dsh-llm-workbuddy
Run the following command in DeepSeek Harness:
dsh plugin install zdk119746/dsh-llm-workbuddy
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command `dsh plugin install zdk119746/dsh-llm-workbuddy`. The source code is available at https://github.com/zdk119746/dsh-llm-workbuddy.
About this plugin
Juggling API keys and accounts for multiple LLM services can be a hassle. This plugin is designed to solve that: it allows you to directly leverage your existing WorkBuddy/CodeBuddy account to access its rich model library (such as DeepSeek-V4, GLM-5.x, etc.) within the DeepSeek Harness environment, all without needing to apply for or configure new API keys.
Its core strength lies in transforming complex backend integration into a streamlined web experience. Through the locally running workbuddy2api proxy, it seamlessly bridges private protocols with standard interfaces. On the web interface, you'll find a new WorkBuddy model group, where the model list updates in real-time based on your account status, and reasoning-capable models offer a reasoning effort selector. A persistent widget in the bottom-right corner provides at-a-glance visibility into login and proxy status, supporting one-click login and diagnostics, which significantly simplifies maintenance.
This plugin is especially suited for two types of users: first, existing WorkBuddy/CodeBuddy users who wish to integrate its models more conveniently into their daily development or research workflows; second, technical enthusiasts who enjoy experimenting with various LLM capabilities locally, as it offers a low-barrier, highly integrated way to expand model choices. If you desire to manage and switch between models from different providers within a unified interface, it will be a powerful tool.
Use Cases
- Quickly integrate model capabilities into a DeepSeek Harness development environment when you have an existing WorkBuddy account.
- Need to conveniently manage and switch between multiple LLMs from different providers within a unified interface.
- Using cloud-based models in a local environment without the need to handle complex API key configurations.
Best For
- Developers who have WorkBuddy/CodeBuddy accounts and want to simplify the process of using its models.
- Tech enthusiasts and LLM researchers seeking to conveniently experiment with different model capabilities in a local environment.
- Engineers pursuing localized, integrated development environments who wish to manage multiple AI services within one tool.
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.