Home / AI news / DeepSeek open-sources dsh-superagent, a research prototype of a team coding agent
AI news

DeepSeek open-sources dsh-superagent, a research prototype of a team coding agent

DeepSeek's Harness team published dsh-superagent on GitHub under the MIT license, a research prototype of a proactive coding agent that takes requests from GitHub and Feishu, works on each in its own session and replies with results such as pull requests.

What happened

  • On October 31, 2026, DeepSeek published the dsh-superagent-prototype repository on GitHub under the MIT license, alongside a technical article from its Harness team.
  • The agent works on one GitHub repository and can also listen to Feishu chats. When an approved person asks for work, it opens a work item, handles it in its own agent session and directory, and answers in the original thread, for example with a pull request.
  • A web panel lists what needs a person. The README says the agent acts only when asked or when a rule the team wrote allows it, to take as little human attention as possible.
  • DeepSeek labels it a research prototype, not an official DeepSeek product, and tells users to review and adapt the code before running it. It is packaged for DeepSeek Harness, and setup is meant to be done with a coding agent following the repo's SETUP.md.
Why it matters: It is a working, open example of a coding agent that serves a whole team from their chat and GitHub instead of one developer's terminal. Teams building internal agents can study its authorization and attention rules, but it isn't a supported product.

Sources

Checked November 1, 2026 against the sources above. Claims about performance or benchmarks are the company's own unless stated otherwise.

More AI news