MIT 许可的视觉工具箱，让纯文本 agent 具备看图能力；通过 dsh-vision-toolkit Profile Bundle 原生接入 DeepSeek Harness，CLI + 技能也可用于任何能调 shell 的 agent。
DSH 适配
原生运行时
作者声明
安全审计
未审计
最后核验
2026-08-21
许可证
MIT
01它能帮你完成什么？
Give a text-only coding agent (e.g. DeepSeek) working vision: image Q&A, OCR of long screenshots and chat histories
Task-aware image answers, transcribed text, and merged OCR of scrolling pages with speaker/timestamp preservation
Developers running text-only models such as DeepSeek who need image understanding without switching to a multimodal model
Rebuild UI pages, infographics, icons and diagrams from screenshots or sketches into editable code
HTML/CSS reconstructions, transparent PNG extractions, editable SVG, and structured Mermaid/Graphviz representations
Frontend developers and designers who want agent-driven screenshot-to-code / sketch-to-interface restoration
Operate a GUI from screenshots: locate controls, act, and verify the resulting state
Pixel-coordinate grounding of controls and a verify-after-each-action automation loop
Automation engineers who need screen-element grounding (e.g. `ground`/`detect`) for GUI control with a text-only agent
02如何接入 DeepSeek Harness？
前置条件
- A coding agent already working with a model, including a text-only model such as DeepSeek V4
- A multimodal vision API supporting OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages, plus its base URL, API key, and model name
- Python 3.11+ for `glance`; optional `pillow` for `ground`/`detect`/`crop` and the long-screenshot OCR playbook, `pillow` + `numpy` for `trace`
安装步骤
- 01
Point it at a vision API — write three env vars (`VISION_API_KEY`, `VISION_BASE_URL`, `VISION_MODEL`) to `~/.config/agent-vision-toolkit/env` (`chmod 600`)
- 02
Put the CLIs on your PATH: `git clone https://github.com/Anionex/agent-vision-toolkit.git` then `export PATH="$PWD/agent-vision-toolkit/bin:$PATH"` (add to your shell profile to persist)
$ git clone https://github.com/Anionex/agent-vision-toolkit.git
- 03
Install the skill so your agent knows the tools exist: `npx skills add Anionex/agent-vision-toolkit --skill vision-skills -a codex -g --copy -y`, or copy `skills/vision-skills/` into your agent's skills directory (e.g. `~/.codex/skills/`) and restart the agent
$ npx skills add Anionex/agent-vision-toolkit --skill vision-skills -a codex -g --copy -y
- 04
Optional seamless integration: follow AGENT_INSTALL.md to install the transparent local proxy (Codex / Claude Code) or single-file native extension/plugin (Pi, Oh My Pi, OpenCode); for native DSH support use the linked `dsh-vision-toolkit` package (clone with `--recurse-submodules` or run `git submodule update --init --recursive`)
$ git submodule update --init --recursive
验证接入成功
- After installing the optional integration and restarting the agent, paste an image directly or let the model call its built-in image tool
03DSH 适配与能力边界
Native DSH Profile Bundle via the linked `dsh-vision-toolkit` package (tracked as a Git submodule); the standalone CLIs and `vision-skills` skill also run in any shell-capable agent
glance — intent-aware image Q&A and OCR
an image file plus a question (or `--ocr`)→task-aware answers or transcribed text, focused on the current step's intent instead of a generic description
sends the image and focus hint to the configured external multimodal vision APIground / detect — pixel-coordinate localization
an image plus a target description (optionally `--region`)→bounding boxes in original pixel coordinates; numbered element inventories with exact visible text
sends the image to the configured external multimodal vision APItrace / crop — deterministic SVG fitting and region cropping
a flat, high-contrast graphic (or a pixel box for `crop`)→editable SVG primitives (`<circle>`, `<line>`, `<polyline>`, `<polygon>`) fitted locally; cropped region files for reuse
writes output files (SVG / cropped images) to diskSeamless integration — transparent local proxy / native extensions
agent requests containing pasted images or built-in image tool calls→images replaced with task-aware text descriptions before reaching the text-only upstream, with no extra prompting
runs a local proxy at 127.0.0.1:19100 and forwards requests (including the original Authorization header) to your existing upstream
04适合谁？何时不该用？
适合
- Developers running text-only models such as DeepSeek who need image understanding without switching to a multimodal model
- Frontend developers and designers who want agent-driven screenshot-to-code / sketch-to-interface restoration
- Automation engineers who need screen-element grounding (e.g. `ground`/`detect`) for GUI control with a text-only agent
不适合
- This is an image-to-text layer — it doesn't hand vision tokens directly to the text model, and overall visual-task quality is determined jointly by the primary LLM and the multimodal LLM.
