# DeepSeek open-sources dsh-superagent, a prototype agent that runs GitHub requests in parallel sessions

Canonical: https://theagenticweekly.com/news/deepseek-dsh-superagent-coding-agent-prototype · Evidence: Reported · First seen: 2026-11-01 10:00 UTC · Source published: 2026-10-31 09:32 UTC · Brief published: 2026-11-01 10:09 UTC · Updated: 2026-11-01 10:09 UTC · Author: Agentic Weekly

> dsh-superagent is an MIT-licensed coding agent DeepSeek put on GitHub on Oct 31, 2026: a DeepSeek Harness bundle that runs each allowed GitHub or Feishu request in its own agent session. Its README calls it a "Research prototype for reference only, not an official DeepSeek product."

## What changed

- dsh-superagent is a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness. It listens to GitHub and, optionally, Feishu, and answers in the original conversation, for example with a pull request.
- It splits work between a router and workers: a main session decides whether a request should become a work item (a Ticket), and each accepted Ticket runs in its own worker session and working directory, with a configurable concurrency limit.
- It acts only when an allowed person addresses it directly or when a rule the team wrote allows it; proactive work starts in a mode that only records what the agent would have done.
- A web panel inside DeepSeek Harness lists first what needs a person (questions, reviews, blocked or failed work), then system health and the history of each request.
- The deployment guide says both of its presets run with full access as the operator's OS user and that its account wrappers are not a security boundary; it recommends a dedicated OS account and a separate GitHub user for the agent.
- It requires Node.js 22.19+ or 24+, GitHub CLI 2.48 or later and a repository on github.com (GitHub Enterprise Server is not supported), plus a model provider configured for DeepSeek Harness.

## In the source's words

> "Research prototype for reference only, not an official DeepSeek product."
> (dsh-superagent README, https://github.com/deepseek-ai/dsh-superagent-prototype)

> "take as little human attention as possible, and give as much value as possible."
> (dsh-superagent README, on how the agent is meant to work, https://github.com/deepseek-ai/dsh-superagent-prototype)

## Early verdict

Worth reading for anyone designing team-facing coding agents, mainly for its permission and attention rules; treat it as research code, as DeepSeek itself does, and isolate it before running it on a real repository. (Basis: Based only on the repository's README and docs as read on Nov 1, 2026; we have not run it.)

## What we have not verified

- We did not install or run dsh-superagent or DeepSeek Harness; everything here comes from the repository's README and docs as read on Nov 1, 2026.
- Press coverage cites a DeepSeek simulation in which p95 task completion time fell from 29.5 to 15.7 minutes; that figure is not in the repository and we have not seen DeepSeek's own write-up, so we do not report it as fact.
- The README says the published code differs from DeepSeek's internal version and that some designs in its accompanying article are not implemented in this prototype; we did not check which.
- The source time is when the GitHub repository was created; we first saw the release through a press feed about a day later.

## Timeline

- Source published: 2026-10-31 09:32 UTC
- First seen by our watcher: 2026-11-01 10:00 UTC (via MarkTechPost feed)
- Brief published: 2026-11-01 10:09 UTC

## Sources

- [dsh-superagent repository and README (GitHub)](https://github.com/deepseek-ai/dsh-superagent-prototype) (primary source) (fetched 2026-11-01)
- [dsh-superagent deployment guide (docs/006-deployment.md)](https://github.com/deepseek-ai/dsh-superagent-prototype/blob/main/docs/006-deployment.md) (primary source) (fetched 2026-11-01)
- [dsh-superagent philosophy (docs/000-philosophy.md)](https://github.com/deepseek-ai/dsh-superagent-prototype/blob/main/docs/000-philosophy.md) (primary source) (fetched 2026-11-01)
- [dsh-superagent execution model (docs/003-execution.md)](https://github.com/deepseek-ai/dsh-superagent-prototype/blob/main/docs/003-execution.md) (primary source) (fetched 2026-11-01)

## Related

- [DeepSeek: verdict and setup guide](https://theagenticweekly.com/tools/deepseek)
- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)

## How to cite

Agentic Weekly, "DeepSeek open-sources dsh-superagent, a prototype agent that runs GitHub requests in parallel sessions", published 2026-11-01 10:09 UTC, https://theagenticweekly.com/news/deepseek-dsh-superagent-coding-agent-prototype