Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
View plugin → 
liustack
internalcot
Make agents show their full chain of thought.
Plugin facts
GitHub stars⭐ 8
LicenseMIT
Primary languageTypeScript
Last push2026-08-11T22:10:42Z
Maintainermorluto
Added to this directory2026-08-15
Screenshots
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:morluto/internalcot ⚠️ 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: internalcot
What is internalcot?
internalcot is a tools & capabilities plugin maintained by morluto. Make agents show their full chain of thought.
How do I install internalcot?
Run dsh plugin add github:morluto/internalcot 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:morluto/internalcot#commit.
Is internalcot free?
internalcot 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.
View plugin → 
PicGo
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.
View plugin → 
Anionex