Hi again! It's been a while since my last llamaMan article, and honestly the project outpaced my ability to write about it. The last update stopped at 1.2.2; we're now at 2.2.2, and the gap in between is... a lot. So instead of a release-by-release dump - no, wait. This time it *is* a release-by-release tour, but only the releases with something big in them, newest first. The patch-level fixes and wording tweaks I'll quietly skip.

llamaMan turns a single llama.cpp manager into a multi-node cluster - pool your spare PCs into one load-balanced, Ollama-compatible inference endpoint. Here's everything new across the 1.x line.

Big architectural updates for the app's maintainability and flexibility - DinD, GPU autodetection, Model Backup and Restore & other.