05兼容性、维护与安全提示
- This is an image-to-text layer — it doesn't hand vision tokens directly to the text model, and overall visual-task quality is determined jointly by the primary LLM and the multimodal LLM.
- Requires an external multimodal API (OpenAI Chat Completions / Responses / Anthropic Messages) with its own base URL, API key, and model name; images leave your machine to that endpoint.
- The proxy's cache lives only inside its process and is cleared on restart.
MIT · actively maintained (latest release v0.2.0, 2026-08-14)
06常见问题
如何把 agent-vision-toolkit 接入 DeepSeek Harness？
通过配套的 `dsh-vision-toolkit` 包——它是 DSH Web 与 Headless 配置的原生 Profile Bundle，提供 10 个结构化视觉工具，并带 DSH Credentials、托管隔离运行时和 Agent 级渐进式工具暴露。它以 Git submodule 形式跟踪：克隆时加 `--recurse-submodules`，或在现有仓库里运行 `git submodule update --init --recursive`。
DSH 集成是原生还是走 MCP？
原生——`dsh-vision-toolkit` 以 Profile Bundle 形式在 DSH 内原生运行，不走 MCP。另外，基础工具箱的 CLI 可被任何能调用 shell 的 agent 直接使用，无需任何集成。
需要什么前置条件？
一个已经能配合模型工作的编程 agent（DeepSeek V4 这类纯文本模型即可），以及一个支持 OpenAI Chat Completions / Responses / Anthropic Messages 的多模态视觉 API（含 base URL、API key 和模型名）。`glance` 需要 Python 3.11+；`ground`/`detect`/`crop` 需要 `pillow`；`trace` 需要 `pillow` + `numpy`。
我的图片和数据会发送到哪里？
图片内容与任务聚焦提示会发送到你在 `VISION_BASE_URL` 中配置的多模态视觉 API。可选的本地代理运行在 127.0.0.1:19100，只原样转发你原有的上游 Authorization 头，不会另外存储上游 API key。
有哪些限制需要注意？
它是图像转文本层——视觉 token 不会直接进入文本模型；视觉任务质量由主模型和多模态模型共同决定；代理缓存只存在于进程内存中，重启即清空。
07相关的 DSH 工作流
modlens
作者 liustack
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）。
dsh-vision-router
作者 ysr666
为纯文本 DeepSeek Harness 智能体提供「视觉」能力，内置免密钥视觉链路与像素级视觉工具，一条命令安装，无需 Python。
dsh-vision-toolkit
作者 anionex
[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端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.
dsh-image-gen
作者 shanliuling
直接在 DeepSeek Harness 对话中生成图片，无需切换外部工具。
08数据与来源
The new [`dsh-vision-toolkit`](https://github.com/Anionex/dsh-vision-toolkit) linked package brings this toolkit into DS…
It provides 10 structured visual tools for intent-aware image Q&A, grounding, detection, tracing, cropping, pixel diff,…
The package is tracked here as a Git submodule and maintained independently at [`Anionex/dsh-vision-toolkit`](https://gi…
页面基于项目公开文档、仓库元数据和 DSH Plugins 的结构化解析生成；最后核验于 2026-08-21。发现错误？提交更正。
最佳 DeepSeek Harness 插件
从全目录挑出的 12 个值得优先安装的插件，覆盖各个分类。