by huliux

Unofficial local meeting transcription for DeepSeek Harness on Apple Silicon macOS

by weixinlll

DSH Tavern Story Illustration Plugin, supporting ComfyUI and multiple online image generation services.

by Flyvhidbwo

DeepSeek Harness plugin: DeepSeek Pro brain + automatic image recognition. GUI-attached images are, by default, recognized natively via the official `deepseek-v4-flash-vision-exp`, then translated into text and handed to DeepSeek to answer (the pure-text V4-Pro can also view images); supports any OpenAI-compatible VLM such as Bailian/Zhipu/OpenRouter, and automatically detects a local Ollama instance when no key is provided; includes a single-question confirmation during installation.

by KaichenCurry

Visual execution layer for DeepSeek Harness—guided intent, infinite canvas, contextual image tools, and chat-native comments.

by poiuyjie

DSH plugin: Auto-convert images to text for pure-text LLMs (DeepSeek etc.) via any vision model. No need to switch your main model.

by Nicholas023

A large-image intelligent recognition plugin tailored for deepseek-v4-flash-vision-exp: full-image pre-check → local OCR + pixel grid (text) + ROI proportional tiling (longest side 800) → aggregation; retains the full-image 800x800 grid tiling mode. Does not count tokens or calculate costs. v0.4.2: picturereader adaptability optimization (coexistence division-of-labor guidance / visual endpoint reuse / OCR venv sharing).

by linenxi-ctrl

Add an external image recognition model to DeepSeek Harness: circular whale button, send image to trigger automatic image recognition and response, model's autonomous screenshot + image recognition tool, multi-protocol auto-adaptation, one-click installation for beginners (auto-downloads Node.js if not installed)

by jyh20030112

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

by ALittleLov

Let text models understand a song: a local music analysis plugin that splits audio into energy, tempo, tonality, and density — all without the audio ever leaving your machine.

by GooDAnDReaDY

Image generation & visual processing suite for DeepSeek Harness: pluggable providers (FAL, Replicate, OpenAI, ChatGPT Plus, Grok, ComfyUI, SeaDream, Gemini), tools (remove_background, upscale_image, v

by loudMore

DSH plugin: images and files delivered directly to text-only models — images keep the native attachment experience, while PDF/Office/archives/videos/audio are shown as attachment-bar blocks that automatically convert to workspace paths when you click send. Works with dsh-vision-toolkit so you can view images simply by pasting. A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep

by PerryLink

Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint)

by YuMS

Control DSH with just your voice

by abbccdd

Local IndexTTS 2.5 and GPT-SoVITS sentence-level speech synthesis and playback for DeepSeek Harness

by siegfly

Vision-language gateway plugin for DeepSeek Harness - paste an image, DeepSeek sees text

by azwosile

High-definition image recognition enhancement plugin exclusively for deepseek-v4-flash-vision-exp: relaxes DSH image limits + highres_read chunked image recognition tool.

by WongYuYe

Codex-style Appshots for DSH Desktop: capture the frontmost macOS window and attach it to the current chat.

by maxwell-feng

dsh plugin: OCR attached images locally with the built-in Windows OCR engine — text-only models can see, privacy-first

by Scorp1o117

Vision model for DeepSeek Harness | DeepSeek Harness External Vision Model Plugin

by FuzzySoul

A vision plugin tailored for DSH (DeepSeek Harness), now supporting agent-triggered image display / Vision plugin for DSH (DeepSeek Harness), supports Proactive Image Display.

by 54xkeee

Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory

by paicat1

Zero-dependency screen capture for DSH: Lightweight — zero deps, zero binaries; Stage & shoot — one-click full screen, window layout, hover-snap capture of occluded windows; Agent self-service — path-

by ns-zzj

Control a HarmonyOS Phone in the DeepSeek Harness Web Page and Have the AI Recognize the Content

by dttxorg

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.