dsh-superagent
Proactive coding agent for one GitHub repository, packaged for DeepSeek Harness. It listens to GitHub and optionally Feishu, opens work items, works independently, replies in the original conversation, and shows human-needed work in a web
Visit deepseek-ai/dsh-superagent-prototypeOverview
dsh-superagent is a research prototype of a proactive coding agent for one GitHub repository. Packaged as a bundle for DeepSeek Harness, it listens to GitHub and optionally Feishu. When an allowed user asks for work, it opens a work item, works in its own agent session and directory, and replies in the original conversation, for example with a pull request. A web panel shows what needs a person.
Key Features
- Listens to GitHub and, optionally, Feishu for work requests.
- Opens a work item and works on it in its own agent session and directory.
- Replies in the original conversation, for example with a pull request.
- Provides a web panel that shows what needs a person.
- Acts only when asked or when a team-written rule allows, and speaks only when someone must act or can use a result.
- Packaged as a bundle for DeepSeek Harness and targets one GitHub repository.
Use Cases
- Taking on requested repository work from GitHub or Feishu, then returning a result such as a pull request.
- Letting teams using DeepSeek Harness trial a proactive agent for one repository.
- Reviewing work that needs human attention in a web panel.
- Separating each work item into its own agent session and directory.
Getting Started
- Ask a coding agent to read SETUP.md in the repository and set up dsh-superagent with you.
- During setup, the agent asks one short question at a time, shows the full plan once, then installs and configures everything.
Deployment & Requirements
- A DeepSeek Harness environment, because the project is packaged as a bundle for DeepSeek Harness.
- One GitHub repository for the agent to watch and work on.
- Feishu integration is optional.
Before You Adopt
- License: MIT. Review its terms before using, modifying, or distributing the project.
- The project is a research prototype and is not an official DeepSeek product.
- The code is not production-ready and may contain bugs or inconsistent engineering practices.
- Users should review and adapt the code before using it in their own environment.
