dsh-codebuddy-plugin
Run the following command in DeepSeek Harness:
dsh plugin install taikaikaikai-pixel/dsh-codebuddy-plugin
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, use the command dsh plugin install taikaikaikai-pixel/dsh-codebuddy-plugin, or obtain the source code directly from the GitHub repository at https://github.com/taikaikaikai-pixel/dsh-codebuddy-plugin.
About this plugin
In AI development, users often need to call multiple models for inference while integrating web search, web scraping, and image generation functionalities, but existing tools may lack a unified and flexible solution. The dsh-codebuddy-plugin fills this gap for DeepSeek Harness users by providing a comprehensive plugin package through the CodeBuddy gateway. Its core capabilities include support for 18 mainstream models (such as DeepSeek, Zhipu GLM, and Moonshot Kimi), with most models offering adjustable reasoning strength and image input acceptance; it also integrates web search and web scraping backends, as well as an image generation tool based on Hunyuan. All features are managed through a local streaming bridge for unified request handling and credential management, ensuring an efficient and secure calling experience. This plugin is ideal for developers, AI researchers, and project teams using DeepSeek Harness who need to quickly access diverse AI models and web tools in local or production environments to streamline workflows and enhance development efficiency.
Use Cases
- Tasks requiring calls to multiple AI models for dialogue and inference.
- Integration of web information retrieval or web content fetching into AI workflows.
- Generating images from text prompts to assist with creative or design work.
Best For
- Programmers using DeepSeek Harness for AI development.
- Technologists engaged in AI research and experimentation.
- Project teams needing to integrate multiple AI models and web tools.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.