DeepSeek Harness Plugin Hub
← Plugins

dsh-tool-visual-primitives

Tool Visual Primitives

DSH visual primitives tool: Based on DeepSeek’s paper “Thinking with Visual Primitives,” routes images to an external vision model and returns text analysis with visual primitives. In a text-only loop, conversational models can “see” images without native vision capabilities.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:InkshadeWoods/dsh-tool-visual-primitives#e1ba75ad226059c8df374df5c3c607f874e4f3d5
对截图进行 UI 复刻的对话

Compatibility and provenance

Tool Visual Primitives is published as dsh-tool-visual-primitives and currently resolves to version 1.3.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated

Versions

1.3.0stable
1.2.0stable
1.1.1stable
Show 1 more versionCollapse versions
1.1.0stable

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Vision Toolkit@anionex/dsh-vision-toolkitDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.Deepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.Imagegen@dickpy/dsh-imagegenAI 鐢熷浘 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / grok-imagine-image / dall-e-3, with native xAI Grok Imagine request shaping), with a settings card for