Harbor 0.5.0 automates local AI tool setup in one command
Harbor 0.5.0 can download, configure, connect, and start local AI tools with one command. Commands such as `harbor up webui llamacpp`, `harbor up opencode mlx`, and `harbor up hermes omlx` connect Open WebUI, OpenCode, and Hermes to backends such as MLX, OMLX, and . The main change is less manual setup.
The has also been adjusted to work better with coding agents, and Harbor now includes first-party skills that can be inspected from the command line. Services such as OpenCode can have these skills pre-installed, so Harbor can be run and configured through requests. A new `harbor pull` command chooses the right download route based on the model source.
Regular Hugging Face repositories and llama.cpp go through `huggingface-cli`, while short model names go to Ollama.
Key points
- Harbor 0.5.0 connects MLX, OMLX, and as backends for other AI tools.
- Open WebUI, OpenCode, and Hermes can be started with related backends using simple commands.
- The CLI now includes first-party skills designed to work with coding agents.
- OpenCode can use those skills so Harbor can be configured through .
- `harbor pull` routes model downloads to Hugging Face, llama.cpp , or Ollama depending on the source.