dsh-image-bridge avatar

dsh-image-bridge

PluginVisionVision / OCRFile
Verification
L1 · Found
Security
Low
Health
Active
Trust
Unrated

What it doesAI

Converts images attached in Web GUI messages into text descriptions via vision models, enabling text-only LLMs like DeepSeek to understand them.

  • Intercepts agent pre-step events to replace image blocks with text descriptions
  • Retries with exponential backoff on 429/503, falls back to alternative models
  • Works with modality plugins to let text-only LLMs see images

AI-generated from the repo README — for reference only.

Installation

dsh plugin --profile web add github:Seryta/dsh-image-bridge

Install method: GitHub · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO VETPASSEDeadd2a
Automated review · daily
PASSED

Vet static analysis found no suspicious behavior — verdict is clean.

0 critical·0 high·0 medium·100 score
plugin version0.2.0dsh manifest
scanned commiteadd2a137f602026-08-21
latest commiteadd2a137f60
vet verdictclean · gitscore 100

Vet is an AST static scan (npm artifact or git source).

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Risk details

No critical or warning findings.

Activity

Last commit 2026-08-14 · activity: Active

• Repo created: 2026-08-21

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/Seryta/dsh-image-bridge

Was this page helpful?