go-farther-and-farther/dsh-tool-eyes ↗★ 0
dsh-tool-eyes
适用于 DeepSeek Harness 的本地视觉“眼睛”：屏幕工具（捕获屏幕或图像并由本地 VLM 描述）和 OCR 工具（Windows 内置 OCR，零模型/GPU/云）
AI 分析
核心用途是提供本地屏幕截图分析与免 GPU 的 Windows 本地 OCR 功能。适合注重隐私、需要在无云端模型或无独立显卡环境下进行屏幕识别与文字提取的用户。
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:go-farther-and-farther/dsh-tool-eyes说明文档
阅读完整 README ↗Configuration
Plugin config (all optional):
| key | default | meaning |
|---|---|---|
baseUrl | http://127.0.0.1:1235/v1 | OpenAI-compatible endpoint for screen |
model | '' | model id to send; empty lets the server decide (llama.cpp serves one model) |
timeoutMs | 180000 | hard cap for one capture call |
captureScript | bundled capture.ps1 | override path to an alternate capture script |
Override in your profile's cordis.patch.yml (id-targeted):
- id: tool-eyes
name: 'dsh-tool-eyes'
config:
baseUrl: http://127.0.0.1:1235/v1
model: qwen3.5-4b
timeoutMs: 120000
Usage
In a conversation, the agent can now:
screen— "what is on my screen?", "describe this image file", with an optionalpromptto focus on a region or detail.ocr— "read all the text on screen", "transcribe this error dialog".
Both accept an optional image path; without it they capture the screen.
The bundled PowerShell scripts can also be run standalone:
powershell -NoProfile -ExecutionPolicy Bypass -File lib\capture.ps1 -Prompt "..." -BaseUrl http://127.0.0.1:1235/v1
powershell -NoProfile -ExecutionPolicy Bypass -File lib\ocr.ps1 -Image C:\path\x.png