dsh plugins中文
← Back to popular plugin directory

LM Studio provides the model as DeepSeek Harness

starlightzfy/dsh-plugin-lmstudio · tools

Use a model served by LM Studio as a chat model inside the DeepSeek Harness (DSH) web GUI.

★ 0GitHub stars
0Forks
2026-08-16Last updated
JavaScriptLanguage
MITLicense

Project overview

Use a model served by LM Studio as a chat model inside the DeepSeek Harness (DSH) web GUI.

LM Studio exposes an OpenAI-compatible endpoint (http://127.0.0.1:1234/v1 by default). This plugin seeds DSH's built-in llm-pi-ai adapter with that route, so the model picker shows your local model — no cloud API quota consumed. Requirements DSH CLI + pnpm (see the DSH docs) LM Studio with Developer → Start Server running (default port 1234) At least one model loaded in LM Studio Install

The package declares dsh.bundle, so dsh plugin automatically adds it to the profile's bundle layers. Then restart the web app (dsh web) and refresh http://127.0.0.1:3080. Configuration

Install command

dsh plugin --profile web add github:starlightzfy/dsh-plugin-lmstudio
View GitHub repository ↗Back to popular plugin directory