
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.
Install Dsh Vision Toolkit
Clean install: prebuilt on npm and declares a `dsh.bundle` layer. Heads up: it runs install-time scripts (prepack) on your machine.
The one-line version
dsh plugin --profile my-profile add @anionex/dsh-vision-toolkitThe easy path: this bundle is published to npm, so the install pulls a prebuilt artifact — no build step runs on your machine and no build approval is needed.
From npm — installs a prebuilt artifact, no build step on your machine
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add @anionex/dsh-vision-toolkit
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profilePackage: @anionex/dsh-vision-toolkit
Prefer to install from source instead?
From GitHub — pulls source, and may ask for build approval on first run
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add github:Anionex/dsh-vision-toolkit#<commit-sha>
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profileBefore you run itinstall scripts
- This package declares
prepack— package-manager lifecycle scripts that execute on your machine at install time, outside the agent sandbox, before any tool-approval prompt exists. - A plugin runs with your permissions once loaded: it can read your files, use your credentials and reach the network. Tool approvals do not sandbox it.
Prerequisites
- API key
- Required — see the repository README for which provider.
- Network access
- Not required at runtime.
- Language
- TypeScript
Install check
Every field the verdict was derived from, so you can re-derive it yourself
| Field checked | Result | Weight | What the spec says about it |
|---|---|---|---|
| lifecycleScripts | fail | warn | runs at install time, outside the agent sandbox: prepack |
| dsh.bundle | pass | fatal | package.json declares a `dsh.bundle` layer |
| dsh.bundle.patch file | pass | fatal | patch file present at `cordis.patch.yml` |
| npm registry | pass | fatal | published as `@anionex/dsh-vision-toolkit` — prebuilt artifacts |
- Verdict reason
- on npm with a valid bundle declaration
- package.json read
- package.json
- Rules applied from
- docs/user/develop/basic/publish.md
- Checked at
- 2026-08-15
- Install-time scripts
prepack
From the README
Excerpt as published by the author, plain text, unedited
**Install:** `dsh plugin --profile web add @anionex/dsh-vision-toolkit` **DSH Vision Toolkit brings [`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) into DeepSeek Harness as a native Profile Bundle.** Give text-only DSH agents eyes—and keep vision in the harness—with intent-aware image Q&A, OCR, original-pixel grounding, UI restoration, pixel verification, managed Artifacts, and Web Settings. Ten independent tools replace shell glue with structured schemas and Agent-scoped progressive exposure. **Upstream toolkit:** [Anionex/agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit) · **Project website:** [agent-vision.anionex.me](https://agent-vision.anionex.me) English | [中文](README.zh.md) `agent-vision-toolkit` treats vision as an Agent-callable capa
Topics
GitHub topics on this repository
More in Text Only Vision Model
Ranked by similarity inside the cluster, not alphabetically
Dsh Sfversion
sparkmio
SF视觉桥——给纯文本模型的 DeepSeek Harness 装上眼睛。
Dsh Vision
xiaoshihou514
DeepSeek Harness: vision
Dsh Plugin Vision
MoneShadow
一个可以让没有视觉的大模型拥有视觉能力的插件(当然,是通过外挂视觉模型实现的)
Dsh Vision Recognizer
kaixinbaba
DeepSeek Harness 识图插件:保持 DeepSeek 对话,15+ 供应商视觉模型把图片转译为文字,可在 设置→插件 配置
Dsh Vision Bridge
ximengxiaolan
Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????
Dsh Vision
Terry12138qy
DeepSeek Harness 识图插件:为不具备原生识图能力的模型提供识图能力(阿里云百炼 qwen3.5-omni-plus,失败自动切换智谱 glm-4.6v-flash)。由 claude-vision-skill 移植适配。 | Vision tool for DeepSeek Harness