Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
66 plugins encontrados
dsh-fine-tune
songrui111/dsh-fine-tune
Ajuste fino local LoRA y QLoRA en un panel: importa JSONL, muestra una estimación de VRAM antes de iniciar el entrenamiento, evalúa y exporta un adaptador. Configura un entorno virtual de Python con un clic, pero debes proporcionar Python 3.10+ y una GPU NVIDIA de 6 GB o más. Verificado de extremo a extremo en Windows 11 con RTX 3060 de 6 GB; el instalador rechaza equipos que no sean Windows, por lo que Linux, macOS y otras GPU no están admitidos por ahora.
dsh-gptsovits-tts
nuoyi207/dsh-gptsovits-tts
Texto a voz local GPT-SoVITS para DSH: lee las respuestas en voz alta, permite cambiar de voz desde la barra lateral derecha y entrenar una nueva con una muestra de audio. La primera ejecución descarga un motor de 11,4 GB y requiere una GPU NVIDIA CUDA.
dsh-dock-vitals
mm998li/dsh-dock-vitals
Lectura en vivo de CPU, memoria y GPU en la barra de estado del composer de DeepSeek Harness: insignia clicable con panel de detalles, conmutadores por métrica y tres velocidades de actualización.
dsh-whale-decor
luo0712yan0219-blip/dsh-whale-decor
Skin azul ballena de aguas profundas para DSH Web GUI: 14 tokens de tema en claro y oscuro, cinco posiciones de la sirvienta con cola de ballena, tarjeta de reloj y clima, y panel plegable de CPU/memoria/GPU/temperaturas por unidad mediante HWiNFO. No incluye imagen de fondo; aporta la tuya. Código y arte del personaje bajo MIT.
dsh-system-monitor
weihaobin0818-lgtm/dsh-system-monitor
Monitor de hardware en tiempo real en la barra lateral DSH: CPU/GPU/memoria/disco en una sola vista, actualización por segundo y acceso desde cada lectura a la aplicación correspondiente. Predice capacidad y agotamiento de memoria, con alertas por umbral y exportación NDJSON. Node puro, cero dependencias de runtime; funcionalidad completa solo en Windows.
dsh-gpu-monitor-nvml
janpauldahlke/dsh-gpu-monitor-nvml
Monitor en vivo de GPU NVIDIA en la barra lateral derecha web de DeepSeek Harness (dsh). En Linux prioriza NVML y recurre a nvidia-smi si es necesario. Solo NVIDIA; no AMD, Intel ni macOS. Muestra uso/VRAM/energía/temperatura de varias GPU, procesos y minigráficas. Instalable como dsh.bundle.
dsh-vitals
joblessjoe/dsh-vitals
Pestaña de monitorización en vivo estilo btop para la GUI web de DeepSeek Harness: CPU, memoria, temperatura y GPU.
dsh-wsl-docker
173787247/dsh-wsl-docker
Informa sobre Docker CLI, contexto y acceso al daemon en WSL, además del estado de `:8000 /v1/models` de vLLM y sugerencias sobre el runtime de GPU.
dsh-gpu-pulse
zhubaohi/dsh-gpu-pulse
Monitor GPU flotante para la Web UI de DSH: franja compacta y arrastrable con nombre exacto, uso, VRAM, temperatura y consumo de cada GPU discreta según nvidia-smi. Permanece visible sobre paneles laterales y tarjetas; muestra los procesos con mayor VRAM si el controlador los informa. Sin controlador NVIDIA, se reduce a una píldora n/a.
dsh-wsl-gpu
173787247/dsh-wsl-gpu
Comprueba nvidia-smi y la visibilidad de la GPU dentro de WSL.
dsh-gpu
zytsyj/dsh-gpu
Capa de ejecución consciente de la GPU para DeepSeek Harness: herramientas gpu_status / gpu_exec / gpu_run_bg, inyección de contexto de GPU por paso, y selección automática de tarjeta mediante CUDA_VISIBLE_DEVICES
dsh-plugin-device-info
lsz-asd/dsh-plugin-device-info
Herramientas de solo lectura de información de dispositivos Windows: una herramienta de agente por cada categoría de dispositivo Win32 (hora, sistema, cpu, memoria, disco, gpu, red, batería, procesos, usb, audio, impresoras) vía colectores WMI/CIM y del módulo os de Node.
