by liustack

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The most powerful DeepSeek Harness vision plugin on the web

by ysr666

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command

by tong-io

Modality-First GenAI Platform

by Anionex

[dsh] A More Powerful Vision Toolkit Designed for Pure-Text Models: One-Line Installation and Use, Paste Image for Direct Recognition, Multi-Image Q&A, Screenshot-to-Frontend-UI Restoration, and More｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts

by shanliuling

AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.

by Yuuyuko-uu

DSH Read-Aloud Bridge: Text in conversations is automatically handed off to the DeepSeek web version to be read aloud, with the voice coming from your own computer

by dickpy

DSH (DeepSeek Harness) Web GUI AI image generation plugin: text-to-image & image-to-image via OpenAI-compatible endpoints (gpt-image-2), with shared cross-device history.

by dundunhan

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / Video understanding plugin for text-only models (scene-aware frame sampling + VLM + optional ASR transcript)

by oil-oil

Near-native image understanding for DeepSeek Harness

by q253595422

DeepSeek Harness plugin: image + video generation studio with an infinite canvas. Fork of dickpy/dsh-imagegen with a complete video pipeline and clip stitching.

by sunxin-ai

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected

DSH-vison is a DeepSeek Harness plugin that adds image understanding for text-only models by converting images into descriptions from a configured vision-capable model.

by fengyungithub

AI Video Creation Workbench Based on DeepSeek Harness and ComfyUI

by kingcharleslzy-ai

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 verifie

by william-jin-cmu

dsh Plugin: Add Visual Capabilities to Plain-Text DeepSeek — The `view_image` Tool Bridges Any OpenAI-Compatible VLM (Defaults to Zhipu’s Free Tier; Verified with 4 Vendors and 10 Models)

by zmm863-commits

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight

by lizhiyao

OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.

by yanfei0725

Local Image Generation Plugin for DeepSeek Harness (Optimized Version): Uses local ComfyUI to invoke Qwen-Image 2.1 for image generation, with all traffic confined to 127.0.0.1. This version improves inference performance, NVIDIA/Intel/AMD GPU compatibility, and Windows/Linux compatibility. Original author @奇迹与你, optimized version @yanfei0725.

by xcw520

Local GPT-SoVITS TTS for DeepSeek Harness: reads assistant replies aloud with a draggable mascot and one-click installer.

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 huliux

Unofficial local meeting transcription for DeepSeek Harness on Apple Silicon macOS

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 weixinlll

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

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.