DeepSeek open-sources dsh-superagent, a research-prototype GitHub coding agent
READ THE ORIGINAL SOURCEOpen original sourcegithub.com · Opens in a new tabdsh-superagent is a research prototype coding agent packaged for DeepSeek Harness. It serves one GitHub repository and listens to GitHub and optionally Feishu. When an allowed person 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 items needing human action. The README stresses the design principle of minimizing human attention, acting only when asked or when a team-written rule allows it. It states the code is not an official DeepSeek product and is not production-ready.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · automated brief
- Discovery linkX
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
Open full article view →- Original repository+40
- Feed text or abstract+15
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
dsh-superagent is a research prototype coding agent packaged for DeepSeek Harness. It serves one GitHub repository and listens to GitHub and optionally Feishu. When an allowed person 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 items needing human action. The README stresses the design principle of minimizing human attention, acting only when asked or when a team-written rule allows it. It states the code is not an official DeepSeek product and is not production-ready.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: github.com. Brief basis: repository README. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; the README itself says the published code differs from the internal version and some article designs are unimplemented.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- The agent handles work for one GitHub repository and responds to requests from allowed users on GitHub or Feishu.
- Each work item runs in its own agent session and directory, and results are returned in the original conversation, such as a pull request.
- A web panel surfaces items that require a person to act.
- The README labels it a research prototype, not an official DeepSeek product, and says it may contain bugs.
Source claims not independently checked; the README itself says the published code differs from the internal version and some article designs are unimplemented.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
DeepSeek published dsh-superagent (MIT), a proactive coding agent for one GitHub repo, packaged for DeepSeek Harness: it listens to GitHub (optionally Feishu), opens work items and answers with pull requests. DeepSeek labels it a research prototype, not an official product, and says it differs from its internal version and its Super-agent Design article. Created Oct 31; 3.3k stars in under a day.
Source claims not independently checked; the README itself says the published code differs from the internal version and some article designs are unimplemented.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
- hn post ↗ · 5 points, 0 comments · observed 11/1/2026, 4:02:34 AM
- x post ↗ · 723 likes, 80 reposts, 40 replies, 16 quotes · observed 11/1/2026, 4:02:23 AM
- github post ↗ · 3,344 stars, 300 forks · observed 11/1/2026, 3:59:55 AM
- Related post ↗
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from repository README.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
It offers a concrete open reference for how a coding agent can be embedded into team workflows with authorization and limited interruptions. Developers evaluating agent architectures can inspect its design documents and code.
Limits and open questions
Source claims not independently checked; the README itself says the published code differs from the internal version and some article designs are unimplemented.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.