multimodal plugins for DeepSeek Harness
9 indexed projects tagged multimodal · 6,408 combined stars · updated 2026-10-25
9 indexed projects carry the `multimodal` tag. Combined, they hold 6,408 GitHub stars. The list below is ranked by stars, not by our opinion — we do not sell placement in it.
Where they sit: Models & Routing (4), Agents & Teams (2), Terminal & CLI (1), Desktop Apps (1).
3 of these 9 have Chinese in their description — the language gap is why this index exists.
Ranked by stars
- 1liustack/modlens ★ 4,426
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). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GL… - 2ysr666/dsh-vision-router ★ 1,169
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 Pytho… - 3oxbshw/watch-skill ★ 518
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is… - 4ZSeven-W/dsh-crew ★ 179
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness v… - 5Stormycry-cryp/dsh-AuthInOne ★ 102
Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps. - 6supersealwqas/dsh-custom-provider-settings ★ 7
DeepSeek Harness 第三方 API 与自定义模型设置插件：支持请求头、User-Agent、模型列表、图像输入和思考等级 | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels - 7libinyam/dsh-vision-provider ★ 3
Config-only DeepSeek Harness bundle for OpenAI-compatible vision models. - 8Dogwind221/dsh-vision-skill ★ 2
Vision for text-only LLMs: multi-model failover vision API + drag-and-drop image recognition in the DSH web UI. Adapted from claude-vision-skill. 为纯文本模型补视觉能力 · 多模型自动降级 - 9AlexKaiqi/dsh-multi-model-provider ★ 2
Model catalog, portraits, Agent selection, and multimodal runtimes for DeepSeek Harness
How to read this list
- Ranking is GitHub stars only. Sponsored placements never appear in this list;
if we ever take one it is labelled and sits outside the ranking.
- Stars measure attention, not quality. A 200-star plugin that solves your
problem beats a 30,000-star desktop client you will not use.
- We do not execute plugin code. Descriptions are the upstream repo's own.
Related