Category · 3 listed

Vision plugins for DeepSeek Harness

Give a text-only model eyes: OCR, screenshot Q&A, UI restore, pixel diff.

liustack/modlens

660

stars

First vision plugin for DeepSeek Harness. Paste an image, get structured JSON: OCR, layout, semantics.

Anionex/agent-vision-toolkit

486

stars

Vision toolkit for text-only LLMs. Works with Codex, Claude Code, Pi, OpenCode — and tags dsh-plugin.

Anionex/dsh-vision-toolkit

125

stars

Harness-native vision toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts.