文件与数据
技能
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). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
agent-skills
claude-code
claude-skills
codex
文件与数据
插件
一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover/search/quota) for DeepSeek Harness (DSH)
agent-tool
ai-agent
cordis
deepseek-harness
文件与数据
插件
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.
ai-agent
ai-evaluation
auditable-ai
browser-automation
文件与数据
插件
Model-agnostic Computer Use for DeepSeek Harness: isolated browser, Windows native helper, third-party vision perception, and a Chrome Cookie Bridge.
computer-use
computer-use-agent
dsh-plugin
playwright
文件与数据
插件
On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
agent
deepseek
deepseek-harness
dsh
文件与数据
插件
DSH 插件：让纯文本模型也能看图。Web 端直接粘贴图片即可发送，无需指定图片路径；模型自主调用视觉技能查看，多模态模型原生直通，零skill绑定。
dsh-plugin
dsh-plugin-market
dsh-plugin-verify
dsh-plugins
文件与数据
插件
DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.
deepseek
deepseek-ai
deepseek-harness
deepseek-harness-desktop
文件与数据
插件
Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.
deepseek
deepseek-harness
dsh-plugin
image-to-text
文件与数据
插件
【已停止维护】DeepSeek Harness 视觉桥接插件：新版 Harness 已原生支持图片识别，请使用原生能力，本仓库仅作历史参考。
agent
ai
attachment
chat
文件与数据
插件
Local OCR, color-statistics, pixel-scan, and metadata bridge for text-only DeepSeek Harness models; no external vision API.
deepseek-harness
dsh-plugin
ocr
vision
文件与数据
插件
Universal vision bridge for DeepSeek Harness: attachments with native models, 40+ tools, PDF/OCR/diagrams.
deepseek-harness
dsh
dsh-plugin
multimodal
文件与数据
插件
DeepSeek Harness vision plugin: analyze_image (structured OCR evidence) + capture_image (USB camera visual loop). 摄像头视觉闭环 + 结构化证据，支持 Ollama / DeepSeek / Xiaomi 三后端。
camera
deepseek-harness
dsh-plugin
image-to-text
文件与数据
插件
DeepSeek Harness plugin for third-party OpenAI Responses and native Gemini APIs, with custom providers, model discovery, and hosted web search.
deepseek-harness
dsh-plugin
gemini
llm
文件与数据
插件
DSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.
deepseek-harness
dsh-plugin
llm
multimodal
文件与数据
插件
DeepSeek Harness 视觉补全：孪生路由解锁原生图片体验，本地 Ollama 请求层看图，零云端依赖。Vision twin + local agentic vision tools for DeepSeek Harness.
deepseek-harness
dsh-plugin
ollama
vision
文件与数据
插件
DSH 视觉桥接插件：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）
deepseek-harness
dsh
dsh-plugin
vision
文件与数据
插件
DeepSeek Harness (DSH) native plugin — describe_image tool: a vision bridge (image → mimo-v2.5 → text description) over the ctx.fs / ctx.credentials seams
agent
cordis
deepseek-harness
dsh
文件与数据
插件
Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.
deepseek-harness
dsh
dsh-plugin
multimodal
文件与数据
插件
明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别
ai-plugin
deepseek
deepseek-harness
dsh-plugin
文件与数据
渠道适配
Image message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen script
bridge
cordis
deepseek
deepseek-harness
