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
Mult-Hands-Eyes-MCPMicroHEROX/Mult-Hands-Eyes-MCPCatalog AnalyzedMCP server that gives online LLMs local hands and eyes: OpenAI-compatible local inference (KoboldCpp / Unsloth / llama.cpp / LM Studio / Ollama) for cheap text work and vision work (OCR / image analysis / comparison).Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-deepeye-setupgrasir-ctrl/dsh-deepeye-setupCatalog AnalyzedGive DeepSeek Harness eyes: one-click install the dsh-plugin-deepeye vision plugin with the free Zhipu GLM-4V-Flash model. Paste images into text-only LLMsVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedopen-designnexu-io/open-designCatalog Analyzed🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-mp-automatorVincentJiang06/dsh-mp-automatorCatalog AnalyzedWeChat Mini Program automated testing for DeepSeek Harness (dsh) — selector-addressed actions, build-freshness gates, geometry-first assertions for text-only models, real screenshots on vision routes · 微信小程序自动化测试 dsh PluginVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-model-managerhrhgit/dsh-model-managerCatalog AnalyzedModel tags, reasoning capabilities, image routing, and vision proxy support for DeepSeek HarnessVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedgewu-toolsgewu-toolsCatalog AnalyzedModel-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.0dsh-ros2StvLi/dsh-ros2Catalog AnalyzedROS2 debugging toolset and robot-state vision analysis for DeepSeek Harness: node/topic/service/action/interface/TF enumeration, whole-graph topology JSON, rosdep checks, approval-gated builds and custom message scaffolding, GUI screenshots and multimodal vision observation, plus headless RViz2 offscreen rendering (low-poly meshes, direct pixel read, GPU passthrough - motion rendering at 30Hz) with parallel VLM realtime analysis.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-drawdsh-drawCatalog AnalyzedMulti-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-session quota tracking, engine failover, credential-safe config, and a result card with regenerate.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.15AI-Novel-WriterEthanYoQ/AI-Novel-WriterCatalog AnalyzedAI 小说创作软件：把灵感、角色、世界观、大纲、章节写作、审稿和修稿组织成可控流程；提供 Windows/macOS 桌面版，支持本地和在线模型。AI Novel Writing Software: Organizes inspirations, characters, worldbuilding, outlines, chapter drafting, review, and revision into a controllable workflow. Features desktop apps for Windows/macOS, Ollama integration, and a DeepSeek Harness (DSH) plugin preview.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedPicGo-CorePicGo/PicGo-CoreCatalog Analyzed:zap:The ultimate image uploading engine. Both CLI & API supports.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-appshotsdsh-appshotsCatalog AnalyzedCodex-style window capture for DSH Desktop on macOS and Windows: press both Command keys (macOS) or both Ctrl keys (Windows), or the camera button, to grab the frontmost window, attach it to the current chat, and inject a VoiceOver-style accessibility tree as hidden context.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.8dsh-crew@zseven-w/dsh-crewCatalog AnalyzedDispatch work to DSH agents from Claude Code or Codex: native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge for vision and image generation.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0-rc.7dsh-model-pickerttmouse/dsh-model-pickerCatalog AnalyzedModel picker for the DSH web composer that replaces the model seat: a search-first popup whose left column indexes the suppliers and scrolls the grouped list, with a favorites group pinned at the top, image icons separating native from bridged vision input, and a reasoning-effort panel opened from the right zone of the trigger.UI EnhancementsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedoh-my-dshllmpolska/oh-my-dshCatalog AnalyzedTiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.Models & ProvidersGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-llm-openai-completionsdrscrewdriver/dsh-llm-openai-completionsCatalog AnalyzedOpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).Models & ProvidersGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-plugin-t-expertdsh-plugin-t-expertCatalog AnalyzedT Expert — a 323-expert, 22-division roster with full Chinese translations, as a standalone DeepSeek Harness plugin, with a built-in multi-agent team engine (T Team).Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.90@eric.wen/dsh-sight@eric.wen/dsh-sightCatalog AnalyzedDeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing, reasoning-effort auto-fill, and progressive Figma MCP bridging (design-to-code + AI-driven design).Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.15dsh-docdsh-docCatalog AnalyzedLocal PDF, Office, image, and OCR document intelligence for DeepSeek Harness.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation