DeepSHPlugins
dsh-vision-LMstudio 项目预览
GITHUB / COMMUNITY PROJECT

dsh-vision-LMstudio

视觉与多模态TypeScriptBSD-3-Clause

dsh-vision-LMstudio:通过 DSH 调用 LM Studio 加载的本地视觉模型——本地识别、描述与 OCR 图片或剪贴板截图,推理全在本机,图片不出设备。

2 StarsTiankunDai 更新时间 2026-08-19
访问 GitHub 仓库
dsh-vision-LMstudio 项目预览

项目介绍

中文

dsh-vision-LMstudio:通过 DSH 调用 LM Studio 加载的本地视觉模型——本地识别、描述与 OCR 图片或剪贴板截图,推理全在本机,图片不出设备。

English

Call vision models loaded in LM Studio through DSH — local recognition, description and OCR of images or clipboard screenshots; inference stays on-device, images never leave it.

项目信息与收录信号

快照 2026-09-11
作者 / 组织
TiankunDai
仓库
TiankunDai/dsh-vision-LMstudio
GitHub Stars
2
Forks
0
开发语言
TypeScript
许可证
BSD-3-Clause
最近推送
2026-08-19
Manifest
未检测到 / 未记录

公开仓库不自动等于可商用;许可证与当前兼容性以原项目文档为准。Manifest 和数据评分不构成安装安全认证。

数据评分

57/ 100
维护活跃
85
文档与实用信息
99
生态关注度
14
安装便捷信号
80
项目声明信号
100

近 23 天仍在更新;README 含完整安装与使用说明;关注度尚低(2)。

评分来自已有数据快照的五维模型,仅作浏览参考,不是实际使用评测或安全检测结论。

安装与使用

所有项目资料与许可均以对应 GitHub 仓库为准。

git clone https://github.com/TiankunDai/dsh-vision-LMstudio.git

复制命令不会自动执行。请先阅读仓库文档,确认环境要求与许可证。

项目截图

仓库 README

GitHub 原文

已保存的仓库文档快照;文档抓取时间未记录,可能与上方目录介绍处于不同版本。安装前请核对当前仓库说明。

dsh-vision-LMstudio

English | 中文

Local LM Studio vision recognition plugin for the DSH (DeepSeek Harness) Web GUI — recognize, describe, and OCR local images or clipboard screenshots with a local vision model. All inference happens on your own machine; images never leave it.

Features

  • Agent tools (registered host-side, available in every session)
  • lmstudio_vision — recognize a local image file by absolute path
  • lmstudio_clipboard — recognize the current clipboard image (screenshot / copied image), no file path needed
  • lmstudio_models — list loaded models and mark the most recently loaded one (the auto-selected one)
  • Settings panel: "Settings → LM Studio Vision" — configure server URL / model / default

prompt / temperature / max tokens, refresh the model list, and one-click recognize a local image or the clipboard

  • Automatic model selection — without an explicit model, the most recently loaded

model is used (the first entry of the server's model list; the native /api/v0/models endpoint is filtered by state, so models that are JIT-visible but not loaded never get picked). No specific model is preset.

  • Persistent config — ~/.dsh/dsh-lmstudio-vision.json (atomic writes), shared by the

panel and the agent tools

Requirements

  • DSH (DeepSeek Harness) with the web profile
  • LM Studio with a vision model loaded and the local server started

(Developer → Start Server, default port 1234)

  • Windows for the clipboard tool (uses Windows PowerShell 5.1 Get-Clipboard -Format Image)

Install

pnpm install
pnpm build
dsh plugin --profile web add link:<path-to-this-repo>/packages/dsh-lmstudio-vision

Then restart DSH (dsh web) and refresh the page. dsh plugin appends the package to dsh.profile.bundles automatically (the package declares dsh.bundle).

Configuration

Configurable from the settings panel or by editing ~/.dsh/dsh-lmstudio-vision.json:

{
  "baseUrl": "http://127.0.0.1:1234",
  "model": "",
  "prompt": "Describe this image in detail.",
  "temperature": 0.2,
  "maxTokens": 1024
}

Leave model empty to auto-select the most recently loaded model, or set an explicit model id to override it.

Repository layout

  • packages/dsh-lmstudio-vision/src/index.ts — host half: LM Studio engine, API routes,

agent tools, system-prompt announcement

  • packages/dsh-lmstudio-vision/src/client/ — browser half: the settings panel
  • packages/dsh-lmstudio-vision/cordis.patch.yml — bundle patch plugin row
  • shared/tsdown.client.ts — build preset (follows the dsh-web-ui clientBundle convention)

License

BSD-3-Clause

使用前核对

安装步骤、兼容版本与授权范围以原项目当前文档为准。Stars 和评分是快照中的导航信号。

安装与排错 · 项目问题反馈

同类项目