shareAI-lab/learn-claude-code: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 ·
github.com · 3,112 words · saved by 1 readers
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
English | 中文 | 日本語 Learn Claude Code -- Harness Engineering for Real Agents Agency Comes from the Model. An Agent Product = Model + Harness. Before we write any code, one thing needs to be clear. Agency -- the capacity to perceive, reason, and act -- comes from model training, not from external code orchestration. But a working agent product needs both the model and the harness. The model is the driver. The harness is the vehicle. This repository teaches you how to build the vehicle. Where Agency Comes From At the core of every agent is a neural network -- a Transformer, an RNN, a…
saved by
related reading
- How to Harness Coding Agents with the Right Infrastructure | Blogalexlavaee.me
- Lecture 01. Strong Models Don't Mean Reliable Execution | Learn Harness Engineeringwalkinglabs.github.io
- Welcome to Learn Harness Engineeringwalkinglabs.github.io
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Inside Coding Agentsvpromise.github.io
- Towards self-driving codebases · Cursorcursor.com
- What is an Agent Harness?rubriclabs.com
- Harness design for long-running application developmentanthropic.com
- sysls on X: "How To Be A World-Class Agentic Engineer" / Xx.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- What I learned building an opinionated and minimal coding agentmariozechner.at