<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Development on snowdon.dev</title><link>https://snowdon.dev/tags/development/</link><description>Recent content in Development on snowdon.dev</description><generator>Hugo</generator><language>en</language><managingEditor>hello@snowdon.dev (snowdon.dev)</managingEditor><webMaster>hello@snowdon.dev (snowdon.dev)</webMaster><lastBuildDate>Mon, 07 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://snowdon.dev/tags/development/index.xml" rel="self" type="application/rss+xml"/><item><title>Run OpenCode in a Secure, Portable Docker Development Environment</title><link>https://snowdon.dev/post/introducing-opencode-docker/</link><pubDate>Mon, 07 Sep 2026 00:00:00 +0000</pubDate><author>hello@snowdon.dev (snowdon.dev)</author><guid>https://snowdon.dev/post/introducing-opencode-docker/</guid><description>&lt;p&gt;AI coding agents are powerful, but giving an agent unrestricted access to your&#10;development machine can be uncomfortable. You want the convenience of an&#10;AI-powered development workflow without turning your entire host system into&#10;the agent&amp;rsquo;s playground.&lt;/p&gt;&#10;&lt;p&gt;That&amp;rsquo;s where&#10;&lt;a href="https://github.com/snowdon-dev/opencode-docker"&gt;&lt;strong&gt;snowdon-dev/opencode-docker&lt;/strong&gt;&lt;/a&gt; comes in.&lt;/p&gt;&#10;&lt;p&gt;OpenCode doesn&amp;rsquo;t impose an opinion on the sandbox its agents run in, and&#10;opencode-docker takes advantage of that. It is a security- and&#10;human-control-oriented workflow for running &lt;a href="https://opencode.ai/"&gt;OpenCode&lt;/a&gt;&#10;inside Docker containers. Your project is available inside the container at&#10;&lt;code&gt;/workspace/project&lt;/code&gt;, while toolchain caches for Go, Rust, Node.js and Python&#10;persist between runs.&lt;/p&gt;</description></item></channel></rss>