DeepSeek Harness vs. Codex Harness: Competing Engineering Philosophies for AI Agents

ArticleMeng LiOpinion

In August 2026, OpenAI and DeepSeek both introduced execution harnesses for AI agents. Meng Li examines how their technical philosophies diverge.

Key points

  1. OpenAI made Codex Harness open source; it serves as the runtime for the ChatGPT desktop app, CLI, and VS Code extension.
  2. DeepSeek launched DeepSeek Harness (dsh) as a developer preview under the MIT licence, following an 'Everything is a plugin' architecture.
  3. The industry increasingly views agents through the formula Agent = Model + Harness, where models provide raw capability and the harness supplies operational control.
  4. Both frameworks illustrate two fundamentally different approaches to designing agent execution infrastructure.

Why it matters

Raw frontier models require execution layers to perform real-world development tasks. Understanding harness design helps engineering teams select the right foundation for custom agent tooling and integration.

Analysis

Because the source article is gated behind a paywall, only the introductory comparison is accessible. The author highlights the shift toward harness architecture as the primary engineering differentiator in autonomous coding workflows.

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Olimpiu Pop

    DeepSeek Harness: Modular Open-Source Runtime for AI Agents

    DeepSeek has released a developer preview of DeepSeek Harness (dsh) under the MIT licence. The execution runtime for autonomous artificial intelligence agents is built on the Cordis meta-framework using a micro-kernel architecture with interchangeable plugins.

    AI & LLMs· News

  • Link:DeepSeek

    DeepSeek Harness: Modular Open-Source Framework for AI Agents

    DeepSeek has launched a developer preview of DeepSeek Harness, an open-source runtime framework for AI agents. Built on the Cordis kernel, it implements an architecture where all capabilities are plugins alongside an append-only event stream for full traceability.

    AI & LLMs· Announcement

  • Repository:deepseek-ai/deepseek-harness

    DeepSeek Harness: Plugin-Based Open-Source AI Agent Framework

    DeepSeek Harness (dsh) is an open-source AI agent harness by DeepSeek AI. Built with TypeScript and Cordis, it uses an 'everything-is-a-plugin' architecture to provide modular agent capabilities and a Web UI.

    212.8kstarsTypeScript

    AI & LLMs· Tool

  • Article:Mehdi Allahyari

    The Harness Beats the Model: Demystifying Agent Harness Engineering

    Following prompt and context engineering, harness engineering marks the third wave in developing autonomous AI systems. Mehdi Allahyari explains why the software infrastructure wrapping an LLM matters more than raw model scale for reliability and self-correction.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.