Plug-in vision for text-only models on DSH
kanchengw/dsh-mindseye · model-adapters
Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.
★ 2GitHub stars
0Forks
2026-08-29Last updated
TypeScriptLanguage
MITLicense
Key features
- Preserves DSH image attachments instead of asking users to select local files manually.
- mindseye_generate_image sends a user's image request to the configured image-generation route.
- When gui.enabled is turned on, MindsEye opens a separate visible Chrome or Edge session.
- Image-capable models keep native DSH image blocks.
- Automatically mounts vision tools on image turns.
Install command
dsh plugin --profile web add github:kanchengw/dsh-mindseye