This follows the 0.14.3 release from yesterday, which added Z-Image Turbo Text-to-Image and GLM-4.7-Flash LLM support.