Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
45 Plugins gefunden
dsh-vision-plugin
bug-huntter/dsh-vision-plugin
Konfigurierbare Bilderkennung für textbasierte DSH-Modelle: Bildnachrichten werden zunächst von einem OpenAI-kompatiblen Vision-Modell transkribiert (Basis-URL, Modell-ID und API-Schlüssel in einem Einstellungsbereich festgelegt) und dann als Text an das Hauptmodell weitergegeben, während die Unterstützung für Bildeingaben angekündigt wird. Das API-Schlüssel-Authentifizierungsschema ist wählbar (OpenAI-, Anthropic-, Gemini- oder Azure-Stil-Anfrage-Header) und ein fehlender Schlüssel wird vor jedem Versand einer Anfrage gemeldet.
dsh-token-attention
young4ever33/dsh-token-attention
Token-Attention-Management-Panel für DeepSeek Harness: Token-Verbrauch und Kosten pro Aufgabe/Tag/Woche/Monat (Eingabe-Hit/Miss, Ausgabe, Reasoning), DeepSeek-Peak-/Off-Peak-Preise, Aufgabentyperkennung und Empfehlungen, wann die Sitzung gewechselt, eine Übergabe geschrieben oder der Kontext komprimiert werden sollte.
dsh-youreyes
54xkeee/dsh-youreyes
Vision-Toolkit für textonly DeepSeek: modellaufrufbares `vision`-Tool, Wrapper-Adapter für deepseek/opencode-go (v4 flash/pro), Antigravity-IDE-Kontingent (default, flash/pro) / jeden OpenAI-kompatiblen VLM / Gemini / lokale Ollama-Kanäle, Evidenzspeicher mit Kompaktierungs-Rehydration, Content-Hash-Cache und ein zweisprachiges Client-Panel.
dsh-wx-bridge
zhy5/dsh-wx-bridge
Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Access defaults to strict (only registered devices are served); the phone channel's permission preset is wide by design - see the README security section before sharing the bot.
dsh-live-voice
victorwads/dsh-live-voice
Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.
context-m
ssmurfgg04-gif/context-m
DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.
dsh-johari-cognition-quadrant-dialog-composer
cyrus123456/dsh-johari-cognition-quadrant-dialog-composer
Johari cognition-quadrant dialog prompt composer — adds a button above the composer that opens a 2×2 quadrant panel (known/unknown × AI-known/AI-unknown) to groom conversation context into a structured prompt written back into the draft.
aura-vision
ck-epsilon/aura-vision
Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.
dsh-speech-input
liznee/dsh-speech-input
A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.
dsh-client-vision (tool-vision)
ankye/dsh-client-vision
Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.
dsh-screen-automation
xiaozs-com/dsh-screen-automation
DeepSeek Harness (dsh) plugin that bridges the local 'Screen Automation Helper' desktop platform (Windows/macOS) into the Agent tool system. Exposes status, capabilities, workflow list/run/stop, run management, screen capture, local recognition primitives
dsh-deepseek-vision
cheng-cheng9669/dsh-deepseek-vision
Nutzt den eingebauten Vision-Modus von DeepSeek web für reine Textmodelle: Das Tool deepseek_vision steuert die lokale Browser-Automatisierung deepseek-vision-cli (Helfer für manuelle Anmeldung, deep-think aktiviert, automatisches Schließen des Browsers) und liefert Bildbeschreibungen als Text.
vision-exp-tile
nicholaskin/vision-exp-tile
Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.
dsh-voice-input-en
mohith-das/dsh-voice-input-en
Minimal English-only voice input for the DeepSeek Harness Web UI: a mic button in the composer that transcribes speech into the draft via the browser's native SpeechRecognition API. No dependencies, no subprocess, no network calls beyond whatever the brow
dsh-vision-bridge
alaxrpg/dsh-vision-bridge
Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.
axiom-dre-dsh
listenj/axiom-dre-dsh
Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.
dsh-dictate
franksong2702/dsh-dictate
Browser Web Speech dictation for the Composer: recognition needs no dedicated ASR server, key, or model download; reuses Session text and a configured DSH model for contextual phrase hints and optional transcript polishing.
dsh-mingmu
lab-sku/dsh-mingmu
明眸 VisionBridge - Selbstentwickelte visuelle Brücke: Wenn ein blindes Modell Bilder empfängt, wird automatisch ein visuelles Modell zur Erkennung aufgerufen und der erkannte Text an das Hauptmodell zurückgegeben; nahtlos, konfigurierbar, verlustfrei bei Upgrades.
dsh-vision-ocr
timeflies-qyh/dsh-vision-ocr
DeepSeek Harness OCR plugin — offline image text recognition powered by PaddleOCR-json (primary) and RapidOCR-json (fallback). 让 DeepSeek Harness 直接识别图片中的文字,无需视觉模型、完全本地离线运行。
dsh-vision-solution
br1nosense/dsh-vision-solution
Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.
dsh-cognition
scd13150/dsh-cognition
Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).