Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision
Near-native image understanding for DeepSeek Harness.
Plugin facts
Screenshots
About this plugin
Near-native image understanding for DeepSeek Harness
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:oil-oil/dsh-vision ⚠️ Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
About this plugin: dsh-vision
What is dsh-vision?
dsh-vision is a tools & capabilities plugin maintained by oil-oil. Near-native image understanding for DeepSeek Harness.
How do I install dsh-vision?
Run dsh plugin add github:oil-oil/dsh-vision in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:oil-oil/dsh-vision#commit.
Is dsh-vision free?
dsh-vision is a community open-source project released under the MIT license. You can inspect its source and install it for free.
Related plugins
The ultimate image-uploading engine with both CLI and API support — a household name in the Chinese dev community.
agent-vision-toolkit
⭐ 840Give text-only coding agents eyes: image Q&A, long-screenshot OCR, frontend UI restoration and GUI automation, as a vision toolkit plus a skill, with optional drop-in support for Codex, Claude Code and more.