站内导读
定位:DeepSeek 团队公开的一个研究原型,是面向单个 GitHub 仓库的主动型编程智能体,探索更自主的智能体系统应如何以最少人力注意力换取最大价值。
核心能力
- 监听 GitHub 及可选的飞书消息,在被授权者提出需求时创建工作项
- 在独立的智能体会话与目录中完成任务,并在原对话里回复结果如 PR
- 仅在被请求或团队规则允许时行动,只在需要人处理时才发声
- 提供网页面板,集中展示需要人工关注的事项
- 安装与配置步骤较多,官方建议让编程智能体陪同按 SETUP.md 逐步完成
适用人群:研究智能体协作方式、想为单仓库试水自动化开发流程的团队与开发者。,先小范围试用再评估价值
注意:仅为研究参考代码,并非官方产品,可能含缺陷且部分设计尚未实现。
位置づけ:DeepSeekチームが公開した研究プロトタイプで、単一のGitHubリポジトリ向けの能動的なコーディングエージェントです。人の注意をできるだけ使わずに価値を出す、自律的なエージェントのあり方を探ります。
主な機能
- GitHubと任意でFeishuを監視し、許可された依頼で作業項目を作成
- 独自のセッションとディレクトリで作業し、元の会話にPRなどで回答
- 依頼された場合かチームのルールが許す場合にのみ行動し、必要な時だけ通知
- 人の対応が必要な事項を示すWebパネルを提供
- セットアップ手順が多いため、SETUP.mdに従ってコーディングエージェントと一緒に進める方法が案内されています
対象ユーザー:エージェント協働の設計を研究したい開発者や、単一リポジトリで自動化された開発フローを試したいチームです。
注意:公式製品ではなく研究用コードのため、バグや未実装の設計が含まれます。
정의: DeepSeek 팀이 공개한 연구용 프로토타입으로, 단일 GitHub 저장소를 담당하는 능동형 코딩 에이전트입니다. 사람의 주의를 최소로 쓰면서 가치를 내는 더 자율적인 에이전트 시스템의 방식을 탐구합니다.
핵심 기능
- GitHub와 선택적으로 Feishu를 듣고, 허용된 요청이 오면 작업 항목 생성
- 자체 세션과 디렉터리에서 작업하고 원래 대화에 PR 등으로 답변
- 요청받았거나 팀 규칙이 허용할 때만 행동하고, 사람이 필요할 때만 알림
- 사람의 처리가 필요한 사항을 보여주는 웹 패널 제공
대상 사용자: 에이전트 협업 설계를 연구하거나 단일 저장소에서 자동화된 개발 흐름을 시험하고 싶은 개발자와 팀입니다.
주의: 공식 제품이 아닌 연구용 코드로, 버그와 아직 구현되지 않은 설계가 포함될 수 있습니다.
What it is: dsh-superagent is a research prototype, not an official DeepSeek product, exploring a more autonomous agent system. Packaged as a bundle for DeepSeek Harness, it is a proactive coding agent for one GitHub repository that listens to GitHub and, optionally, Feishu, and follows a simple principle: take as little human attention as possible and give as much value as possible.
Key capabilities
- Opens a work item when someone allowed asks for work, then works in its own agent session and directory
- Answers in the original conversation, for example with a pull request, instead of creating separate threads
- Acts only when asked or when a rule the team wrote allows it, and speaks only when someone must act or can use a result
- Shows a web panel of what needs a person, keeping human attention focused on decisions
Who it is for: Developers and teams studying super-agent design or wanting to trial an autonomous coding workflow on a single repository.
Note: Treat it as research code, not production-ready software; it may contain bugs and some designs discussed in the related article are future directions not implemented here.
README · 详细文档
来源 · 查看原文
dsh-superagent
Research prototype for reference only, not an official DeepSeek product. This code grew out of our team's day-to-day development work, with much of the engineering done by coding agents. Treat it as research code, not production-ready software. It may still contain bugs, and its coding style and engineering practices may be inconsistent. Review and adapt it before using it in your own environment. We have adapted it for publication, so it is not identical to our internal version or the implementation described in Exploring Super-agent Design: Towards a More Autonomous Agent System. Some designs discussed in the article are directions for future development and are not implemented in this prototype.
dsh-superagent is a proactive coding agent for one GitHub repository, packaged as a bundle for DeepSeek Harness. It listens to GitHub and, optionally, Feishu. When someone allowed asks the agent for work, it opens a work item, works on it in its own agent session and directory, and answers in the original conversation, for example with a pull request. A web panel shows what needs a person.
It is also a way of working with an agent: take as little human attention as possible, and give as much value as possible. An agent that can act for a whole team can also waste a whole team's attention, so it acts only when asked or when a rule the team wrote allows it, and speaks only when someone must act or can use a result. docs/000-philosophy.md explains the principle and what it asks of the operator.
Setup
Setup has many steps, so an agent does it with you. Ask your coding agent:
Read SETUP.md in this repository and set up dsh-superagent with me.
It asks one short question at a time, shows the full plan once, and then installs and configures everything. SETUP.md is what it follows.
Documentation
Read the numbered documents in order; each builds only on the ones before it.
- 000 Philosophy
- 001 Domain model
- 002 Authorization
- 003 Execution
- 004 Prompts
- 005 Panel
- 006 Deployment: manual setup, configuration, upgrades and troubleshooting
- 007 Architecture
- 008 Cookbook: adding a Source
Development
pnpm check runs the typecheck, the tests and the build.
License
MIT