local-llm

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

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.

为DSH接入本地大模型能力：在「设置→插件」页一键启停本地 llama.cpp 大模型（双槽x双模态x双预设），卡片内配置、一条命令安装、自动注册，装完即用| Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to use

贵脑+贱手: cloud-orchestrator + local-worker lanes (delegate & read-only scout) for DeepSeek Harness | 社区 Agent 预设

dsh-llm-ollama 是一个为 DeepSeek Harness（dsh）开发的社区插件，让 Harness 通过 Ollama 原生协议（/api/chat） 接入本地 Ollama 服务。即插即用：不改动 dsh 官方任何文件，安装后自动在「设置」中多出一个 Ollama 页面，并在会话模型选择器中提供该提供方的模型。

Local LLM integration plugin for DeepSeek Harness

Manage local LLM inference servers in DSH: GPU registry, parameter profiles, VRAM validation, and tok/s benchmarks for llama.cpp, SGLang, and vLLM

CedarDSH Model Probe — Detects reasoning and image support for custom DeepSeek Harness models.

When you use DeepSeek harness,you may hate that the big fish is always thinking in English,not Chinese(or the other language).Dot't worry,Deepseek has written an Plugin to translate it,but with qwen 3.5 0.8B's help......This Plugin will translate thinking without API.It is helped by deepseek V4 pro.