DeepSeek发布自主Agent原型dsh-superagent
deepseek-ai/dsh-superagent-prototype: Towards a More Autonomous Agent System
Towards a More Autonomous Agent System
迈向更自主的代理系统
GitHub repository created 2026-10-31 · 1472 stars in 0.3 days (about 1472 a day) · TypeScript
GitHub 仓库创建于 2026-10-31 · 0.3 天内获得 1472 颗星（约每天 1472 颗）· TypeScript
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.
> 仅供研究的原型，并非 DeepSeek 官方产品。此代码源于我们团队的日常开发工作，大部分工程实现由编码代理完成。请将其视为研究代码，而非生产就绪的软件。它可能仍包含错误，且其编码风格和工程实践可能不一致。在您的环境中使用前，请审查并对其进行适配。 > > 我们已对其进行了发布适配，因此它与我们的内部版本或《探索超级代理设计：迈向更自主的代理系统》一文中描述的实现在细节上并不完全相同。文章中讨论的一些设计是未来发展的方向，并未在此原型中实现。
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.
dsh-superagent 是一个针对单个 GitHub 仓库的主动式编码代理，打包为 DeepSeek Harness 的捆绑包。它监听 GitHub 和可选的飞书。当被授权的某人请求代理工作时，它会打开一个工作项，在自己的代理会话和目录中处理该工作项，并在原始对话中回复，例如通过拉取请求（Pull Request）。Web 面板会显示哪些事项需要人工介入。
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.
这也是一种与代理协作的工作方式：尽可能减少人类注意力的投入，同时提供尽可能多的价值。能够代表整个团队行动的代理也可能浪费整个团队的注意力，因此它仅在受邀或被团队制定的规则允许时才行动，并且仅在人必须采取行动或有人可以使用结果时才发声。docs/000-philosophy.md 解释了这一原则及其对操作者的要求。
Setup
设置
Setup has many steps, so an agent does it with you. Ask your coding agent:
设置步骤繁多，因此代理将与您一起完成。请向您的编码代理提问：
> Read SETUP.md in this repository and set up dsh-superagent with me.
> 阅读本仓库中的 SETUP.md，并与我一起设置 dsh-superagent。
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.
它会一次询问一个简短的问题，一次性展示完整计划，然后安装并配置所有内容。SETUP.md 是它所遵循的指南。
Documentation
文档
Read the numbered documents in order; each builds only on the ones before it.
按顺序阅读编号文档；每篇文档仅基于前面的文档构建。
- 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
- 000 哲学 - 001 领域模型 - 002 授权 - 003 执行 - 004 提示词 - 005 面板 - 006 部署：手动设置、配置、升级和故障排除 - 007 架构 - 008 食谱：添加数据源（Source）
Development
开发
`pnpm check` runs the typecheck, the tests and the build.
`pnpm check` 运行类型检查、测试和构建。
License
许可证
MIT
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力