插件目录
完整目录用于发现；各质量维度分别展示，自动化分析不代表插件功能已经完整验证。插件管理器会在本地继续检查候选源。
找到 1065 个来源候选（配置来源覆盖 15812 / 15812） · 快照：2026-09-19搜索排序：文本相关性优先 + 有界质量证据修正
dsh-ext-vision-proxyjin123-alpha/dsh-ext-vision-proxy目录 已分析External vision proxy extension for DeepSeek Harness, enabling text-only models to analyze and understand images via OpenAI-compatible vision APIs.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-helperYuuz12/dsh-vision-helper目录 已分析DeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-visionxiaoshihou514/dsh-vision目录 已分析极简的原生视觉能力增强，支持免费的智谱模型或本地千问视觉模型。视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析text-llm-visionshaoqiuyuavailable/text-llm-vision目录 已分析Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析DeepSeek-VisionPlusqq247505/DeepSeek-VisionPlus目录 已分析DeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-tool-vision-readMappedinfo/dsh-tool-vision-read目录 已分析DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-skillDDDFXYqiming/dsh-vision-skill目录 已分析Vision skill plugin for DeepSeek Harness (image analysis and OCR)视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-mcpmoton16/dsh-vision-mcp目录 已分析Give your text-only LLM eyes: zero-dependency MCP server that reads images via external OpenAI-compatible vision models with automatic provider fallback, plus a one-command patch for DSH image-attachment degradation.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-image-readerzcXie777/dsh-image-reader目录 已分析Give DeepSeek Harness agents native image reading: a read_image tool backed by any OpenAI-compatible vision endpoint.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析shadow-visionWardLu/shadow-vision目录 已分析Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-bridgeXieweikang123/dsh-vision-bridge目录 已分析Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-visionsjakdhasdh/dsh-vision目录 已分析Vision tool plugin for DeepSeek Harness (DSH): give text-only models like deepseek-v4-flash image recognition via Alibaba Bailian / any OpenAI-compatible vision API. 给 DeepSeek Harness 无识图能力模型加识图工具。视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-bridgeTwistedRiCen/dsh-vision-bridge目录 已分析DSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-visionxzyonline/dsh-vision目录 已分析Vision for text-only DeepSeek: view_image tool via any OpenAI-compatible VLM endpoint. macOS/Windows/Linux, one-click install.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-image-toolsJuneLearn/dsh-image-tools目录 已分析DeepSeek Harness 多服务图片生成与编辑插件，支持 OpenAI Images、Gemini Interactions 与顺序故障转移。Multi-provider image generation and editing for DeepSeek Harness.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-visionzoahdev/dsh-vision目录 已分析Give DeepSeek Harness eyes: analyze images with an OpenAI-compatible vision model via a vision_analyze tool.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-bridgelium970320/dsh-vision-bridge目录 已分析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）视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-vision-toolvisail/dsh-vision-tool目录 已分析Paste an image into the chat box and text-only DSH models can "see" it — auto-rewrite of pasted images + analyze_image tool routed to a Kimi vision model.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析来源级候选描述来自第三方目录及 Registry 复核的公开来源，属于不可信导入文本安装前仍需本地 inspect / plan / confirm