DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
49 个项目，匹配「vision」
william-jin-cmu
dsh 插件：给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM（默认智谱免费档，实测 4 厂商 10 模型）
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.
sanshanya
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (wire spellings) + request modalities (vision) for OpenAI-compatible providers. Settings section, zero runtime harness deps, no YAML.
Agents365-ai
Image understanding for text-only models via OpenRouter free vision models
Scorp1o117
Vision model for DeepSeek Harness | DeepSeek Harness 外置视觉模型插件
Einskyle
DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)
ch1bug
Xiaomi MiMo search + multimodal tools for DeepSeek Harness agents: mimo_search/vision/audio/video/asr/tts
woyeshishen
该仓库暂未提供项目说明。
ximengxiaolan
Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????
zcXie777
Give DeepSeek Harness agents native image reading: a read_image tool backed by any OpenAI-compatible vision endpoint.
Elohia
Synesthesia Encoder (通感编码器) — give any text-only LLM (DeepSeek, etc.) the ability to see images via structured spatial text encoding. A Pi agent extension.
Flora233333
DSH 极简模式视觉辅助：保持灰测体验所需的首轮干净上下文，同时通过隐藏上下文和按需 Bash 工作流提供视觉分析 | Vision assistance for DSH minimal mode: preserve the clean first-turn context behind the gray-test DeepSeek experience while adding on-demand visual analysis through a hidden-context Bash workflow.
MoYuSOwO
Manifest-driven multi-source asset manager for DeepSeek Harness profiles (npm/github/release/skill/preset/local) — sync, plan, conflict detection, transactional rollback.
moon09300731
DeepSeek Harness 视觉能力全家桶：vision_understand 工具 + 粘贴/拖拽/按钮三入口识图
sjscy05
该仓库暂未提供项目说明。
xiaoshihou514
DeepSeek Harness: vision
yepyeel
提供dsh中deepseek v4等无法识图的模型一双眼睛
Elohia
该仓库暂未提供项目说明。
JarszmLovesAI
DeepSeek Harness(DSH) web plugin: paste files into the composer, inbox storage, thumbnails. Text via read_inbox; image understanding needs your vision skill (bundled image-reader + ARK_API_KEY).
LuRia-yzk
image_recognize tool for DSH: give text-only models vision via qwen3-vl-flash
MicroHEROX
KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.
Xin-Zhang-IceMan
DeepSeek Harness 视觉插件：让纯文本模型拥有视觉能力 / Vision plugin for DSH: vision_analyze tool + automatic image transcription for text-only models.
YZz-S
DeepSeek Harness (dsh) vision plugin — a fork of ModLens adding multi-engine image reading (Gemini, Volcengine Ark/Doubao, Claude) with per-call engine selection.
cking000bigdemon
Eight DeepSeek Harness plugins: persona, language guard, per-request vision fallback, python/windows write guards, cross-agent memory, image generation, and skill shell injection.