dsh-vision-router
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
This plugin is a GitHub repository with the dsh-plugin topic — the repository README is the authoritative install source. Use the template below, adapting the package name / path from the README:
dsh plugin --profile web add $dsh-vision-routerLocal development? dsh --profile web --patch ./cordis.yml with an absolute plugin path — see Plugin Development.GitHub source? dsh plugin --profile web add github:$ysr666/$dsh-vision-router — needs a prepare script in the repo (see packaging).
| Repository | ysr666/dsh-vision-router |
| License | LGPL-3.0 |
| Category | Tool |
| Status | Unverified |
| Last commit | 2026-08-14 |
| Indexed | 2026-08-14 |
Plugin and skin collection for DeepSeek Harness (DSH) Web UI - task board, git graph, right-side panel, remote mobile UI, pet, live token stats, and skin center.
View
Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent
View
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).
ViewQuestions or feedback? Official Discussions is the project’s canonical support channel; Discord has an active community. dsh.so itself improves via plugin submissions and your feedback.