dsh-ai-voice-cover
vamyane/dsh-ai-voice-cover
AI voice cover for DeepSeek Harness: give any song plus about 10 seconds of reference audio and get a cover sung in that voice — dry vocal and mixed final, with the melody aligned to the original because only timbre is swapped. Supports zero-shot covers and archived voice libraries, automatic semi-tone shift synced with the accompaniment, an isolated Python venv, and runs on GPU or CPU.
dsh-theme-obsidian
inh-ui/dsh-theme-obsidian
Desktop-style client theme for DeepSeek Harness: translucent slate sidebar, #151517 main canvas and #2c2c2e composer dock, four palette presets (obsidian-origin, glacier-midnight, titanium-noir, sonoma-frost), a settings panel for blur, sidebar opacity, ambient glow and content radius, and three GPU performance tiers (ultra, balanced, eco).
dsh-fastfetch
niesc-f/dsh-fastfetch
A fastfetch-style system and DSH panel: one slash command (/fastfetch or /ff) and one simple agent tool render OS, kernel, host, CPU, GPU, memory, every disk and local IP address, plus DSH version, model, session mode, plugin and skill counts into a colored terminal card, with a settings page that edits every field.
dsh-status-monitor
philomelcc/dsh-status-monitor
Disk, CPU/memory/GPU, listening-port and token-usage cards with a full-page zoom; runs as a workbench module or standalone. The port card works on Windows only and the GPU card needs nvidia-smi.
dsh-systeminfo
tntfireage/dsh-systeminfo
Adds a live system dashboard with per-core CPU, memory, GPU, processes, disk usage and a STOP action for ending processes, plus per-process energy on macOS, exposed as a browser page, a GUI panel and a `systemInfo` service other plugins can inject. macOS is the main platform and Linux is best-effort. The dashboard page and its read-only JSON (process list with users, disks, logged-in users) are served with no login check; publicDashboard: false only refuses non-loopback peers. STOP accepts loopback requests only and sends SIGTERM, then SIGKILL after a grace period, to any process your account may signal except pid 1, the DSH host and its parent.
dsh-local-monitor
astelirons-ai/dsh-local-monitor
Floating, draggable sensor dashboard for the Harness Web UI on Windows: GPU-Z GPU temperature, clock and dedicated VRAM on the left, CPU temperature/clock and system memory on the right.
dsh-strata-monitor
arustama/dsh-strata-monitor
Live monitor of a local Strata model server inside the DeepSeek Harness GUI: state, token rate, VRAM, GPU and CPU temperatures, and the last request, next to the message composer.
dsh-sysload
k623615746/dsh-sysload
CPU, GPU and memory load in the DeepSeek Harness Session header: three compact cells with a percentage and a 2 px bar, coloured at 75 % and 90 %; CPU from os.cpus() deltas, GPU from nvidia-smi (Windows counter fallback).
dsh-elysia-memory
1148462398-hub/dsh-elysia-memory
Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment. On by default: after every reply a bubble with an avatar pops up (voice.bubble: false turns it off), and unless the agent already spoke itself it costs one extra small-model request. Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).
dsh-local-llm
verson00/dsh-local-llm
Runs the local llama.cpp Qwen3.5-4B from a Settings page — Windows only, NVIDIA GPU (8 GB VRAM handles the 4B Q4) — with start, stop and restart, launch parameters, deployment paths with a presence check, provider-route and compaction-policy sync in the profile patch, a loopback request-capture proxy, and a local_worker tool that hands translation, OCR and video-frame chores to the local model by file path. Needs llama-server.exe (verified on b12069) and Qwen3.5-4B GGUF + mmproj files on disk; video frames also need ffmpeg.
open-sea-skin
beckchiang/open-sea-skin
Realtime ocean skin for DeepSeek Harness, rebuilt from d-dev0101/open-sea-skin 1.2.7 under MIT. Wave height follows the live session load, the sky comes from a local NOAA ephemeris, the star field is a real 2851-star HYG subset with 88 constellations, one boat per running subagent, plus a searchable 11-group settings panel and three quality tiers. Published to npm as "open-sea-skin-dsh"; it keeps the upstream bundle id, so uninstall d-dev0101/open-sea-skin first — the two cannot be installed side by side.
dsh-resource-monitor
sad-jack/dsh-resource-monitor
Compact macOS strip above the composer showing CPU, GPU, RAM, swap, memory pressure and local Ollama model ON/OFF status. Tested on Harness 0.2.1-rc.5.