Plugins
The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.
Found 1065 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-visual-aidshenyan-008/dsh-visual-aidCatalog Analyzeddsh visual aid plugin: lets text-only main models handle images via a vision modelVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-computer-use-pluginbeijingwahw/dsh-computer-use-pluginCatalog AnalyzedVision-only desktop automation agent plugin for DeepSeek Harness (DSH) | 纯视觉桌面自动化 Agent Plugin：SoM grounding · Planner-Actor · effect verification · skill libraryVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-visibridgelhbsaa/dsh-visibridgeCatalog AnalyzedStructured vision evidence (OCR/layout/semantics) plus a USB camera capture tool for a "shoot-look-adjust" debug loop; backends: Ollama, DeepSeek, Xiaomi.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-xiapan-mediadongsheng123132/dsh-xiapan-mediaCatalog AnalyzedNative vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan CloudVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-qwen-mmRRRosmontis/dsh-qwen-mmCatalog AnalyzedQwen-MM-Plugins integration bundle for DeepSeek Harness (dsh) — multimodal MCP tools (vision, OCR, ASR, search, video, Blender, FreeCAD) + image attachment bridge. 让 DeepSeek Harness 原生支持多模态。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedsidesightZhuXinAI/sidesightCatalog AnalyzedCLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-computer-use-windowsAltairpaca/dsh-computer-use-windowsCatalog AnalyzedWindows Computer Use for DeepSeek Harness (DSH): window-bound screenshot/OCR/click with verification loop, pure-OCR mode, pluggable vision models.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-pluginsBernardxu123/dsh-pluginsCatalog AnalyzedDeepSeek Harness (dsh) 官方 bundle 规范Plugin集合: dsh-vision 看图 + dsh-sensenova-image 生图 + dsh-client-stats-decimal 统计两位小数Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedlocallensuknowmyface/locallensCatalog AnalyzedLocal OCR for DeepSeek Harness — read text from screenshots on your Mac with Apple's Vision framework. No API key, no upload.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-text2img-compressNigel211/dsh-text2img-compressCatalog Analyzed把长文本渲染成图片发送，利用每图 384 token 封顶压缩 LLM 输入 token，专为DeepSeek Harness设计的Plugin；Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedprismrelay-mcpArnoldkevin/prismrelay-mcpCatalog AnalyzedVision-first local MCP that gives text-only Agents image understanding through Agnes AI (BYOK).Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddeepseek-mcp-pluginYNM10086/deepseek-mcp-pluginCatalog AnalyzedDSH 宿主级图片理解Plugin：vision_describe 工具，MiniMax → 智谱 → Ollama 三层后端自动降级，随 DSH 启动自动挂载Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-Sightcransmathenia666-hash/dsh-SightCatalog AnalyzedGive text-only DeepSeek Harness (dsh) agents vision — pasted images auto-convert to text descriptions with persistent caching, each image converted only once.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-tool-read-tifffulander0301/dsh-tool-read-tiffCatalog AnalyzedModel-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-anydoc-markdownSeerableOfficial/dsh-anydoc-markdownCatalog AnalyzedDocument → Markdown + vision image description plugin for DeepSeek Harness (dsh). Converts Word/PPT/Excel/ODT/RTF/EPUB/CSV/PDF via firecrawl-anydoc and describes embedded images with a VLM.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedSuperMate-Harness-SystemSuperMate-Ai/SuperMate-Harness-SystemCatalog AnalyzedGive DeepSeek Eyes · 给 DeepSeek 装眼睛 — a DeepSeek Harness (DSH) Skill: local vision models or vision APIs let DeepSeek read images and graphic filesVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-modlensYZz-S/dsh-modlensCatalog AnalyzedDeepSeek Harness (dsh) vision plugin — a fork of ModLens adding multi-engine image reading (Gemini, Volcengine Ark/Doubao, Claude) with per-call engine selection.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-v4flash-tilerdoublehappy123/dsh-v4flash-tilerCatalog AnalyzedDSH plugin: auto-tiles oversized chat images into labelled grid tiles for DeepSeek v4Flash vision, with Python tiling engineVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedSource candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation