Plugins

Capture a Windows window to a WSL file, whole or cropped to a region or to a named UI element.

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.

Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities, avatar cropping) plus a full Hana memory stack (rolling summaries, layered compilation, SQLite fact store, deep memory).

Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images

Turns an English paper PDF into a Chinese group-meeting .pptx whose figures and tables are the paper's own cropped pixels.

Real-time speech-to-text inside the DeepSeek Harness composer: a live transcript while you speak, inserted at the caret when you stop, with a microphone picker. Local sherpa-onnx inference, so audio never leaves the machine.

Annotates pages inside the built-in browser: click an element, write a comment, and send the batch to the conversation as one message, with a cropped screenshot per note where the element can be located.

LAN phone drop: a QR code on the computer screen opens a page on the phone, and photos or scanned documents land in a computer folder over the local network, with no tunnel and no cloud in between. Document mode binarizes locally in the browser (adaptive threshold plus speckle removal and edge crop) so an ordinary phone photo comes out as a black-and-white scan. Adds a "phone drop" entry at the foot of the DSH sidebar that opens the QR page, plus a phone_drop tool for the assistant; the same CLI also runs standalone without DSH.

Customize the Harness sidebar name and avatar with a local crop editor.

WeChat-style screenshot: freeze the desktop, drag a region or click a window, and the crop lands in the composer. A Windows-only fork of Durandalw/dsh-plugin-screenshot; do not install it alongside the upstream plugin.

Two-way voice for the DSH web app: dictate with the unified composer, hear replies with speaker buttons and auto-read, on any device. Needs DSH 0.1.7+, Node 22+, Python 3 with numpy and requests, a TTS model, and a microphone.

Native, instant region-screenshot button for the DeepSeek Harness composer: one click freezes the screen, a WeChat-style overlay (gray mask, green selection) appears, and the cropped PNG is inserted into the current draft. An optional eye toggle hides the whole DSH window before capturing, then restores it. No ms-screenclip, about 10 ms per drag frame, coexists with voice input. Windows 10/11 x64 only; the first capture compiles a helper with the built-in .NET Framework csc.exe.

System-audio visualizer for the turn navigator rail: the rail reacts in real time to whatever the default playback device is rendering, with four motion modes (spectrum, pulse, sway, travelling wave), a 16-band logarithmic spectrum from a 2048-point FFT on the host, and live sensitivity, strength, bass-punch and wave-speed controls. Audio is captured host-side through WASAPI loopback, so there is no permission prompt, no microphone and no screen capture. The browser half adds one attribute, one stylesheet, some CSS variables and a sidebar control row, and never patches the official component; switching it off removes the attribute, the stylesheet and the variables, returning the rail to its default styling. Windows only.

Dictate prompts into the DeepSeek Harness Web Client — a microphone in the composer, with swappable transcription: hosted Whisper API, self-hosted server, or a fully offline whisper.cpp binary.

DeepSeek Harness Web wallpaper plugin: upload and crop a local image as the web workspace desktop background, with a dedicated Settings section.