ch1bug/dsh-mimo-agent-tools 预览 preview

ch1bug/dsh-mimo-agent-tools

Plugin插件 Native原生 ⭐ 7 MIT Vision & Media视觉与多媒体

小米MiMo搜索+多模态工具,用于DeepSeek Harness代理:mimo_search/vision/audio/video/asr/tts

Project Overview项目介绍

This is a native Cordis plugin built exclusively for DeepSeek Harness (DSH). It wraps the Xiaomi MiMo API into a set of callable agent tools that DSH agents can invoke directly during conversation. To install the plugin, users run the official DSH plugin command to add the bundle from GitHub, then manually copy the included Python driver to the default path at ~/.local/lib/mimo-agent-tools/driver. The driver handles all file reading, payload assembly and HTTP requests to avoid large base64 payload truncation that can happen when passing data through DSH's shell seam. After installation, restart DSH to automatically mount all tools.

The plugin includes 9 distinct MiMo-powered tools covering search, reasoning, structured output, vision, audio, video, ASR, TTS, and voice cloning. The XIAOMI_API_KEY required to access MiMo is pulled first from DSH's built-in credentials service, then falls back to environment variables if it is not found there. You need a valid MiMo API key from https://mimo.mi.com, and the connected-search plugin must be enabled in your MiMo console to use the web search tool. Your DSH host needs the shell and sandboxPolicy services enabled, and your system also needs a working Python 3 installation to run the driver that handles API requests.

The plugin comes with test suites for both the Python driver and the tool registration surface. The plugin registers an extra audio-tools skill that guides DSH on when to use each audio-related tool. You can run 12 test cases for the driver's request-body assembly with python3 tests/test_driver.py, and 9 test cases for the tool surface with node --test tests/tools.test.mjs. All tools are lightweight pure API calls to MiMo's OpenAI-compatible endpoint, and the plugin is released under the open source MIT license. All API access costs are billed by Xiaomi according to MiMo's official pricing, not by the plugin itself.

这是一个专为DeepSeek Harness(DSH)开发的原生Cordis插件,它将小米MiMo API封装成可供DSH代理调用的工具集合,提供网络搜索、深度推理、结构化JSON输出、多模态理解、语音转文字、文字转语音和声音克隆等多种能力,所有能力都调用MiMo官方开放API实现,插件本身不包含大模型权重。

用户只需要在DSH的凭证服务中配置自己的小米MiMo API密钥,就可以在代理对话中直接调用所有工具,插件会自动按照API规范处理请求和响应组装,还额外注册了audio-tools技能来引导代理何时使用音频相关工具。该插件适合需要扩展DSH能力、接入MiMo多模态与工具能力的DSH用户使用。

插件要求宿主环境安装Python 3,拥有可用的DSH shell和sandboxPolicy服务,还需要用户启用MiMo控制台的连接搜索插件才能使用网络搜索工具。安装按照标准DSH插件流程操作,需要额外复制Python驱动到指定路径,插件采用MIT许可协议,所有API调用费用按照MiMo官方定价收取。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 7 stars - very few users, little community feedback星标只有 7,几乎没人在用,遇到问题缺少社区反馈
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 github:ch1bug/dsh-mimo-agent-tools

把 ch1bug/dsh-mimo-agent-tools 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

mimo-agent-tools

DSH (DeepSeek Harness) Cordis plugin that turns the Xiaomi MiMo API into model tools for an agent: web search, image/audio/video understanding, speech-to-text, and text-to-speech — plus, since the single-repo merge (docs/adr/0001, absorbing dsh-voice-mimo), the voice UI: a 🔊 read-aloud button on every assistant reply, in-conversation speech strips for stored mimo_tts output (play / download / regenerate), and a configurable voice map in the Plugins settings tab.

Backed by the OpenAI-compatible endpoint https://api.xiaomimimo.com/v1.

Tools

Tool Model Purpose
mimo_search mimo-v2.5-pro Web search via the native web_search tool, returns answer + cited sources (incl. site_name/logo_url); optional force_search, user_location
mimo_think mimo-v2.5-pro / mimo-v2.5 Deep thinking — full reasoning chain (reasoning_content) + final answer
mimo_json mimo-v2.5-pro / mimo-v2.5 Structured JSON output via response_format: json_object
mimo_vision mimo-v2.5 Image understanding — local files (auto base64) or public URLs, multi-image
mimo_audio mimo-v2.6 Audio understanding / transcription (wav/mp3/flac/ogg/m4a) — local file or public URL
mimo_video mimo-v2.5 Video understanding (mp4/webm/mov) — local file or public URL; optional fps / media_resolution
mimo_asr mimo-v2.5-asr Speech-to-text with optional language hint — local file or public URL
mimo_tts mimo-v2.5-tts / -voicedesign Text-to-speech to a .wav/.mp3 file — preset voices or free-form voice design; optional style (speaking tone) and format (wav/mp3). With store: true the audio lands in the plugin audio store and a playable strip (play/download/regenerate) renders in the conversation (voice/style default to the plugin Config)
mimo_voiceclone mimo-v2.5-tts-voiceclone Voice cloning — reference clip + text → speech in that voice; optional format (wav/mp3)

audio-tools skill

The plugin registers an audio-tools skill that guides when to use the four audio tools (mimo_asr, mimo_tts, mimo_voiceclone, mimo_audio). The tools themselves are always registered — they are lightweight pure-API calls — so the skill only teaches usage, it does not gate the tools.

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 →

← 上一个 Prev dsh-finance 下一个 Next dsh-harness-enterprise →