Glean 拾遗
Daily /2026-08-22 / DeepSeek Harness: A Plugin-Centric Runtime for AI Agents

DeepSeek Harness: A Plugin-Centric Runtime for AI Agents

Source github.com Glean’d 2026-08-22 06:00 Read 2 min
AI summary

DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI with a plugin-everything architecture powered by Cordis, a framework designed around spatiotemporal composability. It is currently in developer preview, so breaking changes are expected. You can run it from npm or from source, and it launches a local Web UI at 127.0.0.1:3080 by default. The project aims to be a modular runtime for building and operating AI agents, and is suited for engineers who want an extensible, self-hosted agent infrastructure rather than a closed product. Community support is available via GitHub Discussions and Discord, and plugins can use the 'dsh-plugin' topic for discoverability.

Original · 2 min
github.com ↗
§ 1

DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI, built as a plugin-centric runtime for AI agents. Instead of a monolithic framework, dsh treats every capability as a plugin and relies on the Cordis runtime for orchestration. It is aimed at developers who want to assemble, run, and observe agent workflows through a Web UI.

DeepSeek Harness(简称 dsh)是 DeepSeek AI 开源的一个 agent 运行时框架(harness)。它采用以插件为中心(plugin-centric)的架构,把每项能力都做成插件,再交由 Cordis 运行时统一编排。面向希望在 Web UI 中组装、运行和观测 agent 工作流的开发者。

§ 2

The core design statement is simple: everything is a plugin. dsh does not hard-code components; instead, capabilities are contributed and connected as plugins. The runtime relies on Cordis, whose design is described in the paper 'A Programming Paradigm for Spatiotemporal Composability.' This makes the harness highly composable and extensible, though the project is still iterating quickly.

核心设计一句话:一切皆插件。dsh 不把组件写死,而是让各种能力以插件形式注入和联动。运行时基于 Cordis,后者在论文《A Programming Paradigm for Spatiotemporal Composability》中阐述了设计思想。这种设计让整个 harness 具备很强的组合性与可扩展性,但项目仍在快速迭代中。

§ 3

DeepSeek Harness is explicitly in developer preview. The README warns that the project is iterating rapidly and compatibility-breaking changes will occur. Developers who plan to adopt it should be prepared to track updates closely and pin versions.

DeepSeek Harness 明确处于开发者预览(developer preview)阶段。README 特别提醒:项目迭代极快,必然会有破坏兼容性的变更(compatibility-breaking changes)。因此打算采用它的人需要紧盯更新、锁定版本。

§ 4

The project requires Node.js. When launched via npm, the command starts the Web UI at http://127.0.0.1:3080 by default and opens it in the default browser; pass --no-open to run without opening a browser. SSH launches only print the host URL. To run from a repository checkout, use:

git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web

pnpm run build prepares the repository artifacts, and pnpm dsh web uses those artifacts without rebuilding.

运行项目需要 Node.js。通过 npm 启动时,命令默认会在 http://127.0.0.1:3080 启动 Web UI,并在默认浏览器中打开;传 --no-open 可只启动服务器、不打开浏览器。SSH 方式启动时只会打印主机地址。从源码运行,执行:

git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web

pnpm run build 用来准备好仓库构建产物,pnpm dsh web 直接使用这些产物,不会重新构建。

§ 5

Feedback and bug reports go through GitHub Discussions. Plugin authors can add the dsh-plugin topic to their repositories for discoverability. There is also a Discord community for real-time discussion. Contributions should follow CONTRIBUTING.md; new developers can start with the development guide, architecture docs, and AGENTS.md.

反馈与 bug 报告通过 GitHub Discussions 提交。插件作者可以给自己的仓库打上 dsh-plugin 主题标签,方便被检索。项目还设有 Discord 社区供实时交流。贡献代码请遵循 CONTRIBUTING.md;新开发者可先阅读开发指南、架构文档和 AGENTS.md

§ 6

dsh fits developers building custom agent workflows who want a plugin-based, UI-observable harness. Because it is in developer preview, it is not yet a stable foundation for production systems. The README does not include benchmark numbers or a detailed feature list, so evaluation should be hands-on.

dsh 适合那些想自定义 agent 工作流、希望拥有插件化且可在 Web UI 中观测的 harness 的开发者。由于处于开发者预览期,它还不适合作为生产系统的稳定底座。README 没有提供基准测试数字或详细功能清单,判断它是否合身最好亲手跑一跑。

Open source ↗