chou109/dsh-vision-bridge
chou109★ 0PowerShellLast synced: 2026-08-15
dsh-vision-bridge：在 DeepSeek Harness 聊天框粘贴图片，任意模型都能看懂——纯文本模型自动转成图片路径并调用 vision_chat 识图，支持图片的模型直接接收原图。粘贴即用，自动识别、自动回答。dsh-vision-bridge: paste any image into the DeepSeek Harness chat box — every model can see it: text-only models get an automatic vision_chat bridge, vision-capable models receive the image directly. Paste, send, done.
README excerpt
dsh-vision-bridge Paste an image into the DeepSeek Harness chat box and let the agent see and describe it automatically — no more "current model does not support images" errors, no manually handing over file paths. 国内镜像 / Mirror : also hosted on gitee.com/chill109/dsh-vision-bridge — Gitee is a mainland-China Git host (faster access from mainland China; use it if GitHub is slow). Platform Windows / macOS / Linux (dsh web) Requires DeepSeek Harness dsh web 0.1.0-rc.6 + the qwen-mm-plugins-api MCP server ( vision chat tool) License MIT (add a LICENSE file before publishing) 中文版见 README.zh.md。 Part 1 — If you are a human This part is written for people who just want the feature installed. What it does Before this project, pasting an image into the chat box with a text-only model (e.g. deepseek-v4-flash ) showed: 当前模型不支持图片，请切换支持图片的模型 / The current model does not support images; switch to a model that does After installing this project: 1. Paste any image into the send box (it shows as a thumbnail, as usual). 2. Send it — the message goes through even though the chat model cannot take images. 3. The harness automatically hands the agent the image as a local file path , and the agent aut…
View full README on GitHub →Category
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、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
★ 2,346
Anionex/agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
★ 946
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
★ 517