Top AI Repos β open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
π Two books on harness engineering β the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev
| Date | Stars |
|---|---|
| 2026-07-24 | 2698 |
| 2026-07-25 | 2701 |
| 2026-07-28 | 2701 |
| 2026-07-30 | 2701 |
| 2026-07-31 | 2715 |
| 2026-08-06 | 2715 |
Today
β stars today
This week
+14 stars this week
This month
β stars this month
Momentum
0.0
growth rate 0.52%/day
# Harness Books
[δΈζ README](./README.zh-CN.md)
[](https://harness-books.agentway.dev/en/)
[](https://agentway.dev)
Two books on harness engineering. They pursue the same engineering question: once a code-writing model is placed inside terminals, repositories, permission systems, and team workflows, what keeps the overall system bounded, continuous, and accountable for consequences?
<table>
<tr>
<td align="center" valign="top" width="50%">
<a href="https://harness-books.agentway.dev/en/book1-claude-code/">
<img src="./book1-claude-code/assets/cover-wxb-en.svg" alt="Harness Engineering: A Design Guide to Claude Code" width="280">
</a>
<br>
<strong>Harness Engineering: A Design Guide to Claude Code</strong>
<br>
<a href="https://harness-books.agentway.dev/en/book1-claude-code/">Read online</a> Β·
<a href="https://harness-books.agentway.dev/en/book1-claude-code/exported/book1-claude-code-en.pdf">Download PDF</a>
</td>
<td align="center" valign="top" width="50%">
<a href="https://harness-books.agentway.dev/en/book2-comparing/">
<img src="./book2-comparing/assets/cover-wxb-en.svg" alt="The Harness Design Philosophies of Claude Code and Codex" width="280">
</a>
<br>
<strong>The Harness Design Philosophies of Claude Code and Codex</strong>
<br>
<a href="https://harness-books.agentway.dev/en/book2-comparing/">Read online</a> Β·
<a href="https://harness-books.agentway.dev/en/book2-comparing/exported/book2-comparing-en.pdf">Download PDF</a>
</td>
</tr>
</table>
These books are not meant to walk line by line through the source code. They focus on how a harness organizes constraints and execution, and how an inherently unstable model can be folded into a sustainable engineering order. Prompt layering, query loops, permission decisions, context governance, failure recovery, multi-agent verification, local rules, and team institutions together form the organ system of a harness. The real danger is not that a model occasionally says something wrong, but that the system has no structure for handling consequences.
## Core Claims
- Harness engineering is about how constraint structures organize execution.
- Once a code-writing model enters a real engineering environment, the main problem is no longer answer quality but behavioral consequences.
- Prompts, tools, permissions, state, recovery, verification, and institutions are not accessories around the system. They are organs in the same control structure.
- When comparing agent systems, the key question is not the feature checklist but where order is actually placed.
- If a team cannot turn individual experience into reusable rules, it will struggle to turn an agent into a stable system.
## What The Two Books Focus On
### Book 1: A Design Guide to Claude Code
The first book uses Claude Code as the observation target and concentrates on runtime structure. Its concern is why a system eventually has to grow components such as a control plane, query loop, tool permissions, context governance, recovery paths, multi-agent verification, and team rules.
Start with Book 1 if these are the questions you care about:
- Why harness engineering is not just prompt engineering at a larger scale
- Why prompts are fundamentally part of the control plane rather than a chat box
- Why model mistakes should be treated as a runtime norm rather than an exceptional event
- Why multi-agent work and verification should not be blended into one vague mechanism
- How a team can solidify personal experience into reusable engineering institutions
### Book 2: Comparing Claude Code and Codex
The second book places Claude Code and Codex side by side and Excerpt of 9,974 characters
Read on GitHubWould you bet a product on this? Bounded 0β100 and slow moving.
matched fp:c7d756f17ac74da7, topic:ai-agents, topic:agentic-ai, desc:multi-agent
