Plugins
Browse, filter, and install DeepSeek-Harness plugins.
9 plugins found
dsh-qwen-studio
kingcharleslzy-ai/dsh-qwen-studio
Qwen Image 2.1 workspace for DSH: Apple Silicon MLX or your own NVIDIA server, native reference editing, LoRA, ControlNet, inpainting, shared presets, gallery and live agent progress. Includes verified updates and an agent setup guide.
rapid-mlx-dsh-provider
raullenchai/rapid-mlx-dsh-provider
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
dsh-matlab-runner
seally-web/dsh-matlab-runner
MATLAB in the sidebar: a VS Code-like .m editor backed by a persistent MATLAB session (first boot ~6–9 s, then 12–84 ms per run in the default session mode, where figures really open on the desktop), live workspace variables you can edit, .mlx preview, extra folder mounts, and an agent-facing matlab_run tool. Requires a local MATLAB installation.
seminar-copilot
wsqstar/seminar-copilot
DeepSeek Harness Web GUI plugin for Seminar Copilot: one-click local seminar recording, ASR backend settings (local MLX Whisper / Aliyun Bailian), auto-start of the dev stack.
dsh-podwave
watchcats211/dsh-podwave
Local-first podcast player and transcriber for DeepSeek Harness: plays audio files from your disk, transcribes with local ASR, shows bilingual subtitles and exports SRT or Markdown.
audio-transcript-skill
chengfeiai/audio-transcript-skill
Skill that transcribes local audio files into a timestamped transcript and an interactive two-column minutes page, with optional speaker separation. Transcription uses mlx-whisper in a Python 3.11 environment you set up yourself (the first run may download models); the renderer uses only the system python3. Given a public short-video share link, it can also drive a real browser through ego-browser and fetch the audio track with curl and ffmpeg, none of which ship with the package.
VoiceTranser
lumos-789/voicetranser
Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR 0.6B 4bit on MLX/Metal by default, SenseVoice and mlx-whisper fallbacks), zero external APIs, launchd self-healing service and an 8-point diagnose script. The bundled skill lets the agent install, configure (Karabiner hotkey wiring, launchd, engine switching) and troubleshoot the whole toolchain for you.
dsh-voice
scarf1985566475-cloud/dsh-voice
Local English-to-Chinese simultaneous interpretation: on-device Qwen3-ASR bilingual captions with automatic language detection, crash-safe meeting records with minutes, and Obsidian export.
dsh-llm-mlx
robbywang25/dsh-llm-mlx
Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.