Privacy and advertising choices

Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy

LogoGit-Stars
Top StarsTrendingAI AgentsDaily PicksViral ReposInsights
LogoGit-Stars

Discover top GitHub projects with real rankings and AI insights

GitHub
Built withLogo of Git-StarsGit-Stars
Rankings
  • Top Stars
  • Trending
  • AI Agents
  • Daily Picks
  • Explore
Resources
  • Insights
  • Editorial Policy
About
  • About
  • Contact
Legal
  • Privacy Policy
  • Terms of Service
© 2026 Git-Stars. All Rights Reserved.
AI Agent Analysis
DH

deepseek-ai/deepseek-harness

DeepSeek Harness: Everything is a Plugin.

stars
116k
Language
TypeScript
GitHub
Source and compliance noteLast synced: Aug 16, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub sourceMethodologyEditorial Policy

Overview

DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI that adopts a plugin-based architecture where every component is a plugin, built on the Cordis framework. It provides a web UI for interacting with AI agents and emphasizes composability and extensibility, currently in developer preview with rapid iteration.

Installation

Run `npx @deepseek-ai/dsh web` (requires Node.js) or clone the repo and run `pnpm install && pnpm run build && pnpm dsh web`.

Problem solved

It addresses the challenge of building flexible and extensible AI agent systems by making every part a plugin, allowing developers to swap or compose components without tight coupling. This contrasts with monolithic agent frameworks, enabling easier customization and community-driven plugin sharing.

What you can build

Developers can build custom AI agent workflows with a modular plugin system, integrating various tools, models, and UI components. Real-world use cases include creating specialized assistants, automating complex tasks with custom tool integrations, and building multi-agent systems. The ceiling is high due to the plugin ecosystem and Cordis's composability paradigm, allowing for sophisticated spatiotemporal compositions.

Community sentiment

Positive

No community feedback yet.

Concerns

No concerns documented yet.

Bottom line

This is for developers who want a highly modular and extensible agent harness and are comfortable with rapid breaking changes during preview. Avoid if you need stability or a turnkey solution. The key trade-off is flexibility and composability versus maturity and stability.

Analyzed by Git-Stars - 8/16/2026