Skip to content
dsh-market Browse plugins GitHub 中文

Junkrat9527/dsh-autovision

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

Stars ★ 0 Category Vision & Multimodal Listed 2026-08-19 npm @iroam2375/dsh-autovision

Install

Inside DeepSeek Harness, with dsh-market

dsh plugin --profile web add dshmarket

Or from the command line

dsh plugin --profile web add @iroam2375/dsh-autovision

Installing runs third-party code with your own permissions — it can read your files, use your credentials and reach the network. Review the source first, and pin a commit (github:owner/repo#sha) when you can.