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 1572 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-tool-visiongloryxpnv/dsh-tool-visionCatalog AnalyzedLocal-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-analyze-image-toolCaseyTso/dsh-analyze-image-toolCatalog Analyzed给纯文本 DeepSeek Harness 模型加上识图能力：analyze_image 把图片转发到任意 OpenAI 兼容视觉端点 | Vision bridge for text-only DSH modelsVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-plugin-mm-visionElohia/dsh-plugin-mm-visionCatalog AnalyzedSynesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedchat-deepseek-visionorrinzeng/chat-deepseek-visionCatalog AnalyzedA native DeepSeek Harness (DSH) Cordis plugin that analyzes images through the reverse-engineered chat.deepseek.com vision mode (model_type=vision) — free, no third-party vision API key required. DeepSeek Harness（DSH）原生 Cordis Plugin：通过逆向 chat.deepseek.com 识图模式（model_type=vision）分析图片，免费、无需第三方视觉 API key。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-llm-deepseek-visionNagasakiSoyo-ui/dsh-llm-deepseek-visionCatalog AnalyzedVision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-yali-image-generatordsh-yali-image-generatorCatalog AnalyzedDeepSeek-Harness 图像生成Plugin。申请 Yali AI API Key：https://api.yaliai.com/Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1dsh-shell-card-plusdsh-shell-card-plusCatalog AnalyzedReplaces the stock bash/pwsh terminal rows in the DSH web UI with shell command cards: long commands soft-wrap with line numbers instead of truncating, plus separate copy-command and copy-output buttons.UI EnhancementsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.2dsh-agent-shelldsh-agent-shellCatalog AnalyzedPersistent, conversation-decoupled multi-shell terminal panel for DeepSeek Harness (DSH): real tmux TTYs, 7 model tools, draggable floating panelMemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.3@easytz/dsh-terminal-panel@easytz/dsh-terminal-panelCatalog Analyzed终端面板：在当前工作区敲命令、看实时输出，多标签页、Tab 补全、Ctrl+C 中断。Terminal panel for DeepSeek Harness: run commands with streaming output, tabs, completion.UI EnhancementsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.7dsh-easyvisions3yf1337/dsh-easyvisionCatalog AnalyzedGive text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-omni-visionRenji004/dsh-omni-visionCatalog AnalyzedLocal eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-ui-external-visionxiyue718/dsh-ui-external-visionCatalog AnalyzedDSH 外接识图Plugin：当当前模型不支持识图时，调用外部视觉模型识别图片。 / External vision model plugin for DSH: recognize images when the active model lacks vision.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-tool-visionbcdahb0-jpg/dsh-tool-visionCatalog AnalyzedDeepSeek Harness 外置视觉模型Plugin：inspect_image 工具 + 文本模型图片桥（聊天显示图片、模型收文本提示）。External vision model + image bridge for DeepSeek Harness.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-solutionbr1nosense/dsh-vision-solutionCatalog AnalyzedGive DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolved@alain-prot0s5/dsh-screenshot@alain-prot0s5/dsh-screenshotCatalog AnalyzedScreenshot-to-input for DeepSeek Harness: composer camera button + global hotkey (Alt+A) + listener bound to the app lifecycle, configurable in settings. 截图自动粘贴到 DSH 输入框：相机按钮 + 全局快捷键 + 生命周期绑定 + 设置页配置。Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.4vision-translation-dshvision-translation-dshCatalog AnalyzedNative dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into <vision-context> via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.2dsh-web-ui#packages/dsh-tool-describe-imagezhu1090093659/dsh-web-uiCatalog AnalyzedA `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-auto-imagedsh-auto-imageCatalog AnalyzedBridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.3Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation