local-models 3

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Web search for local models in DeepSeek Harness. DuckDuckGo by default, optional SearXNG and API providers.

dsh addon: a Local Models settings tab that starts and stops a llama-server child process living with the dsh host process.