返回目錄

dsh-mimo-agent-tools

精選清單收錄維護狀態: 活躍

ch1bug/dsh-mimo-agent-tools

小米 MiMo 工具外掛,整合搜尋、視覺、語音、影片與 ASR/TTS 等多模態能力。

前往 GitHub
$ dsh plugin add dsh-mimo-agent-tools

安裝

dsh 沒有統一的安裝指令 —— 把該外掛 README 中的設定行加入你的 profile / patch 設定,然後重啟即可。

查看安裝教學

7

星數

3

Fork

JavaScript

語言

MIT

授權條款

2026-08-14

建立於

2026-10-03

最近推送

README

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.

Requirements

  • A MiMo API key — the web_search tool requires the connected-search plugin enabled in the MiMo console.
  • python3 on the host (used by driver/mimo_driver.py).
  • DSH host with the shell and sandboxPolicy services.

Configuration

The API key is resolved at tool-call time from the DSH credentials service first (key name XIAOMI_API_KEY — the web Models page writes keys there), falling back to the environment. Nothing is hardcoded:

Source Key Priority
DSH credentials service (~/.dsh/.credentials.yaml, web Models page) XIAOMI_API_KEY 1
Environment XIAOMI_API_KEY or MIMO_API_KEY 2

Other options (environment, read at apply time):

Env var Purpose Default
MIMO_DRIVER path to driver/mimo_driver.py ~/.local/lib/mimo-agent-tools/driver/mimo_driver.py
MIMO_TMP temp dir for spec/response files /tmp

Install the driver at the default path (or point MIMO_DRIVER at it):

mkdir -p ~/.local/lib/mimo-agent-tools/driver
cp driver/mimo_driver.py ~/.local/lib/mimo-agent-tools/driver/

Why a python driver?

Multimodal payloads are multi-megabyte base64 strings. Agent shells commonly cap captured stdout (DSH's bash seam caps at 64KB), which silently truncates large payloads. The driver therefore does ALL file reading, body assembly and HTTP POSTing inside one python3 process, using spec/response files on disk — nothing large ever crosses the shell.

Install (DSH bundle)

Standard DSH bundle — install with the official plugin command (auto-inits the profile, pnpm-installs, and appends the bundle layer per dsh.bundle.patch):

# From a local checkout, or via git/npm:
dsh plugin --profile web add /path/to/dsh-mimo-agent-tools
# or: dsh plugin --profile web add github:you/dsh-mimo-agent-tools

# Install the python driver to the default path (MIMO_DRIVER points at it):
mkdir -p ~/.local/lib/mimo-agent-tools/driver
cp driver/mimo_driver.py ~/.local/lib/mimo-agent-tools/driver/

# Restart dsh web; the tools mount automatically.

Dependencies are declared as peerDependencies (ecosystem convention — @deepseek-ai/dsh-tools is already loaded in the DSH process, so nothing is duplicated). dsh plugin add installs the bundle into the profile's node_modules where peer deps resolve against the running harness.

Notes on the MiMo API (from the official docs)

在 GitHub 閱讀完整 README →

DSH Plugins 是獨立的 DeepSeek Harness 外掛目錄,與 DeepSeek 官方無關,也不代表官方背書。第三方外掛未經安全稽核,安裝前請審查原始碼。

每週取得最新的 DeepSeek Harness 外掛,絕不濫發。