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 1334 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
deepseek-vision#plugins/dsh-plugin-deepseek-visiondsh-plugin-deepseek-visionCatalog AnalyzedVision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.2dsh-audio-copilotdsh-audio-copilotCatalog Analyzed聊天框语音输入按钮 for DeepSeek Harness: 点击麦克风说话,多引擎转写(智谱 GLM-ASR-2512 / 本地 faster-whisper / Gemini / OpenAI)自动填入输入框。一个按钮,所见即所得。Voice & AudionpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.0dsh-audiodsh-audioCatalog AnalyzedAudio toolkit for dsh - name reserved; first release in development.Voice & AudionpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.0.1dsh-invoicedsh-invoiceCatalog AnalyzedInvoice tools for dsh - name reserved; first release in development.Voice & AudionpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.0.1dsh-vision-proxydsh-vision-proxyCatalog AnalyzedDeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit2 reported in bounded auditArtifact0.4.1@gelomen/glm-vision-plugin@gelomen/glm-vision-pluginCatalog AnalyzedDSH Web Plugin：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + Plugin设置卡片）。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.0dsh-glm-visiondsh-glm-visionCatalog AnalyzedGLM 视觉模型Plugin：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.3dsh-vision-guarddsh-vision-guardCatalog AnalyzedTransparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.3@lijian-ui/dsh-vision-toggle@lijian-ui/dsh-vision-toggleCatalog AnalyzedPer-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.1dsh-free-visiondsh-free-visionCatalog AnalyzedFree vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit3 reported in bounded auditArtifact1.0.8dsh-autovision@iroam2375/dsh-autovisionCatalog AnalyzedVision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-vision-pro-bridgedsh-vision-pro-bridgeCatalog AnalyzedVision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.0image-visionwangyang10/image-visionCatalog AnalyzedDSH plugin from wangyang10/image-visionVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-imagenxuxun-oss/dsh-vision-imagenCatalog AnalyzedDeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-visionxiaoyuink/dsh-image-visionCatalog AnalyzedImage understanding for any DSH model: vision, OCR, grounding, and crop tools with domain presets for histopathology, cell biology, anatomy, clinical images and scientific figures.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-visionxsoc1/dsh-image-visionCatalog AnalyzedChat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-visionVeryInt/dsh-image-visionCatalog AnalyzedDSH plugin from VeryInt/dsh-image-visionVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-visionniushuanan/dsh-image-visionCatalog AnalyzedLet vision-capable models read native attachments while giving text-only models an image tool that supports follow-up questions.Vision & 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