Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
57 plugins encontrados
dsh-liquid-glass
shuoweifu/dsh-liquid-glass
A high-performance WebGL liquid glass plugin made for DeepSeek Harness. It features domain distortion, chromatic refraction, and a 5-layer GPU overheat protection system.
ai-voice
root-7-khx/ai-voice
A local AI voice studio for DeepSeek Harness with nine local TTS engines for voice design, voice cloning, emotional performance, a reference-audio library and audio export. It only registers /ai-voice/api routes; the UI lives in the companion-memory plugin's integrations page, and every engine needs its own Python virtualenv and downloaded model weights, which are not bundled.
dsh-session-vacuum
mili1360/dsh-session-vacuum
Deletes the write-only streaming fragment rows from session logs on disk so a long session loads into fewer objects; the pruned log is checked against the loader contract before the file is replaced, and the previous file is kept as .orig.
dsh-lag-guard
456erddgr/dsh-lag-guard
Limita a 120 mensajes la solicitud de historial y sustituye por una matriz vacía los esquemas request/header de herramientas de más de 200 000 caracteres antes del renderizado de React, para abrir sesiones largas sin congelar la transcripción.
dsh-performance
wanyi424/dsh-performance
¿Ligero y eficiente? Consulta CPU, memoria y bloqueos de UI de DSH, desglosados por plugin, terminal y servidor MCP, vinculados con los tiempos de bloqueo; copia un informe de diagnóstico. Solo Windows x64.
dsh-lucky-block
lyhtakeashot/dsh-lucky-block
Añade un botón lucky-block arrastrable a la web UI de DeepSeek Harness. Clic simple: actuaciones breves sin coste (popups, pantalla azul falsa, fortuna diaria, trivia, chistes malos, música y efectos visuales). Mantener 1,4 s mina el bloque e inicia una sesión para crear un paper aleatorio, leer noticias, inventar o contar una historia corta. Añade una opción lucky block a preguntas de elección múltiple del modelo y sortea; «rollback» revierte. Aspecto y pesos ajustables.
dsh-speed-gauge
moreanp2003/dsh-speed-gauge
Indicador en tiempo real de velocidad de generación para DSH: dial semicircular y curva de tendencia fluida, con 50 muestras tok/s por segundo para medir con más precisión.
dsh-cpp-optimization
chthollyfan/dsh-cpp-optimization
Habilidad de auditoría C++: detecta el estándar C++ real del proyecto antes de recomendar. Revisa RAII y propiedad, semántica de movimiento, seguridad de excepciones, rendimiento y memoria, contenedores y algoritmos, concurrencia, plantillas y compilación, límites del estándar y seguridad de tipos, ABI e interfaces. Cada hallazgo incluye punto de control, motivo, ejemplo de malo a bueno y estándar mínimo.
wincu
dxxcao/wincu
Control del equipo Windows para DeepSeek Harness: backend UIA persistente de PowerShell mediante 16 entradas MCP agrupadas (read/click/type/observe/verify). Capa de políticas reforzada (líneas rojas, aprobaciones, vinculación a la observación y controles de propiedad del punto y foco) y mejoras de rendimiento (precarga, caché y prueba de estabilidad por hash de píxeles). Fork de dsh-computer-use-win.
dsh-wsl-perf
173787247/dsh-wsl-perf
Rendimiento del host Windows desde WSL: CPU, memoria, disco y procesos principales.
dsh-pianist
laplace-bit/dsh-pianist
Plugin de interpretación de piano: pide al agente que toque una pieza y la reproduce con muestras reales de Salamander Grand en un piano de cola Canvas2D, un escenario inmersivo y un teclado interactivo de 88 teclas.
dsh-k6
wode25500/dsh-k6
Pruebas de carga con Grafana k6: primero una smoke test, luego ejecuta scripts y lee los percentiles desde el resumen JSON.
dsh-compressor
lifeodyssey/dsh-compressor
Un port ligero de Headroom: comprime la salida de herramientas y recorta hasta un 20% del contexto sin afectar la caché de contexto del modelo ni el rendimiento del agente.
dsh-plugin-code-review
yytbit/dsh-plugin-code-review
Skill de revisión de código estructurada para DeepSeek Harness: errores, seguridad, rendimiento, estilo
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-tts-voice
pandaman0759/dsh-tts-voice
End-of-turn voice summary: the model calls voice_say once before finishing a reply so the conclusion is spoken through Breeze TTS, with Chinese bracket audio tags (laughter, sighs, pauses) and optional performance instructions. Audio is synthesized host-side and played from browser memory without ever touching disk; the character limit is a writing target for the model, not a cut-off, so long lines still play in full. The API key stays in the credential store, and an optional daily Breeze check-in is included. Needs a Breeze API key and sends the spoken text to the Breeze service; its HTTP routes (including the settings route that stores the key) have no DSH access check.
dsh-hr-workbench
xscanzm/dsh-hr-workbench
Runs a complete HR workbench inside DSH — a 3D office, recruiting pipeline (resume, interview, written test, score), employee roster, files, attendance, performance, training and analytics — with the site’s AI assistant answering through the model DSH already runs.
dsh-model-radar
chip-g0202/dsh-model-radar
Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.
dsh-aot-runner (plugin)
boyingliu01/dsh-aot-runner
Drop-in replacement for the Node.js subprocess runner with a NativeAOT binary, cutting per-spawn overhead by 59-67% (p50 156ms to 63ms) while staying byte-identical on 28 A/B cases; Windows x64 only, requires a one-line upstream patch, and ships disabled until you set enabled: true.
dsh-longsession
asots/dsh-longsession
Adds a reversible “Collapse history” toggle to the session header with a light/dark status dot: it unloads the history already rendered by the page and keeps the latest two turns, then shows “History collapsed”; clicking again restores the saved window. A manual restore keeps auto-collapse off for the rest of that session; thresholds and request caps live on Settings → Long session.
dsh-agent-speedup
hj1h/dsh-agent-speedup
Tool-execution efficiency suite for DeepSeek Harness: read-only result cache, speculative prefetch, and concurrent readonly shell commands. Honest scope: helps when tools are slow and calls repeat; model latency dominates otherwise.
dsh-token-rmb
liuyun2025/dsh-token-rmb
Appends the current turn's estimated token cost in CNY to the assistant action row, right after the usage/time indicator. Prices come from a built-in DeepSeek peak/off-peak CNY table (Beijing time, Monday-Friday 9:00-12:00 and 14:00-18:00) and can be overridden from the profile's cordis.patch.yml; a model without a configured price shows a dash instead of a made-up amount. Follows the shipped Performance & usage - Compact setting and hides together with the usage pill. Token cost only, per turn only.
dsh-windows-monitor
joyboy-yy/dsh-windows-monitor
Superposición de monitor del sistema para DeepSeek Harness: una cápsula compacta en una esquina muestra CPU y memoria; al expandirla, ofrece actividad y rendimiento de disco, capacidad por volumen, red, tiempo activo y batería. Solo Windows.
dsh-perf-hud
yanzhaohui1999/dsh-perf-hud
HUD de rendimiento client-side y grabador continuo para DeepSeek Harness: FPS/peor frame, atribución de tareas largas en cuatro vías (React fiber/subtree/DOM writes/scheduler), callback rate/tiempo sync por plugin, crecimiento y escritores DOM, JS heap, event loop host y RTT. El grabador night-watch conserva los peores parones y exporta incident packs reproducibles.