PerryLink/dsh-local-ai
DeepSeek Harness 的本地模型(Ollama)集成:发现、拉取、移除和检查本地模型,按任务类型或关键词将请求路由到本地模型并自动回退到云端,通过 `/ollama` 获取一次性状态概览。
Project Overview项目介绍
dsh-local-ai is a native plugin built exclusively for DeepSeek Harness, integrating locally hosted large language models running on Ollama into DSH workflows. To install it, users first install the dsh1024 toolchain globally via npm with npm i -g dsh1024, then run the dsh plugin --profile web add dsh-local-ai command to add it to their DSH profile. It provides core capabilities including model discovery, health checks, custom routing rules, and a one-shot /ollama command to get a full status overview of all installed and running local models. It also supports pulling new models, removing unused models, and checking model details such as parameter size and context length.
This plugin is designed for DSH users who want to work offline, handle sensitive data that cannot be sent to third-party cloud APIs, or reduce the cost of large language model inference. A common workflow starts after installation, when users add routing rules to their DSH profile configuration that match requests to specific local models based on task type or keywords. Once configured, DSH will automatically route matching requests to the appropriate local Ollama instance. If the local model fails to process the request for any reason, DSH will automatically fall back to a cloud-hosted DeepSeek model to complete the task.
dsh-local-ai requires Node.js version 22.19.0 or newer, or any version 24.0.0 and above, and a running local Ollama service to work correctly with DSH. Currently, the plugin only supports text-only models, though it does support full tool calls and tool result processing for text-based tasks. It is released under the permissive Apache 2.0 open source license, so it is free to use, modify, and distribute for both personal and commercial projects. It carries zero bundled dependencies beyond what is required to connect to Ollama’s HTTP API, and no model files are included in the plugin repository, with all models pulled directly from Ollama’s official registry.
这是一款专为 DeepSeek Harness 开发的原生插件,用于将通过 Ollama 运行的本地大语言模型集成到 DSH 工作流中。它支持发现、拉取、删除和检查本地模型,支持按任务类型或关键词路由请求,本地请求失败时可自动回退到云端模型,还能通过 /ollama 命令一键获取本地模型状态总览,可通过 DSH 插件命令直接从 npm 或 GitHub 安装。
这款插件适合需要离线处理敏感数据或降低大模型调用成本的 DSH 用户使用。典型工作流程为:安装插件后,在配置文件中设置路由规则,指定哪些任务由对应本地模型处理,启动 DSH 后即可自动按照规则将请求路由到本地 Ollama 服务。如果本地模型处理失败,会自动切换到云端 DeepSeek 模型继续处理。
该插件依赖 Node.js 版本 22.19.0 以上或 24.0.0 以上,需要本地运行 Ollama 服务,目前仅支持纯文本类型的模型路由,支持工具调用和工具结果返回。插件采用 Apache 2.0 开源许可证,无使用成本,不捆绑任何模型文件,所有模型均从 Ollama 官方仓库拉取。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-local-ai(PerryLink/dsh-local-ai)
仓库:https://github.com/PerryLink/dsh-local-ai
本站详情页:https://www.yhbd.top/plugins/perrylink-dsh-local-ai/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 17 · 最近提交 2026-09-24 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 17 stars - an early-stage project星标 17,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add dsh-local-ai
把 PerryLink/dsh-local-ai 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
🤖 dsh-local-ai
- 1024 store channel:
npm i -g dsh1024once, thendsh1024 plugin --profile web add dsh-local-ai(counts toward the deepseek1024.com install ranking).
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.
Official repository. This is the only official repository of dsh-local-ai, maintained by PerryLink. Same-name repositories under other accounts are not affiliated.
⭐ 如果它帮到了你
这个插件是 DSH 插件家族的一员(40+ 个,全部 Apache-2.0)。如果你在用,给个 star —— 它不会解锁任何功能,但会让下一个人在搜索里更容易找到它。
English: part of a 40+ plugin family for DeepSeek Harness. If it is useful, a star helps the next person find it — nothing is gated behind it.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
agentrq/agentrq
KelaoHu/dsh-lowtide
XDTrees/dsh-workbuddy-xdpool
FeatherHunter/dsh-prompt
dragonbaba/dsh-routing-suite
LouisHaoL/dsh-timer-agent