dsh-vision
Give DeepSeek Harness eyes: analyze images with an OpenAI-compatible vision model via a vision_analyze tool.
给DeepSeek Harness装上眼睛：通过vision_analyze工具，使用兼容OpenAI的视觉模型分析图像。
How to install
dsh plugin add dsh-vision About
dsh-vision Give DeepSeek Harness eyes: a vision_analyze tool that sends an image (local path or URL) to an OpenAI-compatible vision model and returns a text answer. English | 中文 Install sh dsh plugin --profile web add dsh-vision Set apiKey (or OPENAI_API_KEY), or point baseUrl at a local OpenAI-compatible endpoint such as Ollama (http://localhost:11434) with a vision model. Tool | Parameter | Type | Description | | --- | --- | --- | | image | string | Image path or https/data: URL | | question | string | What to ask (default: "Describe this image in detail.") | Config | Key | Type | Default | …
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 0
- mo. downloads
- 1.9K
- Last push
- 2026-08-17
- Created
- 2026-08-17
Links
Basic safety check
- Findings
- None
- Sources
- curated:0xsline/awesome-deepseek-harness
- Topics
- agent, deepseek-harness, dsh-plugin, image, multimodal, vision
Related plugins
mobile-mcp
mobile-next/mobile-mcp
Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
davinci-resolve-mcp
samuelgursky/davinci-resolve-mcp
MCP server integration for DaVinci Resolve Studio
ssh-mcp
tufantunc/ssh-mcp
MCP server exposing SSH control for Linux servers via Model Context Protocol.