<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>GitHub Actions on Zhanwei Wang</title><link>https://zhanwei.wang/en/tags/github-actions/</link><description>Recent content in GitHub Actions on Zhanwei Wang</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 08 May 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://zhanwei.wang/en/tags/github-actions/index.xml" rel="self" type="application/rss+xml"/><item><title>We Built Ourselves an AI Coding Workbench — Using GitHub Actions as the Sandbox</title><link>https://zhanwei.wang/en/posts/ai-coding-workbench-on-gha/</link><pubDate>Fri, 08 May 2026 00:00:00 +0800</pubDate><guid>https://zhanwei.wang/en/posts/ai-coding-workbench-on-gha/</guid><description>&lt;h2 id="how-it-started"&gt;How it started&lt;/h2&gt;
&lt;p&gt;Over the last year or two, our team has been doing more and more coding work with AI. We started by running CLIs like Claude Code locally, and quickly hit a practical problem: &lt;strong&gt;every agent task I kicked off held my laptop hostage&lt;/strong&gt;. The agent was building, running tests, editing files, thinking about the next step; meanwhile I wanted to do something else, and the CPU fan started screaming. Forget about running five agents on five unrelated things at once.&lt;/p&gt;</description></item></channel></rss>