DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
A

dsh-ai-model-builder

Ai Model Builder

AI Model Builder: Configure the learning rate, number of neurons, number of network layers, and dataset in the DSH sidebar to generate a PyTorch model architecture with one click, and open a new session with one click to have Agent automatically train the model according to the dataset.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:kalozamf233/dsh-ai-model-builder#7ccbe803651a28b544a954df6eeae801fc6fc2a6
READMECompatibilityVersions

Compatibility and provenance

Ai Model Builder is published as dsh-ai-model-builder and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
10/26/2026

Versions

0.1.0stable
10/26/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/26/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in developer-tools.

Web App@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)Sdk Minimal@deepseek-ai/dsh-sdk-minimalThe standalone minimal SDK profile bundle: JSON-RPC, one DeepSeek adapter, persistent shell, and JSONL sessionsSdk App@deepseek-ai/dsh-sdk-appThe dsh SDK profile bundle: stdio JSON-RPC serving and process lifecycle over dsh-baseExperimental Inspector@deepseek-ai/dsh-experimental-inspectorExperimental cross-realm CDP hub for Host debugging and Client Runtime inspection

README

dsh-ai-model-builder

DSH 左侧栏插件:AI 模型构建器。在图形界面里配置一个多层全连接神经网络, 一键生成 PyTorch 模型架构,并一键新开 DSH 会话让 Agent 按数据集自动训练该模型。

面板功能

在 DSH 左侧栏点击「AI 模型构建」图标打开配置面板:

区域字段说明
模型结构学习率优化器学习率
输入维度 / 输出维度数据维度与任务输出
每层神经元数量每个隐藏层的神经元数
神经网络层数隐藏层数量(1–128)
数据集与用途数据集路径(可选)CSV / 图片目录等;留空时训练会生成合成演示数据
模型主要用途写入 params.json,并作为训练指令的背景
保存路径模型文件保存路径「运行」在此写入 model.py
参数文件保存路径「运行」在此写入 params.json

三个按钮:

  1. 确认保存 —— 把当前配置持久化到 <DSH_HOME>/data/dsh-ai-model-builder/config.json;
  2. 运行(生成模型架构) —— 保存配置,并生成:
    • model.py:PyTorch 多层感知机(build_model() 读取 params.json 构建),
    • params.json:学习率 / 层数 / 神经元 / 维度 / 数据集 / 用途等超参数,
    • architecture.json:架构说明与参数量估算(与 model.py 同目录);
  3. 训练(新会话自动启动) —— 保存配置后,用 DSH 的 agents 服务新建一个会话 (工作目录 = 模型文件所在目录),并自动注入训练指令:Agent 会检查/安装依赖 (torch、numpy、pandas、scikit-learn)、编写 train.py、按数据集训练、把权重保存到 model_weights.pt,最后汇报训练指标。面板随后自动切到该会话,可实时观察执行过程。

HTTP 端点(Node half,仅同源可写)

  • GET /ai-model-builder/config —— 读取已保存配置
  • POST /ai-model-builder/config —— 保存配置(body: {config: {...}})
  • POST /ai-model-builder/generate —— 保存配置并生成模型架构文件
  • POST /ai-model-builder/train —— 保存配置、新建会话并注入训练指令,返回 {sessionId, cwd, ...}

安装(本地 link)

  1. 把本目录放到 %USERPROFILE%\.dsh\plugins\dsh-ai-model-builder;
  2. 编辑 %USERPROFILE%\.dsh\profiles\<profile>\package.json:
    • dependencies 增加 "dsh-ai-model-builder": "link:C:/Users/<你>/.dsh/plugins/dsh-ai-model-builder"(用绝对路径,正斜杠);
    • dsh.profile.bundles 追加 "dsh-ai-model-builder";
  3. 在 profile 目录执行 pnpm install;
  4. 重启 DeepSeek Harness。

卸载

从 profile package.json 移除依赖与 bundle 条目,pnpm install,重启 DSH; 再删除本插件目录与 <DSH_HOME>/data/dsh-ai-model-builder 即可。

实现说明

  • 零外部 npm 依赖:Node half 只 import node: 内置模块; installModelSelection / createUserMessage 是按宿主 @deepseek-ai/dsh-agent / @deepseek-ai/dsh-llm 公开语义内联的最小等价实现 (与官方 headless runner 使用同一调用契约)。
  • 客户端通过 main 槽位(key=ai-model-builder)+ sidebar.panellist 槽位 注册左侧栏入口;训练跳转使用 sessions.retain(sessionId, {source: "mainView"})
    • layout.selectPanel(null)。