xsoc1/dsh-image-vision
“Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud).”
Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.
tt-a1i/archify
Generate validated, self-contained interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams from repositories or system descriptions.
Tencent/BrowserSkill
BrowserSkill bridge for controlling visible Chrome and Edge Agent Windows from DeepSeek Harness, with native browser tools, accessibility and VOM observations, screenshots, owned multi-session control, and a live Web UI overlay.
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
YuJunZhiXue/dsh-purge
Adds a Settings card to edit prompt-inject.md, manage AGENTS.md or CLAUDE.md rule sets, check for plugin updates, and apply or restore reversible local package updates.